diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..b2fd9eefc9bc7f77fa55c60257a6bf150595a3d3 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +*.tar.gz filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 32897cd3e640101ba184f8c4ccd896981de3804a..59dba63f5d7a311e4d8cc3f12d513bc3945c6378 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,7 @@ --- license: mit --- + +Voices for [Piper](https://github.com/rhasspy/piper) text to speech system. + +For checkpoints that you can use to [train your own voices](https://github.com/rhasspy/piper/blob/master/TRAINING.md), see [piper-checkpoints](https://huggingface.co/datasets/rhasspy/piper-checkpoints/tree/main) diff --git a/ca/ca_ES/upc_ona/medium/MODEL_CARD b/ca/ca_ES/upc_ona/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..f37cccd8c075a014c6affbc29dd5b48d186868a2 --- /dev/null +++ b/ca/ca_ES/upc_ona/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for upc_ona (medium) + +* Language: ca_ES (Catalan, Spain) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://collectivat.cat/asr#upc-festcat-tts-corpora +* License: CC BY-SA 3.0 ES + +## Training + +Finetuned from U.S English lessac voice (medium quality). diff --git a/ca/ca_ES/upc_ona/medium/ca_ES-upc_ona-medium.onnx b/ca/ca_ES/upc_ona/medium/ca_ES-upc_ona-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..e7d829edacc7ff678d24fffd5d5cf43f6c0b666f --- /dev/null +++ b/ca/ca_ES/upc_ona/medium/ca_ES-upc_ona-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb652db8c11a4475527346cf3241cb064d1ba393cf370f3f2ec09a872d118fd +size 63201294 diff --git a/ca/ca_ES/upc_ona/medium/ca_ES-upc_ona-medium.onnx.json b/ca/ca_ES/upc_ona/medium/ca_ES-upc_ona-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..97204198ce32ecb0b69b6fc96f346bbd4c6c0234 --- /dev/null +++ b/ca/ca_ES/upc_ona/medium/ca_ES-upc_ona-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "ca" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/ca/ca_ES/upc_ona/x_low/MODEL_CARD b/ca/ca_ES/upc_ona/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..28af710860cbf25b5c16d4e718f4c4a1524b493f --- /dev/null +++ b/ca/ca_ES/upc_ona/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for upc_ona (x_low) + +* Language: ca_ES (Catalan, Spain) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://collectivat.cat/asr#upc-festcat-tts-corpora +* License: CC BY-SA 3.0 ES + +## Training + +Trained from scratch. diff --git a/ca/ca_ES/upc_ona/x_low/ca_ES-upc_ona-x_low.onnx b/ca/ca_ES/upc_ona/x_low/ca_ES-upc_ona-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..27fee8f95905a13e9830211f2e628c4fe548006e --- /dev/null +++ b/ca/ca_ES/upc_ona/x_low/ca_ES-upc_ona-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13661d26423e0c791823823a5971f4e1aaf644a62e65e0e94d299c0e70560e14 +size 20628813 diff --git a/ca/ca_ES/upc_ona/x_low/ca_ES-upc_ona-x_low.onnx.json b/ca/ca_ES/upc_ona/x_low/ca_ES-upc_ona-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..3d0ed8bd53a208d5b6d99850358009f572da8e56 --- /dev/null +++ b/ca/ca_ES/upc_ona/x_low/ca_ES-upc_ona-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "ca" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/ca/ca_ES/upc_pau/x_low/MODEL_CARD b/ca/ca_ES/upc_pau/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..80efef44a88a48e311a1d2b3c4cfaf79a32d59ed --- /dev/null +++ b/ca/ca_ES/upc_pau/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for upc_pau (x_low) + +* Language: ca_ES (Catalan, Spain) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://collectivat.cat/asr#upc-festcat-tts-corpora +* License: CC BY-SA 3.0 ES + +## Training + +Trained from scratch. diff --git a/ca/ca_ES/upc_pau/x_low/ca_ES-upc_pau-x_low.onnx b/ca/ca_ES/upc_pau/x_low/ca_ES-upc_pau-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..6b9bd1fc3cb39e4e8654a19465f24405dfd418fe --- /dev/null +++ b/ca/ca_ES/upc_pau/x_low/ca_ES-upc_pau-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c936a1a78b0a795af3c2422a0f2edb26303c389ff961616902ba12e26b489071 +size 28130791 diff --git a/ca/ca_ES/upc_pau/x_low/ca_ES-upc_pau-x_low.onnx.json b/ca/ca_ES/upc_pau/x_low/ca_ES-upc_pau-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..3d0ed8bd53a208d5b6d99850358009f572da8e56 --- /dev/null +++ b/ca/ca_ES/upc_pau/x_low/ca_ES-upc_pau-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "ca" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/da/da_DK/talesyntese/medium/MODEL_CARD b/da/da_DK/talesyntese/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..baebdac8d20150090bab97b524b04b73573c1193 --- /dev/null +++ b/da/da_DK/talesyntese/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for talesyntese (medium) + +* Language: da_DK (Danish, Denmark) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-21/ +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/da/da_DK/talesyntese/medium/da_DK-talesyntese-medium.onnx b/da/da_DK/talesyntese/medium/da_DK-talesyntese-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..03209209e740457ddbacfadcef8237895882261f --- /dev/null +++ b/da/da_DK/talesyntese/medium/da_DK-talesyntese-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9271efd25f7b8494bbd28d48dd675c8c119daa284f3ee488008935f515f1241 +size 63201294 diff --git a/da/da_DK/talesyntese/medium/da_DK-talesyntese-medium.onnx.json b/da/da_DK/talesyntese/medium/da_DK-talesyntese-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..a167c7bb0fbd99cc453b8d3049b9b02600bcf0ab --- /dev/null +++ b/da/da_DK/talesyntese/medium/da_DK-talesyntese-medium.onnx.json @@ -0,0 +1,482 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "da" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/de/de_DE/eva_k/x_low/MODEL_CARD b/de/de_DE/eva_k/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..4255b7b127ea1ca0b5dc2c3d3da94181b1577a32 --- /dev/null +++ b/de/de_DE/eva_k/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for eva_k (x_low) + +* Language: de (German) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/ +* License: See URL + +## Training + +Trained from scratch. diff --git a/de/de_DE/eva_k/x_low/de_DE-eva_k-x_low.onnx b/de/de_DE/eva_k/x_low/de_DE-eva_k-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..401b967bfbf237807f9ed3a38474ef6a2f3bddd7 --- /dev/null +++ b/de/de_DE/eva_k/x_low/de_DE-eva_k-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88cf290fbfb768bf111330d2e8a46e376b0d85e3423a28bfebbc863a260dad8 +size 20628813 diff --git a/de/de_DE/eva_k/x_low/de_DE-eva_k-x_low.onnx.json b/de/de_DE/eva_k/x_low/de_DE-eva_k-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..6ca1a4ce8428977639198a83a3633e2929f60900 --- /dev/null +++ b/de/de_DE/eva_k/x_low/de_DE-eva_k-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "de" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/de/de_DE/karlsson/low/MODEL_CARD b/de/de_DE/karlsson/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..86307058b813506071c8ad0f12f122ca6a7ef79f --- /dev/null +++ b/de/de_DE/karlsson/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for karlsson (low) + +* Language: de_DE (German, Germany) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/ +* License: See URL + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/de/de_DE/karlsson/low/de_DE-karlsson-low.onnx b/de/de_DE/karlsson/low/de_DE-karlsson-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..1f4be24f9fe518d56ced944033bfb4fc862a94b0 --- /dev/null +++ b/de/de_DE/karlsson/low/de_DE-karlsson-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9793bf7e461a472b3916cf260774bfc9812e9eb72601b147ed649d01064e8fe +size 63104526 diff --git a/de/de_DE/karlsson/low/de_DE-karlsson-low.onnx.json b/de/de_DE/karlsson/low/de_DE-karlsson-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..6ca1a4ce8428977639198a83a3633e2929f60900 --- /dev/null +++ b/de/de_DE/karlsson/low/de_DE-karlsson-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "de" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/de/de_DE/kerstin/low/MODEL_CARD b/de/de_DE/kerstin/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..2da47e36d5507784368e1d4dc6b9e7394e6cc3c8 --- /dev/null +++ b/de/de_DE/kerstin/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for kerstin (low) + +* Language: de_DE (German, Germany) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/rhasspy/dataset-voice-kerstin +* License: CC0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/de/de_DE/kerstin/low/de_DE-kerstin-low.onnx b/de/de_DE/kerstin/low/de_DE-kerstin-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..bcc407e33d6beb48c01332eeb2b54eb569813167 --- /dev/null +++ b/de/de_DE/kerstin/low/de_DE-kerstin-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d352a7641892cebf2903859af94e9ba81a141110215fe3943bcda7f7da401b7a +size 63104526 diff --git a/de/de_DE/kerstin/low/de_DE-kerstin-low.onnx.json b/de/de_DE/kerstin/low/de_DE-kerstin-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..6ca1a4ce8428977639198a83a3633e2929f60900 --- /dev/null +++ b/de/de_DE/kerstin/low/de_DE-kerstin-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "de" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/de/de_DE/pavoque/low/MODEL_CARD b/de/de_DE/pavoque/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..e2a535a9cb28eacc8e0888b96b34036ffecf8858 --- /dev/null +++ b/de/de_DE/pavoque/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for pavoque (low) + +* Language: de_DE (German, Germany) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/marytts/pavoque-data +* License: http://creativecommons.org/licenses/by-nc-sa/4.0/ + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/de/de_DE/pavoque/low/de_DE-pavoque-low.onnx b/de/de_DE/pavoque/low/de_DE-pavoque-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d6ebd6f6124e9f23feca98a21fc287659d8daa0a --- /dev/null +++ b/de/de_DE/pavoque/low/de_DE-pavoque-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96cd41fe2303dfe4745422a2580658bdbc5f935b7ee67640a94da7435a502a26 +size 63104526 diff --git a/de/de_DE/pavoque/low/de_DE-pavoque-low.onnx.json b/de/de_DE/pavoque/low/de_DE-pavoque-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..6ca1a4ce8428977639198a83a3633e2929f60900 --- /dev/null +++ b/de/de_DE/pavoque/low/de_DE-pavoque-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "de" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/de/de_DE/ramona/low/MODEL_CARD b/de/de_DE/ramona/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..17fda96a36dec4d0a9ff5fcb4b99cae42f52a728 --- /dev/null +++ b/de/de_DE/ramona/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for ramona (low) + +* Language: de_DE (German, Germany) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/ +* License: See URL + +## Training + +Trained from scratch. diff --git a/de/de_DE/ramona/low/de_DE-ramona-low.onnx b/de/de_DE/ramona/low/de_DE-ramona-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..2550d88cd2e7fa185ccfac25dff6fc666aac616c --- /dev/null +++ b/de/de_DE/ramona/low/de_DE-ramona-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1068592532aad8c49bf3d1a01b8749c11d7dba726689ee28ad64e7b627ae4c5 +size 63104526 diff --git a/de/de_DE/ramona/low/de_DE-ramona-low.onnx.json b/de/de_DE/ramona/low/de_DE-ramona-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..6ca1a4ce8428977639198a83a3633e2929f60900 --- /dev/null +++ b/de/de_DE/ramona/low/de_DE-ramona-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "de" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/de/de_DE/thorsten/low/MODEL_CARD b/de/de_DE/thorsten/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..26b311678d6725c7550bf248fce613b317f70280 --- /dev/null +++ b/de/de_DE/thorsten/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for Thorsten (low) + +* Language: de_DE (German, Germany) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/thorstenMueller/Thorsten-Voice +* License: CC0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/de/de_DE/thorsten/low/de_DE-thorsten-low.onnx b/de/de_DE/thorsten/low/de_DE-thorsten-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d3649202e19ebfba36a5cf0ecf11ff94baa65406 --- /dev/null +++ b/de/de_DE/thorsten/low/de_DE-thorsten-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac27fad17cec5c1a791161976a64f026f16fc058b400b1fea62565b8b2cf375 +size 63104526 diff --git a/de/de_DE/thorsten/low/de_DE-thorsten-low.onnx.json b/de/de_DE/thorsten/low/de_DE-thorsten-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..6ca1a4ce8428977639198a83a3633e2929f60900 --- /dev/null +++ b/de/de_DE/thorsten/low/de_DE-thorsten-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "de" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/de/de_DE/thorsten/medium/MODEL_CARD b/de/de_DE/thorsten/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..4b0095781c1867ad86f561d5b692472fbea25895 --- /dev/null +++ b/de/de_DE/thorsten/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for thorsten (medium) + +* Language: de_DE (German, Germany) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/thorstenMueller/Thorsten-Voice +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/de/de_DE/thorsten/medium/de_DE-thorsten-medium.onnx b/de/de_DE/thorsten/medium/de_DE-thorsten-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..b9118e0f672b24a1da4e04872f23ed27a9d8b55f --- /dev/null +++ b/de/de_DE/thorsten/medium/de_DE-thorsten-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e64762d8e5118bb578f2eea6207e1a35a8e0c30595010b666f983fc87bb7819 +size 63201294 diff --git a/de/de_DE/thorsten/medium/de_DE-thorsten-medium.onnx.json b/de/de_DE/thorsten/medium/de_DE-thorsten-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..0542e8f181bd26e8b855325e683bbfbf2ac57b53 --- /dev/null +++ b/de/de_DE/thorsten/medium/de_DE-thorsten-medium.onnx.json @@ -0,0 +1,477 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "de" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/el/el_GR/rapunzelina/low/MODEL_CARD b/el/el_GR/rapunzelina/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..c271b0d3d4d89b2be1c9f9222759f289dd2c40ed --- /dev/null +++ b/el/el_GR/rapunzelina/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for rapunzelina (low) + +* Language: el_GR (Greek, Greece) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://www.kaggle.com/datasets/bryanpark/greek-single-speaker-speech-dataset +* License: CC0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/el/el_GR/rapunzelina/low/el_GR-rapunzelina-low.onnx b/el/el_GR/rapunzelina/low/el_GR-rapunzelina-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ba35766a92e2330ddc4706021399410cceff7ed6 --- /dev/null +++ b/el/el_GR/rapunzelina/low/el_GR-rapunzelina-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebb335946c5d868743ff35fbb66b6f00e431b5b9b2e18caf47d3f609a2bf2e1 +size 63104526 diff --git a/el/el_GR/rapunzelina/low/el_GR-rapunzelina-low.onnx.json b/el/el_GR/rapunzelina/low/el_GR-rapunzelina-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..a0209ae47f41bcac3709097c25e4dabec4210c4e --- /dev/null +++ b/el/el_GR/rapunzelina/low/el_GR-rapunzelina-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "el" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/en/en_GB/alan/low/MODEL_CARD b/en/en_GB/alan/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..44ebf1a5833f34a4976476b65f7ff27797f5eff9 --- /dev/null +++ b/en/en_GB/alan/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for alan (low) + +* Language: en_GB (English, Great Britain) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/MycroftAI/mimic3-voices/blob/master/voices/en_UK/apope_low +* License: See URL + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/en/en_GB/alan/low/en_GB-alan-low.onnx b/en/en_GB/alan/low/en_GB-alan-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..4fbb7895c9414b5cf929461c92ce2f7673b41cce --- /dev/null +++ b/en/en_GB/alan/low/en_GB-alan-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1f60584620a2bed203de823d08f5abb336fb15f3d6f33f8c341e3e2cabf5dde +size 63104526 diff --git a/en/en_GB/alan/low/en_GB-alan-low.onnx.json b/en/en_GB/alan/low/en_GB-alan-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..17194cf2306a47b06a7887a9b7c3914c78fcf8cd --- /dev/null +++ b/en/en_GB/alan/low/en_GB-alan-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "en-gb-x-rp" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/en/en_GB/alan/medium/MODEL_CARD b/en/en_GB/alan/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..095e2701e47cf8c3e5a44c01122ffbcd42405b84 --- /dev/null +++ b/en/en_GB/alan/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for alan (medium) + +* Language: en_GB (English, Great Britain) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/MycroftAI/mimic3-voices/blob/master/voices/en_UK/apope_low +* License: See URL + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_GB/alan/medium/en_GB-alan-medium.onnx b/en/en_GB/alan/medium/en_GB-alan-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..2ac9c14965ab564630cdf8cb497be802eafbaf6c --- /dev/null +++ b/en/en_GB/alan/medium/en_GB-alan-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a309668932205e762801f1efc2736cd4b0120329622adf62be09e56339d3330 +size 63201294 diff --git a/en/en_GB/alan/medium/en_GB-alan-medium.onnx.json b/en/en_GB/alan/medium/en_GB-alan-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..d4cd5cb7b87c17561e484905e83cf8706bb0966c --- /dev/null +++ b/en/en_GB/alan/medium/en_GB-alan-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-gb-x-rp" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_GB/alba/medium/MODEL_CARD b/en/en_GB/alba/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..61e578c81ce2f7d59fb6c8840d8290ae29efb45c --- /dev/null +++ b/en/en_GB/alba/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for alba (medium) + +* Language: en_GB (English, Great Britain) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://datashare.ed.ac.uk/handle/10283/3270 +* License: https://creativecommons.org/licenses/by/4.0/ + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_GB/alba/medium/en_GB-alba-medium.onnx b/en/en_GB/alba/medium/en_GB-alba-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..e1e90ce2f071e4e97ef6ef268b16e72a01987642 --- /dev/null +++ b/en/en_GB/alba/medium/en_GB-alba-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:401369c4a81d09fdd86c32c5c864440811dbdcc66466cde2d64f7133a66ad03b +size 63201294 diff --git a/en/en_GB/alba/medium/en_GB-alba-medium.onnx.json b/en/en_GB/alba/medium/en_GB-alba-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..d4cd5cb7b87c17561e484905e83cf8706bb0966c --- /dev/null +++ b/en/en_GB/alba/medium/en_GB-alba-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-gb-x-rp" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_GB/aru/medium/MODEL_CARD b/en/en_GB/aru/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..667bfe0d72942adb50ef85bdb4f34db65fe47764 --- /dev/null +++ b/en/en_GB/aru/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for aru (medium) + +* Language: en_GB (English, Great Britain) +* Speakers: 12 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.liverpool.ac.uk/architecture/research/acoustics-research-unit/speech-corpus/ +* License: https://creativecommons.org/licenses/by/4.0/ + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_GB/aru/medium/en_GB-aru-medium.onnx b/en/en_GB/aru/medium/en_GB-aru-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..87a14086ede68c1d7f80b8c5142a26bf02d55346 --- /dev/null +++ b/en/en_GB/aru/medium/en_GB-aru-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e74d089a8563f8b2446426d01becb046cd3c3bfbafe1a20fd03a9a79bd82619 +size 76754097 diff --git a/en/en_GB/aru/medium/en_GB-aru-medium.onnx.json b/en/en_GB/aru/medium/en_GB-aru-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..9287a98030ef875db52a4c6ceb16197f51589080 --- /dev/null +++ b/en/en_GB/aru/medium/en_GB-aru-medium.onnx.json @@ -0,0 +1,496 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-gb-x-rp" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 12, + "speaker_id_map": { + "03": 0, + "06": 1, + "10": 2, + "01": 3, + "09": 4, + "08": 5, + "11": 6, + "05": 7, + "12": 8, + "02": 9, + "07": 10, + "04": 11 + }, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_GB/jenny_dioco/medium/MODEL_CARD b/en/en_GB/jenny_dioco/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..cbce04cd9197c5889ff62edcd56b2b87c7684163 --- /dev/null +++ b/en/en_GB/jenny_dioco/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for jenny_dioco (medium) + +* Language: en_GB (English, Great Britain) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/dioco-group/jenny-tts-dataset +* License: See URL + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_GB/jenny_dioco/medium/en_GB-jenny_dioco-medium.onnx b/en/en_GB/jenny_dioco/medium/en_GB-jenny_dioco-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..606e942874870a3e854f0b1a1ae7ef8f2cb683b2 --- /dev/null +++ b/en/en_GB/jenny_dioco/medium/en_GB-jenny_dioco-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:469c630d209e139dd392a66bf4abde4ab86390a0269c1e47b4e5d7ce81526b01 +size 63201294 diff --git a/en/en_GB/jenny_dioco/medium/en_GB-jenny_dioco-medium.onnx.json b/en/en_GB/jenny_dioco/medium/en_GB-jenny_dioco-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..d4cd5cb7b87c17561e484905e83cf8706bb0966c --- /dev/null +++ b/en/en_GB/jenny_dioco/medium/en_GB-jenny_dioco-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-gb-x-rp" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_GB/northern_english_male/medium/MODEL_CARD b/en/en_GB/northern_english_male/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..492a27e88841f2201eebba52d83c521a521bf1fa --- /dev/null +++ b/en/en_GB/northern_english_male/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for northern_english_male (medium) + +* Language: en_GB (English, Great Britain) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: http://www.openslr.org/83/ +* License: CC-BY-SA 4.0 International + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_GB/northern_english_male/medium/en_GB-northern_english_male-medium.onnx b/en/en_GB/northern_english_male/medium/en_GB-northern_english_male-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0455cee2e68a4efa33e3c1d69b766f8970fd3cb6 --- /dev/null +++ b/en/en_GB/northern_english_male/medium/en_GB-northern_english_male-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57a219ae8e638873db7d18893304be5069c42868f392bb95c3ff17f0690d0689 +size 63201294 diff --git a/en/en_GB/northern_english_male/medium/en_GB-northern_english_male-medium.onnx.json b/en/en_GB/northern_english_male/medium/en_GB-northern_english_male-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..051c4d5f3d7ff9ae139affaedcd1f298816943cc --- /dev/null +++ b/en/en_GB/northern_english_male/medium/en_GB-northern_english_male-medium.onnx.json @@ -0,0 +1,477 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-gb-x-rp" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_GB/southern_english_female/low/MODEL_CARD b/en/en_GB/southern_english_female/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..ab8a038fc5b744a548f7150edeb35b1c1a35d6a3 --- /dev/null +++ b/en/en_GB/southern_english_female/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for southern_english_female (low) + +* Language: en_GB (English, Great Britain) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: http://www.openslr.org/83/ +* License: CC-BY-SA 4.0 International + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/en/en_GB/southern_english_female/low/en_GB-southern_english_female-low.onnx b/en/en_GB/southern_english_female/low/en_GB-southern_english_female-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..b1304bd85680a323f627749e8cec9b8652248e24 --- /dev/null +++ b/en/en_GB/southern_english_female/low/en_GB-southern_english_female-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f37aed1b3a093476f719d1379ba0c0b1b1cf6f1ef99288e2ebf502971a07c3 +size 63104526 diff --git a/en/en_GB/southern_english_female/low/en_GB-southern_english_female-low.onnx.json b/en/en_GB/southern_english_female/low/en_GB-southern_english_female-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..17194cf2306a47b06a7887a9b7c3914c78fcf8cd --- /dev/null +++ b/en/en_GB/southern_english_female/low/en_GB-southern_english_female-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "en-gb-x-rp" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/en/en_GB/vctk/medium/MODEL_CARD b/en/en_GB/vctk/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..ead7f850edbce2c5e0a2af5749e5c8afcf99f454 --- /dev/null +++ b/en/en_GB/vctk/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for vctk (medium) + +* Language: en_GB (English, Great Britain) +* Speakers: 109 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://datashare.ed.ac.uk/handle/10283/3443 +* License: https://creativecommons.org/licenses/by/4.0/ + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_GB/vctk/medium/en_GB-vctk-medium.onnx b/en/en_GB/vctk/medium/en_GB-vctk-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3c01d9375aa487856511647e24c15b2db8462e69 --- /dev/null +++ b/en/en_GB/vctk/medium/en_GB-vctk-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9fc85ab9009385319fc6bae7f55577f8a2d7ee77fd9159a5500eb6531f41e6 +size 76952753 diff --git a/en/en_GB/vctk/medium/en_GB-vctk-medium.onnx.json b/en/en_GB/vctk/medium/en_GB-vctk-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..01135777f6c81f032d327f932fd78eaa73542e43 --- /dev/null +++ b/en/en_GB/vctk/medium/en_GB-vctk-medium.onnx.json @@ -0,0 +1,593 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-gb-x-rp" + }, + "inference": { + "noise_scale": 0.333, + "length_scale": 1.4, + "noise_w": 0.333 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 109, + "speaker_id_map": { + "p239": 0, + "p236": 1, + "p264": 2, + "p250": 3, + "p259": 4, + "p247": 5, + "p261": 6, + "p263": 7, + "p283": 8, + "p286": 9, + "p274": 10, + "p276": 11, + "p270": 12, + "p281": 13, + "p277": 14, + "p231": 15, + "p271": 16, + "p238": 17, + "p257": 18, + "p273": 19, + "p284": 20, + "p329": 21, + "p361": 22, + "p287": 23, + "p360": 24, + "p374": 25, + "p376": 26, + "p310": 27, + "p304": 28, + "p334": 29, + "p340": 30, + "p323": 31, + "p347": 32, + "p330": 33, + "p308": 34, + "p314": 35, + "p317": 36, + "p339": 37, + "p311": 38, + "p294": 39, + "p305": 40, + "p266": 41, + "p335": 42, + "p318": 43, + "p351": 44, + "p333": 45, + "p313": 46, + "p316": 47, + "p244": 48, + "p307": 49, + "p363": 50, + "p336": 51, + "p297": 52, + "p312": 53, + "p267": 54, + "p275": 55, + "p295": 56, + "p258": 57, + "p288": 58, + "p301": 59, + "p232": 60, + "p292": 61, + "p272": 62, + "p280": 63, + "p278": 64, + "p341": 65, + "p268": 66, + "p298": 67, + "p299": 68, + "p279": 69, + "p285": 70, + "p326": 71, + "p300": 72, + "s5": 73, + "p230": 74, + "p345": 75, + "p254": 76, + "p269": 77, + "p293": 78, + "p252": 79, + "p262": 80, + "p243": 81, + "p227": 82, + "p343": 83, + "p255": 84, + "p229": 85, + "p240": 86, + "p248": 87, + "p253": 88, + "p233": 89, + "p228": 90, + "p282": 91, + "p251": 92, + "p246": 93, + "p234": 94, + "p226": 95, + "p260": 96, + "p245": 97, + "p241": 98, + "p303": 99, + "p265": 100, + "p306": 101, + "p237": 102, + "p249": 103, + "p256": 104, + "p302": 105, + "p364": 106, + "p225": 107, + "p362": 108 + }, + "piper_version": "1.0.0" +} diff --git a/en/en_US/amy/low/MODEL_CARD b/en/en_US/amy/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..29114de3514fe3c8648a8db2695a546e9d083a36 --- /dev/null +++ b/en/en_US/amy/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for amy (low) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/MycroftAI/mimic3-voices +* License: See URL + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/en/en_US/amy/low/en_US-amy-low.onnx b/en/en_US/amy/low/en_US-amy-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..90ea9e91d5a948cab41dbd3860b9ca92ff566ebb --- /dev/null +++ b/en/en_US/amy/low/en_US-amy-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a91abb7de0f104358a25aded480ddacf1ff0762886325886ec406a2e86aab3 +size 63104526 diff --git a/en/en_US/amy/low/en_US-amy-low.onnx.json b/en/en_US/amy/low/en_US-amy-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..d64db2e768280bea5e5a90d3b71a29e512bf0899 --- /dev/null +++ b/en/en_US/amy/low/en_US-amy-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/en/en_US/amy/medium/MODEL_CARD b/en/en_US/amy/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..afaf80d8eb2304e99e5ac516c764e9f35ae624ba --- /dev/null +++ b/en/en_US/amy/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for amy (low) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/MycroftAI/mimic3-voices +* License: See URL + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_US/amy/medium/en_US-amy-medium.onnx b/en/en_US/amy/medium/en_US-amy-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..1d703b260d0732739ed941fead81f4514b91a79e --- /dev/null +++ b/en/en_US/amy/medium/en_US-amy-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a6e47b57b8c7fbe6a0ce2518161a50f59a9cdd8a50835c02cb02bdd6206c18 +size 63201294 diff --git a/en/en_US/amy/medium/en_US-amy-medium.onnx.json b/en/en_US/amy/medium/en_US-amy-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..0367d8eb33b62837f15bd7eabf08f4e6966d0d5f --- /dev/null +++ b/en/en_US/amy/medium/en_US-amy-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_US/arctic/medium/MODEL_CARD b/en/en_US/arctic/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..ecdf2b25279227724eba1ebffa9ef768eab70254 --- /dev/null +++ b/en/en_US/arctic/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for arctic (medium) + +* Language: en_US (English, United States) +* Speakers: 18 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: http://www.festvox.org/cmu_arctic/ +* License: See LICENSE file + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_US/arctic/medium/en_US-arctic-medium.onnx b/en/en_US/arctic/medium/en_US-arctic-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..aebeba23b778996ab132183f1616f4d334b004b5 --- /dev/null +++ b/en/en_US/arctic/medium/en_US-arctic-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:483303e294947a3ec2f910ea96093d876e1640f5772e9d89e511d6c82c667286 +size 76766385 diff --git a/en/en_US/arctic/medium/en_US-arctic-medium.onnx.json b/en/en_US/arctic/medium/en_US-arctic-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..f6ac786fc0e54a600a52fc9f1cc7902d5b3710b8 --- /dev/null +++ b/en/en_US/arctic/medium/en_US-arctic-medium.onnx.json @@ -0,0 +1,502 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 18, + "speaker_id_map": { + "awb": 0, + "rms": 1, + "slt": 2, + "ksp": 3, + "clb": 4, + "lnh": 5, + "aew": 6, + "bdl": 7, + "jmk": 8, + "rxr": 9, + "fem": 10, + "ljm": 11, + "slp": 12, + "aup": 13, + "ahw": 14, + "axb": 15, + "eey": 16, + "gka": 17 + }, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_US/danny/low/MODEL_CARD b/en/en_US/danny/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..4ddbd802e442ea98d52839ed98b7d15086e85c4f --- /dev/null +++ b/en/en_US/danny/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for danny (low) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/MycroftAI/mimic3-voices +* License: See URL + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/en/en_US/danny/low/en_US-danny-low.onnx b/en/en_US/danny/low/en_US-danny-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3c929e8b28cccc4dce4273cbdd389386ae00c5c7 --- /dev/null +++ b/en/en_US/danny/low/en_US-danny-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a9ae9499e961514f060aac2866cb323a21e5989592fc4f208e56fdc323ab64 +size 63104526 diff --git a/en/en_US/danny/low/en_US-danny-low.onnx.json b/en/en_US/danny/low/en_US-danny-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..d64db2e768280bea5e5a90d3b71a29e512bf0899 --- /dev/null +++ b/en/en_US/danny/low/en_US-danny-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/en/en_US/joe/medium/MODEL_CARD b/en/en_US/joe/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..edc69d2a5bb3fdb58ff219f1c11cf61a6b0deccd --- /dev/null +++ b/en/en_US/joe/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for joe (medium) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/NabuCasa/voice-datasets +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_US/joe/medium/en_US-joe-medium.onnx b/en/en_US/joe/medium/en_US-joe-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8c620f3be0b47774b4dc5a1beea372efc4a76a93 --- /dev/null +++ b/en/en_US/joe/medium/en_US-joe-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58afce0321b8d9c46d7cdf9c16500cc55a793b4220212dba6b70fb788b3baf06 +size 63201294 diff --git a/en/en_US/joe/medium/en_US-joe-medium.onnx.json b/en/en_US/joe/medium/en_US-joe-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..4c95a7d304d45d66c8673169610cd4e91f752beb --- /dev/null +++ b/en/en_US/joe/medium/en_US-joe-medium.onnx.json @@ -0,0 +1,474 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_US/kathleen/low/MODEL_CARD b/en/en_US/kathleen/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..1f053c05000834c4ecb927179af0dd99574734d8 --- /dev/null +++ b/en/en_US/kathleen/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for kathleen (low) + +* Language: en_US (English, United Staets) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/rhasspy/dataset-voice-kathleen +* License: CC0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/en/en_US/kathleen/low/en_US-kathleen-low.onnx b/en/en_US/kathleen/low/en_US-kathleen-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..e80b620cc5bc6654f814924cc5a5c75d2921eb2c --- /dev/null +++ b/en/en_US/kathleen/low/en_US-kathleen-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87adf17f5326bc0782282147a8b9788406236245f0f9b0e68dacb651bc1de8b6 +size 63104526 diff --git a/en/en_US/kathleen/low/en_US-kathleen-low.onnx.json b/en/en_US/kathleen/low/en_US-kathleen-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..d64db2e768280bea5e5a90d3b71a29e512bf0899 --- /dev/null +++ b/en/en_US/kathleen/low/en_US-kathleen-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/en/en_US/kusal/medium/MODEL_CARD b/en/en_US/kusal/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..1425aeee8b85c7a90516e84004fa6d4903e6ea99 --- /dev/null +++ b/en/en_US/kusal/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for kusal (medium) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/MycroftAI/mimic2 +* License: See URL + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_US/kusal/medium/en_US-kusal-medium.onnx b/en/en_US/kusal/medium/en_US-kusal-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8e9405f72133b2b1df47fb5687df4dc0e8c1bbae --- /dev/null +++ b/en/en_US/kusal/medium/en_US-kusal-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438ae25bb305b2a7f6d632327d6102df25011f793e8222fa9db876e7321df8f3 +size 63201294 diff --git a/en/en_US/kusal/medium/en_US-kusal-medium.onnx.json b/en/en_US/kusal/medium/en_US-kusal-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..0367d8eb33b62837f15bd7eabf08f4e6966d0d5f --- /dev/null +++ b/en/en_US/kusal/medium/en_US-kusal-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_US/l2arctic/medium/MODEL_CARD b/en/en_US/l2arctic/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..730fcd6b9186c43931106a96c6a7a0bc8599b84d --- /dev/null +++ b/en/en_US/l2arctic/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for l2arctic (medium) + +* Language: en_US (English, United States) +* Speakers: 24 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.isca-speech.org/archive/interspeech_2018/zhao18b_interspeech.html +* License: https://creativecommons.org/licenses/by-nc/4.0/ + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_US/l2arctic/medium/en_US-l2arctic-medium.onnx b/en/en_US/l2arctic/medium/en_US-l2arctic-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..81d2572366f905fd20308474d1fd2fb04fd084c2 --- /dev/null +++ b/en/en_US/l2arctic/medium/en_US-l2arctic-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d89f6f124bf1e7735b2179d2141b8001c3e19169d5e743ed6e35624f4c76f044 +size 76778673 diff --git a/en/en_US/l2arctic/medium/en_US-l2arctic-medium.onnx.json b/en/en_US/l2arctic/medium/en_US-l2arctic-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..37a943852af7f8b9c5dc9d3035e69e6c906b2c76 --- /dev/null +++ b/en/en_US/l2arctic/medium/en_US-l2arctic-medium.onnx.json @@ -0,0 +1,508 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 24, + "speaker_id_map": { + "TXHC": 0, + "THV": 1, + "SVBI": 2, + "ZHAA": 3, + "PNV": 4, + "TLV": 5, + "ERMS": 6, + "MBMPS": 7, + "HQTV": 8, + "TNI": 9, + "ASI": 10, + "HJK": 11, + "LXC": 12, + "NCC": 13, + "YKWK": 14, + "YDCK": 15, + "HKK": 16, + "NJS": 17, + "YBAA": 18, + "RRBI": 19, + "BWC": 20, + "ABA": 21, + "EBVS": 22, + "SKA": 23 + }, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_US/lessac/high/MODEL_CARD b/en/en_US/lessac/high/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..019c2ac5e9b50aebad2a512c715e1ebbc80b7777 --- /dev/null +++ b/en/en_US/lessac/high/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for lessac (high) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: high +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.cstr.ed.ac.uk/projects/blizzard/2013/lessac_blizzard2013/ +* License: https://www.cstr.ed.ac.uk/projects/blizzard/2013/lessac_blizzard2013/license.html + +## Training + +Trained from scratch. diff --git a/en/en_US/lessac/high/en_US-lessac-high.onnx b/en/en_US/lessac/high/en_US-lessac-high.onnx new file mode 100644 index 0000000000000000000000000000000000000000..fe08c7518f3a88b92cab9bc2eceb88f07312b8cb --- /dev/null +++ b/en/en_US/lessac/high/en_US-lessac-high.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cabf7c3a638017137f34a1516522032d4fe3f38228a843cc9b764ddcbcd9e09 +size 113895201 diff --git a/en/en_US/lessac/high/en_US-lessac-high.onnx.json b/en/en_US/lessac/high/en_US-lessac-high.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..0367d8eb33b62837f15bd7eabf08f4e6966d0d5f --- /dev/null +++ b/en/en_US/lessac/high/en_US-lessac-high.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/en/en_US/lessac/low/MODEL_CARD b/en/en_US/lessac/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..cd2267b26d4931212cb63e41e933ac5512e2c236 --- /dev/null +++ b/en/en_US/lessac/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for lessac (low) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://www.cstr.ed.ac.uk/projects/blizzard/2013/lessac_blizzard2013/ +* License: https://www.cstr.ed.ac.uk/projects/blizzard/2013/lessac_blizzard2013/license.html + +## Training + +Trained from scratch. diff --git a/en/en_US/lessac/low/en_US-lessac-low.onnx b/en/en_US/lessac/low/en_US-lessac-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ba6045826d5a33f489e37692d6f346d4b9a3ea0a --- /dev/null +++ b/en/en_US/lessac/low/en_US-lessac-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7d01dde371555732c4c314111ac79672b1a5ce2fc19266ab42178fd8df7f375 +size 63201294 diff --git a/en/en_US/lessac/low/en_US-lessac-low.onnx.json b/en/en_US/lessac/low/en_US-lessac-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..0611f14f1992fc0c0be69b4510dcdc09ece8a8a1 --- /dev/null +++ b/en/en_US/lessac/low/en_US-lessac-low.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} diff --git a/en/en_US/lessac/medium/MODEL_CARD b/en/en_US/lessac/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..c0b9a3d60eb5b2e852aedb2a806031f85d02d40b --- /dev/null +++ b/en/en_US/lessac/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for lessac (medium) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.cstr.ed.ac.uk/projects/blizzard/2013/lessac_blizzard2013/ +* License: https://www.cstr.ed.ac.uk/projects/blizzard/2013/lessac_blizzard2013/license.html + +## Training + +Trained from scratch. diff --git a/en/en_US/lessac/medium/en_US-lessac-medium.onnx b/en/en_US/lessac/medium/en_US-lessac-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..96c54a44122cdf5bc67d5d2cb24e2979dec53f93 --- /dev/null +++ b/en/en_US/lessac/medium/en_US-lessac-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5efe09e69902187827af646e1a6e9d269dee769f9877d17b16b1b46eeaaf019f +size 63201294 diff --git a/en/en_US/lessac/medium/en_US-lessac-medium.onnx.json b/en/en_US/lessac/medium/en_US-lessac-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..dd6a99bd873ffbc6fd2d4809a2f4f6c1a202a641 --- /dev/null +++ b/en/en_US/lessac/medium/en_US-lessac-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} diff --git a/en/en_US/libritts/high/MODEL_CARD b/en/en_US/libritts/high/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..3bc22608e1537151bb6f7f1c171a0e2424193193 --- /dev/null +++ b/en/en_US/libritts/high/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for libritts (high) + +* Language: en_US (English, United States) +* Speakers: 904 +* Quality: high +* Samplerate: 22,050Hz + +## Dataset + +* URL: http://www.openslr.org/60/ +* License: CC BY 4.0 + +## Training + +Trained from scratch on train-clean-360. diff --git a/en/en_US/libritts/high/en_US-libritts-high.onnx b/en/en_US/libritts/high/en_US-libritts-high.onnx new file mode 100644 index 0000000000000000000000000000000000000000..944e7e5f47210d7a2286ff12caebb3807e1a788c --- /dev/null +++ b/en/en_US/libritts/high/en_US-libritts-high.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9127a559e11603f10b366d1a20ac7426826081dbc521de4c2420c57728d73f0f +size 136673811 diff --git a/en/en_US/libritts/high/en_US-libritts-high.onnx.json b/en/en_US/libritts/high/en_US-libritts-high.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..357af0e9ea2ddd4f8e7bdd47a7d9e9543f03c238 --- /dev/null +++ b/en/en_US/libritts/high/en_US-libritts-high.onnx.json @@ -0,0 +1,1314 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 904, + "speaker_id_map": { + "3922": 0, + "8699": 1, + "4535": 2, + "6701": 3, + "3638": 4, + "922": 5, + "2531": 6, + "1638": 7, + "8848": 8, + "6544": 9, + "3615": 10, + "318": 11, + "6104": 12, + "1382": 13, + "5400": 14, + "5712": 15, + "2769": 16, + "2573": 17, + "1463": 18, + "6458": 19, + "3274": 20, + "4356": 21, + "8498": 22, + "5570": 23, + "176": 24, + "339": 25, + "28": 26, + "5909": 27, + "3869": 28, + "4899": 29, + "64": 30, + "3368": 31, + "3307": 32, + "5618": 33, + "3370": 34, + "7704": 35, + "8506": 36, + "8410": 37, + "6904": 38, + "5655": 39, + "2204": 40, + "501": 41, + "7314": 42, + "1027": 43, + "5054": 44, + "534": 45, + "2853": 46, + "5935": 47, + "2404": 48, + "7874": 49, + "816": 50, + "2053": 51, + "8066": 52, + "16": 53, + "4586": 54, + "1923": 55, + "2592": 56, + "1265": 57, + "6189": 58, + "100": 59, + "6371": 60, + "4957": 61, + "4116": 62, + "3003": 63, + "7739": 64, + "1752": 65, + "5717": 66, + "5012": 67, + "5062": 68, + "7481": 69, + "4595": 70, + "2299": 71, + "7188": 72, + "93": 73, + "4145": 74, + "8684": 75, + "7594": 76, + "2598": 77, + "3540": 78, + "7717": 79, + "6426": 80, + "4148": 81, + "335": 82, + "1379": 83, + "2512": 84, + "242": 85, + "8855": 86, + "8118": 87, + "369": 88, + "6575": 89, + "6694": 90, + "8080": 91, + "1283": 92, + "7434": 93, + "5290": 94, + "1731": 95, + "2401": 96, + "459": 97, + "192": 98, + "7910": 99, + "114": 100, + "5660": 101, + "1313": 102, + "203": 103, + "7460": 104, + "207": 105, + "6497": 106, + "6696": 107, + "7766": 108, + "6233": 109, + "3185": 110, + "2010": 111, + "2056": 112, + "3717": 113, + "5802": 114, + "5622": 115, + "2156": 116, + "4243": 117, + "1422": 118, + "5039": 119, + "4110": 120, + "1093": 121, + "1776": 122, + "7995": 123, + "6877": 124, + "5635": 125, + "54": 126, + "288": 127, + "4592": 128, + "7276": 129, + "688": 130, + "8388": 131, + "8152": 132, + "8194": 133, + "7000": 134, + "8527": 135, + "5126": 136, + "3923": 137, + "1054": 138, + "3927": 139, + "5029": 140, + "4098": 141, + "1789": 142, + "56": 143, + "7240": 144, + "5538": 145, + "1903": 146, + "6538": 147, + "3380": 148, + "6643": 149, + "7495": 150, + "8718": 151, + "8050": 152, + "126": 153, + "7245": 154, + "2517": 155, + "4438": 156, + "4945": 157, + "7145": 158, + "724": 159, + "9022": 160, + "6637": 161, + "6927": 162, + "6937": 163, + "8113": 164, + "5724": 165, + "6006": 166, + "3584": 167, + "2971": 168, + "2230": 169, + "7982": 170, + "1649": 171, + "3994": 172, + "7720": 173, + "6981": 174, + "781": 175, + "4973": 176, + "6206": 177, + "2481": 178, + "3157": 179, + "1509": 180, + "510": 181, + "7540": 182, + "8887": 183, + "7120": 184, + "2882": 185, + "7128": 186, + "8142": 187, + "7229": 188, + "2787": 189, + "8820": 190, + "2368": 191, + "4331": 192, + "4967": 193, + "4427": 194, + "6054": 195, + "3728": 196, + "274": 197, + "7134": 198, + "1603": 199, + "1383": 200, + "1165": 201, + "4363": 202, + "512": 203, + "5985": 204, + "7967": 205, + "2060": 206, + "7752": 207, + "7484": 208, + "8643": 209, + "3549": 210, + "5731": 211, + "7881": 212, + "667": 213, + "6828": 214, + "5740": 215, + "3483": 216, + "718": 217, + "6341": 218, + "1913": 219, + "3228": 220, + "7247": 221, + "7705": 222, + "1018": 223, + "8193": 224, + "6098": 225, + "3989": 226, + "7828": 227, + "5876": 228, + "7754": 229, + "4719": 230, + "8011": 231, + "7939": 232, + "5975": 233, + "2004": 234, + "6139": 235, + "8183": 236, + "3482": 237, + "3361": 238, + "4289": 239, + "231": 240, + "7789": 241, + "4598": 242, + "5239": 243, + "2638": 244, + "6300": 245, + "8474": 246, + "2194": 247, + "7832": 248, + "1079": 249, + "1335": 250, + "188": 251, + "1195": 252, + "5914": 253, + "1401": 254, + "7318": 255, + "5448": 256, + "1392": 257, + "3703": 258, + "2113": 259, + "7783": 260, + "8176": 261, + "6519": 262, + "7933": 263, + "7938": 264, + "7802": 265, + "6120": 266, + "224": 267, + "209": 268, + "5656": 269, + "3032": 270, + "6965": 271, + "258": 272, + "4837": 273, + "5489": 274, + "272": 275, + "3851": 276, + "7140": 277, + "2562": 278, + "1472": 279, + "79": 280, + "2775": 281, + "3046": 282, + "2532": 283, + "8266": 284, + "6099": 285, + "4425": 286, + "5293": 287, + "7981": 288, + "2045": 289, + "920": 290, + "511": 291, + "7416": 292, + "835": 293, + "1289": 294, + "8195": 295, + "7833": 296, + "8772": 297, + "968": 298, + "1641": 299, + "7117": 300, + "1678": 301, + "5809": 302, + "8028": 303, + "500": 304, + "6505": 305, + "7868": 306, + "14": 307, + "2238": 308, + "4744": 309, + "3733": 310, + "7515": 311, + "699": 312, + "5093": 313, + "6388": 314, + "7959": 315, + "98": 316, + "3914": 317, + "5246": 318, + "2570": 319, + "8396": 320, + "3513": 321, + "882": 322, + "7994": 323, + "5968": 324, + "8591": 325, + "806": 326, + "5261": 327, + "1271": 328, + "899": 329, + "3945": 330, + "8404": 331, + "249": 332, + "3008": 333, + "7139": 334, + "6395": 335, + "6215": 336, + "6080": 337, + "4054": 338, + "7825": 339, + "6683": 340, + "8725": 341, + "3230": 342, + "4138": 343, + "6160": 344, + "666": 345, + "6510": 346, + "3551": 347, + "8075": 348, + "225": 349, + "7169": 350, + "1851": 351, + "5984": 352, + "2960": 353, + "8329": 354, + "175": 355, + "6378": 356, + "480": 357, + "7538": 358, + "479": 359, + "5519": 360, + "8534": 361, + "4856": 362, + "101": 363, + "3521": 364, + "2256": 365, + "3083": 366, + "4278": 367, + "8713": 368, + "1226": 369, + "4222": 370, + "8494": 371, + "8776": 372, + "731": 373, + "6574": 374, + "5319": 375, + "8605": 376, + "5583": 377, + "6406": 378, + "4064": 379, + "4806": 380, + "3972": 381, + "7383": 382, + "5133": 383, + "597": 384, + "1025": 385, + "7313": 386, + "5304": 387, + "8758": 388, + "1050": 389, + "6499": 390, + "6956": 391, + "770": 392, + "4108": 393, + "2774": 394, + "3864": 395, + "4490": 396, + "4848": 397, + "1826": 398, + "6294": 399, + "7949": 400, + "1446": 401, + "7867": 402, + "8163": 403, + "953": 404, + "8138": 405, + "353": 406, + "7553": 407, + "8825": 408, + "5189": 409, + "2012": 410, + "948": 411, + "205": 412, + "1535": 413, + "8008": 414, + "1112": 415, + "7926": 416, + "4039": 417, + "716": 418, + "3967": 419, + "7932": 420, + "7525": 421, + "7316": 422, + "3448": 423, + "2393": 424, + "6788": 425, + "6550": 426, + "7011": 427, + "8791": 428, + "8119": 429, + "1777": 430, + "6014": 431, + "1046": 432, + "6269": 433, + "6188": 434, + "5266": 435, + "3490": 436, + "8786": 437, + "8824": 438, + "589": 439, + "576": 440, + "1121": 441, + "1806": 442, + "7294": 443, + "3119": 444, + "2688": 445, + "1012": 446, + "4807": 447, + "7498": 448, + "3905": 449, + "7384": 450, + "2992": 451, + "30": 452, + "497": 453, + "227": 454, + "4226": 455, + "5007": 456, + "1066": 457, + "8222": 458, + "7688": 459, + "6865": 460, + "6286": 461, + "8225": 462, + "3224": 463, + "8635": 464, + "1348": 465, + "3645": 466, + "1961": 467, + "8190": 468, + "6032": 469, + "7286": 470, + "5389": 471, + "3105": 472, + "1028": 473, + "6038": 474, + "764": 475, + "7437": 476, + "6555": 477, + "8875": 478, + "2074": 479, + "7809": 480, + "2240": 481, + "2827": 482, + "5386": 483, + "6763": 484, + "3009": 485, + "6339": 486, + "1825": 487, + "7569": 488, + "359": 489, + "7956": 490, + "2137": 491, + "8677": 492, + "4434": 493, + "329": 494, + "3289": 495, + "4290": 496, + "2999": 497, + "2427": 498, + "637": 499, + "2229": 500, + "1874": 501, + "3446": 502, + "9023": 503, + "3114": 504, + "6235": 505, + "4860": 506, + "4519": 507, + "561": 508, + "70": 509, + "4800": 510, + "2294": 511, + "6115": 512, + "2582": 513, + "8464": 514, + "5139": 515, + "6918": 516, + "337": 517, + "5810": 518, + "8401": 519, + "303": 520, + "5206": 521, + "2589": 522, + "7061": 523, + "2269": 524, + "2758": 525, + "3389": 526, + "4629": 527, + "707": 528, + "5606": 529, + "1513": 530, + "2473": 531, + "664": 532, + "5092": 533, + "5154": 534, + "6288": 535, + "6308": 536, + "4731": 537, + "3328": 538, + "7816": 539, + "3221": 540, + "8687": 541, + "7030": 542, + "476": 543, + "4257": 544, + "5918": 545, + "6317": 546, + "204": 547, + "8006": 548, + "6895": 549, + "1264": 550, + "2494": 551, + "112": 552, + "1859": 553, + "398": 554, + "1052": 555, + "3294": 556, + "1460": 557, + "8573": 558, + "5684": 559, + "8421": 560, + "5883": 561, + "7297": 562, + "246": 563, + "8057": 564, + "3835": 565, + "1748": 566, + "3816": 567, + "3357": 568, + "1053": 569, + "409": 570, + "868": 571, + "3118": 572, + "7520": 573, + "6686": 574, + "1241": 575, + "5190": 576, + "166": 577, + "1482": 578, + "5604": 579, + "1212": 580, + "2741": 581, + "1259": 582, + "984": 583, + "6492": 584, + "6167": 585, + "296": 586, + "6567": 587, + "6924": 588, + "2272": 589, + "7085": 590, + "345": 591, + "2388": 592, + "1705": 593, + "1343": 594, + "7241": 595, + "451": 596, + "5401": 597, + "6446": 598, + "612": 599, + "594": 600, + "7555": 601, + "7069": 602, + "2577": 603, + "5333": 604, + "8742": 605, + "6727": 606, + "1571": 607, + "4734": 608, + "7258": 609, + "3977": 610, + "373": 611, + "5723": 612, + "1365": 613, + "7285": 614, + "580": 615, + "836": 616, + "6782": 617, + "3654": 618, + "1974": 619, + "6258": 620, + "925": 621, + "949": 622, + "2790": 623, + "698": 624, + "6373": 625, + "2785": 626, + "1222": 627, + "2751": 628, + "3825": 629, + "5115": 630, + "1827": 631, + "3171": 632, + "119": 633, + "850": 634, + "3258": 635, + "7909": 636, + "1322": 637, + "8097": 638, + "22": 639, + "7478": 640, + "1349": 641, + "4854": 642, + "2929": 643, + "7335": 644, + "5868": 645, + "454": 646, + "7945": 647, + "2654": 648, + "3493": 649, + "1060": 650, + "8545": 651, + "6509": 652, + "5002": 653, + "7732": 654, + "3082": 655, + "1779": 656, + "2709": 657, + "7398": 658, + "8879": 659, + "639": 660, + "598": 661, + "5672": 662, + "6553": 663, + "4111": 664, + "1417": 665, + "7991": 666, + "380": 667, + "8459": 668, + "8347": 669, + "1769": 670, + "2673": 671, + "3330": 672, + "7051": 673, + "1337": 674, + "4057": 675, + "4839": 676, + "6060": 677, + "7095": 678, + "278": 679, + "1445": 680, + "6518": 681, + "2364": 682, + "1958": 683, + "548": 684, + "4010": 685, + "3072": 686, + "6993": 687, + "8575": 688, + "2149": 689, + "240": 690, + "2920": 691, + "5588": 692, + "1885": 693, + "6082": 694, + "9026": 695, + "340": 696, + "159": 697, + "7730": 698, + "7962": 699, + "1987": 700, + "3876": 701, + "8771": 702, + "5123": 703, + "3866": 704, + "3546": 705, + "7777": 706, + "115": 707, + "5337": 708, + "475": 709, + "1724": 710, + "6359": 711, + "4260": 712, + "2110": 713, + "1845": 714, + "4335": 715, + "4133": 716, + "783": 717, + "8479": 718, + "1448": 719, + "1160": 720, + "7647": 721, + "2618": 722, + "3630": 723, + "4013": 724, + "5242": 725, + "7957": 726, + "3852": 727, + "3889": 728, + "1387": 729, + "439": 730, + "1425": 731, + "2061": 732, + "7395": 733, + "7837": 734, + "5147": 735, + "2319": 736, + "3781": 737, + "1311": 738, + "4733": 739, + "8705": 740, + "3094": 741, + "2823": 742, + "1914": 743, + "954": 744, + "4381": 745, + "4044": 746, + "593": 747, + "8300": 748, + "7558": 749, + "6494": 750, + "6330": 751, + "5940": 752, + "7126": 753, + "1061": 754, + "6352": 755, + "5186": 756, + "1944": 757, + "2285": 758, + "6673": 759, + "5746": 760, + "208": 761, + "492": 762, + "216": 763, + "979": 764, + "1668": 765, + "6620": 766, + "711": 767, + "7733": 768, + "8619": 769, + "5157": 770, + "829": 771, + "3180": 772, + "3979": 773, + "1556": 774, + "3379": 775, + "5727": 776, + "596": 777, + "2127": 778, + "581": 779, + "2652": 780, + "2628": 781, + "1849": 782, + "4238": 783, + "606": 784, + "1224": 785, + "1629": 786, + "1413": 787, + "957": 788, + "8592": 789, + "2254": 790, + "1323": 791, + "122": 792, + "2093": 793, + "1100": 794, + "81": 795, + "323": 796, + "815": 797, + "2581": 798, + "543": 799, + "6037": 800, + "2397": 801, + "5513": 802, + "4495": 803, + "5776": 804, + "17": 805, + "4590": 806, + "8228": 807, + "708": 808, + "3792": 809, + "3790": 810, + "7090": 811, + "1943": 812, + "4246": 813, + "559": 814, + "3738": 815, + "2167": 816, + "1933": 817, + "2162": 818, + "549": 819, + "3025": 820, + "1182": 821, + "4358": 822, + "636": 823, + "986": 824, + "8490": 825, + "3340": 826, + "90": 827, + "1487": 828, + "1639": 829, + "1547": 830, + "4152": 831, + "1498": 832, + "1740": 833, + "6157": 834, + "217": 835, + "2201": 836, + "362": 837, + "2146": 838, + "1801": 839, + "5063": 840, + "7339": 841, + "663": 842, + "38": 843, + "1336": 844, + "3215": 845, + "210": 846, + "6075": 847, + "55": 848, + "2411": 849, + "7445": 850, + "5767": 851, + "2812": 852, + "472": 853, + "803": 854, + "4236": 855, + "7665": 856, + "1607": 857, + "1316": 858, + "7475": 859, + "3001": 860, + "1473": 861, + "3537": 862, + "3070": 863, + "1390": 864, + "1290": 865, + "2499": 866, + "154": 867, + "7518": 868, + "408": 869, + "1811": 870, + "1734": 871, + "7342": 872, + "8722": 873, + "1754": 874, + "7657": 875, + "583": 876, + "830": 877, + "6690": 878, + "1552": 879, + "2498": 880, + "1296": 881, + "3686": 882, + "157": 883, + "487": 884, + "6119": 885, + "4926": 886, + "4846": 887, + "1536": 888, + "2674": 889, + "1645": 890, + "3187": 891, + "1058": 892, + "2039": 893, + "4071": 894, + "4433": 895, + "1175": 896, + "434": 897, + "1001": 898, + "2816": 899, + "820": 900, + "2696": 901, + "4681": 902, + "2085": 903 + } +} diff --git a/en/en_US/ryan/high/MODEL_CARD b/en/en_US/ryan/high/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..e422ec797dc70302105e02385f98a05310ee5a1d --- /dev/null +++ b/en/en_US/ryan/high/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for ryan (high) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: high +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.kaggle.com/datasets/roholazandie/ryanspeech +* License: CC BY-NC-SA 4.0 + +## Training + +Trained from scratch. diff --git a/en/en_US/ryan/high/en_US-ryan-high.onnx b/en/en_US/ryan/high/en_US-ryan-high.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8aaceeab8ccd969f0d21b1f3cee6f65300d63c02 --- /dev/null +++ b/en/en_US/ryan/high/en_US-ryan-high.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3990d7606e183ec8dbfba70a4607074f162de1a0c412e0180d1ff60bb154eca +size 120786792 diff --git a/en/en_US/ryan/high/en_US-ryan-high.onnx.json b/en/en_US/ryan/high/en_US-ryan-high.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..f549fbd61ceaf8cca4c3e9cb17560073755231b2 --- /dev/null +++ b/en/en_US/ryan/high/en_US-ryan-high.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/en/en_US/ryan/low/MODEL_CARD b/en/en_US/ryan/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..9a355774ffba2b44882a7d7ede041ecbde4c6340 --- /dev/null +++ b/en/en_US/ryan/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for ryan (low) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://www.kaggle.com/datasets/roholazandie/ryanspeech +* License: CC BY-NC-SA 4.0 + +## Training + +Trained from scratch. diff --git a/en/en_US/ryan/low/en_US-ryan-low.onnx b/en/en_US/ryan/low/en_US-ryan-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..e17ffefb601072fc9ad1127149ba2e52ec6d2119 --- /dev/null +++ b/en/en_US/ryan/low/en_US-ryan-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d21a085cc4c0010f1f3e91d5008c8691277ccfa744eb0d747becd33a3444baf +size 63104526 diff --git a/en/en_US/ryan/low/en_US-ryan-low.onnx.json b/en/en_US/ryan/low/en_US-ryan-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..c98a238ba35b6db13e996cf07713dbdbe6060b3c --- /dev/null +++ b/en/en_US/ryan/low/en_US-ryan-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} diff --git a/en/en_US/ryan/medium/MODEL_CARD b/en/en_US/ryan/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..b331c598d3a2067c2c1bbb2126096d61d6ee8b0b --- /dev/null +++ b/en/en_US/ryan/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for ryan (medium) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.kaggle.com/datasets/roholazandie/ryanspeech +* License: CC BY-NC-SA 4.0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/en/en_US/ryan/medium/en_US-ryan-medium.onnx b/en/en_US/ryan/medium/en_US-ryan-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..cea8ee0be78def0ff65419e3ccd078507f79c69c --- /dev/null +++ b/en/en_US/ryan/medium/en_US-ryan-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abf4c274862564ed647ba0d2c47f8ee7c9b717d27bdad9219100eb310db4047a +size 63201294 diff --git a/en/en_US/ryan/medium/en_US-ryan-medium.onnx.json b/en/en_US/ryan/medium/en_US-ryan-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..0367d8eb33b62837f15bd7eabf08f4e6966d0d5f --- /dev/null +++ b/en/en_US/ryan/medium/en_US-ryan-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "en-us" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/es/es_ES/carlfm/x_low/MODEL_CARD b/es/es_ES/carlfm/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..d9a317cb56dcc7de17e1584365833531887b6649 --- /dev/null +++ b/es/es_ES/carlfm/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for carlfm (x_low) + +* Language: es_ES (Spanish, Spain) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/carlfm01/my-speech-datasets +* License: Public domain + +## Training + +Trained from scratch. diff --git a/es/es_ES/carlfm/x_low/es_ES-carlfm-x-low.onnx b/es/es_ES/carlfm/x_low/es_ES-carlfm-x-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0759ad093f8a5f9aae55380cbf1b87371467fd2e --- /dev/null +++ b/es/es_ES/carlfm/x_low/es_ES-carlfm-x-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69677323a907cd4963f42b29c20a98b5d6bfa7f3e64df339915e4650c00d125 +size 28130791 diff --git a/es/es_ES/carlfm/x_low/es_ES-carlfm-x-low.onnx.json b/es/es_ES/carlfm/x_low/es_ES-carlfm-x-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..9fa28170b54dbcdda86afb576fe70dc062b6d584 --- /dev/null +++ b/es/es_ES/carlfm/x_low/es_ES-carlfm-x-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "es" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/es/es_ES/davefx/medium/MODEL_CARD b/es/es_ES/davefx/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..4a7151eef75a6854a8ccf6096af9e7f809c4ae80 --- /dev/null +++ b/es/es_ES/davefx/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for davefx (medium) + +* Language: es_ES (Spanish, Spain) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/NabuCasa/voice-datasets +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/es/es_ES/davefx/medium/es_ES-davefx-medium.onnx b/es/es_ES/davefx/medium/es_ES-davefx-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..a9b417941bc25a9866f0952e80cad1245fa99712 --- /dev/null +++ b/es/es_ES/davefx/medium/es_ES-davefx-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6658b03b1a6c316ee4c265a9896abc1393353c2d9e1bca7d66c2c442e222a917 +size 63201294 diff --git a/es/es_ES/davefx/medium/es_ES-davefx-medium.onnx.json b/es/es_ES/davefx/medium/es_ES-davefx-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..e68f8f3029590e7e21bad480026a7bd0f90d70eb --- /dev/null +++ b/es/es_ES/davefx/medium/es_ES-davefx-medium.onnx.json @@ -0,0 +1,477 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "es" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/es/es_ES/mls_10246/low/MODEL_CARD b/es/es_ES/mls_10246/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..781602bc5aa6416b3edd4fdb7cc761928bb4b9a3 --- /dev/null +++ b/es/es_ES/mls_10246/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for mls_10246 (low) + +* Language: es_ES (Spanish, Spain) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: http://www.openslr.org/94/ +* License: CC BY 4.0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/es/es_ES/mls_10246/low/es_ES-mls_10246-low.onnx b/es/es_ES/mls_10246/low/es_ES-mls_10246-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..a7173650c062bf66fe841301d1fc31d9d4c50f08 --- /dev/null +++ b/es/es_ES/mls_10246/low/es_ES-mls_10246-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9d76d2778778942297aab052aa7b2e67248d3f43614c889ee82901a230e197 +size 63104526 diff --git a/es/es_ES/mls_10246/low/es_ES-mls_10246-low.onnx.json b/es/es_ES/mls_10246/low/es_ES-mls_10246-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..9fa28170b54dbcdda86afb576fe70dc062b6d584 --- /dev/null +++ b/es/es_ES/mls_10246/low/es_ES-mls_10246-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "es" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/es/es_ES/mls_9772/low/MODEL_CARD b/es/es_ES/mls_9772/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..6e3f517d93181ec17c059e1dcf8963cb56c6542d --- /dev/null +++ b/es/es_ES/mls_9772/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for mls_9972 (low) + +* Language: es_ES (Spanish, Spain) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: http://www.openslr.org/94/ +* License: CC BY 4.0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/es/es_ES/mls_9772/low/es_ES-mls_9972-low.onnx b/es/es_ES/mls_9772/low/es_ES-mls_9972-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8f38f2e76812f1196e4fc48267471b984f489ca1 --- /dev/null +++ b/es/es_ES/mls_9772/low/es_ES-mls_9972-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdd61beb26d3aba18245c0352a8173e7f96196fbe4979e115590e8f775c95f0 +size 63104526 diff --git a/es/es_ES/mls_9772/low/es_ES-mls_9972-low.onnx.json b/es/es_ES/mls_9772/low/es_ES-mls_9972-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..9fa28170b54dbcdda86afb576fe70dc062b6d584 --- /dev/null +++ b/es/es_ES/mls_9772/low/es_ES-mls_9972-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "es" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/es/es_ES/sharvard/medium/MODEL_CARD b/es/es_ES/sharvard/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..8ce8fb3966b2480974b07a27036b1962d12cad84 --- /dev/null +++ b/es/es_ES/sharvard/medium/MODEL_CARD @@ -0,0 +1,16 @@ +# Model card for sharvard (medium) + +* Language: es_ES (Spanish, Spain) +* Speakers: 2 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://datashare.ed.ac.uk/handle/10283/574 +* License: http://creativecommons.org/licenses/by/3.0/ +* Paper: https://www.tandfonline.com/doi/abs/10.3109/14992027.2014.907507 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/es/es_ES/sharvard/medium/es_ES-sharvard-medium.onnx b/es/es_ES/sharvard/medium/es_ES-sharvard-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..1d8d7097fc26b9fe9d2500c6f70a7fd3c3f66b8e --- /dev/null +++ b/es/es_ES/sharvard/medium/es_ES-sharvard-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40febfb1679c69a4505ff311dc136e121e3419a13a290ef264fdf43ddedd0fb1 +size 76733615 diff --git a/es/es_ES/sharvard/medium/es_ES-sharvard-medium.onnx.json b/es/es_ES/sharvard/medium/es_ES-sharvard-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..41f31e284fc628f034e47d90763b0efcd82b3b06 --- /dev/null +++ b/es/es_ES/sharvard/medium/es_ES-sharvard-medium.onnx.json @@ -0,0 +1,486 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "es" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 2, + "speaker_id_map": { + "M": 0, + "F": 1 + }, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/es/es_MX/ald/medium/MODEL_CARD b/es/es_MX/ald/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..824c689d61aee72278ebcd99db9290b551c1b8d7 --- /dev/null +++ b/es/es_MX/ald/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for ald (medium) + +* Language: es_MX (Spanish, Mexico) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://huggingface.co/datasets/rmcpantoja/Ald_Mexican_Spanish_speech_dataset +* License: http://unlicense.org + +## Training + +Finetuned from Spanish davefx voice (medium quality). diff --git a/es/es_MX/ald/medium/es_MX-ald-medium.onnx b/es/es_MX/ald/medium/es_MX-ald-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..9259a452146658db56d195d116d341a396b65a01 --- /dev/null +++ b/es/es_MX/ald/medium/es_MX-ald-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:019b3803293c93e34a206dd2e53a3889209a514e786fd7144f7b70196c579b63 +size 63201294 diff --git a/es/es_MX/ald/medium/es_MX-ald-medium.onnx.json b/es/es_MX/ald/medium/es_MX-ald-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..dcbb38042f7fe77bf9c29f0c47a0023bb9d3a66e --- /dev/null +++ b/es/es_MX/ald/medium/es_MX-ald-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "es-419" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "PhonemeType.ESPEAK", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/fi/fi_FI/harri/low/MODEL_CARD b/fi/fi_FI/harri/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..de7faafd1556208adc091229d56450ed89edce1d --- /dev/null +++ b/fi/fi_FI/harri/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for harri (low) + +* Language: fi_FI (Finnish) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://www.kaggle.com/bryanpark/finnish-single-speaker-speech-dataset +* License: CC0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/fi/fi_FI/harri/low/fi_FI-harri-low.onnx b/fi/fi_FI/harri/low/fi_FI-harri-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..131619ed9360e51eefdfe4c0c24cf6677991ab33 --- /dev/null +++ b/fi/fi_FI/harri/low/fi_FI-harri-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208847719a1906e2af69dfabc3be4f192536beb1394e253e294690a8ea239853 +size 69795191 diff --git a/fi/fi_FI/harri/low/fi_FI-harri-low.onnx.json b/fi/fi_FI/harri/low/fi_FI-harri-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..a994a27b3a79e3e17bf198ee8a4927f0699ba044 --- /dev/null +++ b/fi/fi_FI/harri/low/fi_FI-harri-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "fi" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/fi/fi_FI/harri/medium/MODEL_CARD b/fi/fi_FI/harri/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..90b99487fb101188267dc3000129612b0353f42f --- /dev/null +++ b/fi/fi_FI/harri/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for harri (medium) + +* Language: fi_FI (Finnish, Finland) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.kaggle.com/bryanpark/finnish-single-speaker-speech-dataset +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/fi/fi_FI/harri/medium/fi_FI-harri-medium.onnx b/fi/fi_FI/harri/medium/fi_FI-harri-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..1bbc756915d88348b4b958371ac7b4beee3a5d0b --- /dev/null +++ b/fi/fi_FI/harri/medium/fi_FI-harri-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44167faa34caed940e4fcad139fcc35922266b2593bcebe77701774c0fb2389 +size 63201294 diff --git a/fi/fi_FI/harri/medium/fi_FI-harri-medium.onnx.json b/fi/fi_FI/harri/medium/fi_FI-harri-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..0c7eec2039089b75d1d9e2a7527eb5b5cdd67238 --- /dev/null +++ b/fi/fi_FI/harri/medium/fi_FI-harri-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "fi" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/fr/fr_FR/gilles/low/MODEL_CARD b/fr/fr_FR/gilles/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..06455bb315201d7330194081d16a8c1668f35f1a --- /dev/null +++ b/fr/fr_FR/gilles/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for gilles (low) + +* Language: fr_FR (French, France) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://www.kaggle.com/datasets/bryanpark/french-single-speaker-speech-dataset +* License: CC0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/fr/fr_FR/gilles/low/fr_FR-gilles-low.onnx b/fr/fr_FR/gilles/low/fr_FR-gilles-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0ef2205e56d69023e8663eb9a2e83bc798678286 --- /dev/null +++ b/fr/fr_FR/gilles/low/fr_FR-gilles-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd711846720e261c2a176f6924c198a7424d0a75dd4b0a5357a5fb9cb739285 +size 63104526 diff --git a/fr/fr_FR/gilles/low/fr_FR-gilles-low.onnx.json b/fr/fr_FR/gilles/low/fr_FR-gilles-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..ac8f4a8183142ca0a7962d90890f6ca2ab049077 --- /dev/null +++ b/fr/fr_FR/gilles/low/fr_FR-gilles-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "fr" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/fr/fr_FR/mls_1840/low/MODEL_CARD b/fr/fr_FR/mls_1840/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..f29b51c6647dbb7691eeb8b743c3db354e28874a --- /dev/null +++ b/fr/fr_FR/mls_1840/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for mls_1840 (low) + +* Language: fr_FR (French, France) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: http://www.openslr.org/94/ +* License: CC BY 4.0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/fr/fr_FR/mls_1840/low/fr_FR-mls_1840-low.onnx b/fr/fr_FR/mls_1840/low/fr_FR-mls_1840-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..00739abcc4a1289c49ef139e8136cf65ba36b959 --- /dev/null +++ b/fr/fr_FR/mls_1840/low/fr_FR-mls_1840-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcea3d495b760f168179b6bd27c7daefa1d8304ce6ec48867e42bae7cb2e507a +size 63104526 diff --git a/fr/fr_FR/mls_1840/low/fr_FR-mls_1840-low.onnx.json b/fr/fr_FR/mls_1840/low/fr_FR-mls_1840-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..ac8f4a8183142ca0a7962d90890f6ca2ab049077 --- /dev/null +++ b/fr/fr_FR/mls_1840/low/fr_FR-mls_1840-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "fr" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/fr/fr_FR/siwis/low/MODEL_CARD b/fr/fr_FR/siwis/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..3a88280386cb503df91313294736437fc23cf115 --- /dev/null +++ b/fr/fr_FR/siwis/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for siwis (low) + +* Language: fr_FR (French, France) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://datashare.is.ed.ac.uk/handle/10283/2353 +* License: CC-BY 4.0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/fr/fr_FR/siwis/low/fr_FR-siwis-low.onnx b/fr/fr_FR/siwis/low/fr_FR-siwis-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..a09816fe2369eecc94a89614e094f2c71d7bc991 --- /dev/null +++ b/fr/fr_FR/siwis/low/fr_FR-siwis-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b7dcaf87229b32af8275cb1a719371234ea677bc0313d2289d5c50ab0ac53d +size 28130791 diff --git a/fr/fr_FR/siwis/low/fr_FR-siwis-low.onnx.json b/fr/fr_FR/siwis/low/fr_FR-siwis-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..ac8f4a8183142ca0a7962d90890f6ca2ab049077 --- /dev/null +++ b/fr/fr_FR/siwis/low/fr_FR-siwis-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "fr" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/fr/fr_FR/siwis/medium/MODEL_CARD b/fr/fr_FR/siwis/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..36c73f2fd5e9fab5fe90a8a744d36aa08280c231 --- /dev/null +++ b/fr/fr_FR/siwis/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for siwis (medium) + +* Language: fr_FR (French, France) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://datashare.is.ed.ac.uk/handle/10283/2353 +* License: CC-BY 4.0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality) diff --git a/fr/fr_FR/siwis/medium/fr_FR-siwis-medium.onnx b/fr/fr_FR/siwis/medium/fr_FR-siwis-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0d6760d87cd690b7d503affefd239a8bae6642ad --- /dev/null +++ b/fr/fr_FR/siwis/medium/fr_FR-siwis-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:641d1ab097da2b81128c076810edb052b385decc8be3381814802a64a73baf99 +size 63201294 diff --git a/fr/fr_FR/siwis/medium/fr_FR-siwis-medium.onnx.json b/fr/fr_FR/siwis/medium/fr_FR-siwis-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..90faa2a7a3de2762b10c05f4b6a6b882041715fe --- /dev/null +++ b/fr/fr_FR/siwis/medium/fr_FR-siwis-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "fr" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/is/is_IS/bui/medium/MODEL_CARD b/is/is_IS/bui/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..52def23e17df8fc801fb094f1c9b4cae87bdae11 --- /dev/null +++ b/is/is_IS/bui/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for bui (medium) + +* Language: is_IS (Icelandic, Iceland) +* Speakers: 1 (Búi) +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: http://hdl.handle.net/20.500.12537/104 +* License: See URL + +## Training + +Trained from scratch. diff --git a/is/is_IS/bui/medium/is_IS-bui-medium.onnx b/is/is_IS/bui/medium/is_IS-bui-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d8f3d2dc78bcee3c3a22fd78fad29bdb2b35e6d0 --- /dev/null +++ b/is/is_IS/bui/medium/is_IS-bui-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a645b2d2850e4098f01f3765cece931836c03741e01a5cc514d09d39d37c05c +size 76495465 diff --git a/is/is_IS/bui/medium/is_IS-bui-medium.onnx.json b/is/is_IS/bui/medium/is_IS-bui-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..94e06df795af0b02e5022e7ee5d6d35cab7d5315 --- /dev/null +++ b/is/is_IS/bui/medium/is_IS-bui-medium.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "is" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/is/is_IS/salka/medium/MODEL_CARD b/is/is_IS/salka/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..c4deaa6c0c78772c862624d124bf08bf131537e1 --- /dev/null +++ b/is/is_IS/salka/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for salka (medium) + +* Language: is_IS (Icelandic, Iceland) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: http://hdl.handle.net/20.500.12537/104 +* License: See URL + +## Training + +Trained from scratch. diff --git a/is/is_IS/salka/medium/is_IS-salka-medium.onnx b/is/is_IS/salka/medium/is_IS-salka-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..cb3f8e85c00d8b80926287f2781ad22e44170cfe --- /dev/null +++ b/is/is_IS/salka/medium/is_IS-salka-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392a8e033772de8f7d4afa3258580f0fd509678b55014c3dc1a0d3e231475d0e +size 76495465 diff --git a/is/is_IS/salka/medium/is_IS-salka-medium.onnx.json b/is/is_IS/salka/medium/is_IS-salka-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..94e06df795af0b02e5022e7ee5d6d35cab7d5315 --- /dev/null +++ b/is/is_IS/salka/medium/is_IS-salka-medium.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "is" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/is/is_IS/steinn/medium/MODEL_CARD b/is/is_IS/steinn/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..97ee40854e4a578d493ab7f1260782851716c487 --- /dev/null +++ b/is/is_IS/steinn/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for steinn (medium) + +* Language: is_IS (Icelandic, Iceland) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: http://hdl.handle.net/20.500.12537/104 +* License: See URL + +## Training + +Trained from scratch. diff --git a/is/is_IS/steinn/medium/is_IS-steinn-medium.onnx b/is/is_IS/steinn/medium/is_IS-steinn-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..796772cc35c482baab0ef636077e58101212751e --- /dev/null +++ b/is/is_IS/steinn/medium/is_IS-steinn-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10fa173c46fb9b9b683066e3198f61716ab8ab310ffce67004ba25d86bb74b1 +size 76495465 diff --git a/is/is_IS/steinn/medium/is_IS-steinn-medium.onnx.json b/is/is_IS/steinn/medium/is_IS-steinn-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..94e06df795af0b02e5022e7ee5d6d35cab7d5315 --- /dev/null +++ b/is/is_IS/steinn/medium/is_IS-steinn-medium.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "is" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/is/is_IS/ugla/medium/MODEL_CARD b/is/is_IS/ugla/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..62472b68c4246b7b11492347a8cca25a12e2d986 --- /dev/null +++ b/is/is_IS/ugla/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for ugla (medium) + +* Language: is_IS (Icelandic, Iceland) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: http://hdl.handle.net/20.500.12537/104 +* License: See URL + +## Training + +Trained from scratch. diff --git a/is/is_IS/ugla/medium/is_IS-ugla-medium.onnx b/is/is_IS/ugla/medium/is_IS-ugla-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..05e667bd6236026b894ad2c1adbf42b6267ba6a3 --- /dev/null +++ b/is/is_IS/ugla/medium/is_IS-ugla-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b43aef7648d13f68b6db0032d85716b82ca78716218a68442fd7f12444a73b24 +size 76495465 diff --git a/is/is_IS/ugla/medium/is_IS-ugla-medium.onnx.json b/is/is_IS/ugla/medium/is_IS-ugla-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..94e06df795af0b02e5022e7ee5d6d35cab7d5315 --- /dev/null +++ b/is/is_IS/ugla/medium/is_IS-ugla-medium.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "is" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/it/it_IT/riccardo/x_low/MODEL_CARD b/it/it_IT/riccardo/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..4b91ee4189954d51b466372d33c862ef41b70993 --- /dev/null +++ b/it/it_IT/riccardo/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for riccardo (x_low) + +* Language: it_IT (Italian, Italy) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/ +* License: See URL + +## Training + +Trained from scratch. diff --git a/it/it_IT/riccardo/x_low/it_IT-riccardo-x_low.onnx b/it/it_IT/riccardo/x_low/it_IT-riccardo-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..267840572cc88c433f4482625d8627288394cf28 --- /dev/null +++ b/it/it_IT/riccardo/x_low/it_IT-riccardo-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1368de15f123275a7ef951c9e5e30be0f58a032daa14a0da44037443c1d1d21b +size 28130791 diff --git a/it/it_IT/riccardo/x_low/it_IT-riccardo-x_low.onnx.json b/it/it_IT/riccardo/x_low/it_IT-riccardo-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..41d11de5e05aa6b5dad8cf873d8298423a972373 --- /dev/null +++ b/it/it_IT/riccardo/x_low/it_IT-riccardo-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "it" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/ka/ka_GE/natia/medium/MODEL_CARD b/ka/ka_GE/natia/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..37f2267bd1a925188c7291d8d7b3cde03a29e682 --- /dev/null +++ b/ka/ka_GE/natia/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for natia (medium) + +* Language: ka_GE (Georgian, Georgia) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: http://github.com/Olga-Yakovleva/RHVoice +* License: See LICENSE file + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/ka/ka_GE/natia/medium/ka_GE-natia-medium.onnx b/ka/ka_GE/natia/medium/ka_GE-natia-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..354f9f96da38388907873b8e5f91cdc92b7c4052 --- /dev/null +++ b/ka/ka_GE/natia/medium/ka_GE-natia-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04bdacf188fa24499885f9109b395fe8561a05ec2cd90d55453ec5beed7af460 +size 63201294 diff --git a/ka/ka_GE/natia/medium/ka_GE-natia-medium.onnx.json b/ka/ka_GE/natia/medium/ka_GE-natia-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..a02ddb4c994a203048255d0cc6ac78cc7f26a5aa --- /dev/null +++ b/ka/ka_GE/natia/medium/ka_GE-natia-medium.onnx.json @@ -0,0 +1,477 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "ka" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/kk/kk_KZ/iseke/x_low/MODEL_CARD b/kk/kk_KZ/iseke/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..f53968ae19def9449efb653a7c49783716b256f1 --- /dev/null +++ b/kk/kk_KZ/iseke/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for iseke (x_low) + +* Language: kk_KZ (Kazakh, Kazakhstan) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/IS2AI/Kazakh_TTS +* License: CC-BY-4.0 + +## Training + +Trained from scratch. diff --git a/kk/kk_KZ/iseke/x_low/kk_KZ-iseke-x_low.onnx b/kk/kk_KZ/iseke/x_low/kk_KZ-iseke-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8e5264d117f0eec8e329c1ba8eb9c220faae662c --- /dev/null +++ b/kk/kk_KZ/iseke/x_low/kk_KZ-iseke-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf526e1c089823c9f896f8f7fddd9b05d538752e139c8a2b4cf4fba41c9715c +size 28130791 diff --git a/kk/kk_KZ/iseke/x_low/kk_KZ-iseke-x_low.onnx.json b/kk/kk_KZ/iseke/x_low/kk_KZ-iseke-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..17e690cad63f3660a1f15fcb47d9168b20b7bfa7 --- /dev/null +++ b/kk/kk_KZ/iseke/x_low/kk_KZ-iseke-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "kk" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/kk/kk_KZ/issai/high/MODEL_CARD b/kk/kk_KZ/issai/high/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..7f44fcb74006d58f244aeceecf68cf139fd73c7e --- /dev/null +++ b/kk/kk_KZ/issai/high/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for issai (high) + +* Language: kk_KZ (Kazakh, Kazakhstan) +* Speakers: 6 +* Quality: high +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/IS2AI/Kazakh_TTS +* License: CC-BY-4.0 + +## Training + +Trained from scratch. diff --git a/kk/kk_KZ/issai/high/kk_KZ-issai-high.onnx b/kk/kk_KZ/issai/high/kk_KZ-issai-high.onnx new file mode 100644 index 0000000000000000000000000000000000000000..13b88f5b547849b2387ba8cb349f66c73d29c664 --- /dev/null +++ b/kk/kk_KZ/issai/high/kk_KZ-issai-high.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dee767c893e8535da821447d12cb030e3569e11254c14030a1da5d8b2222c16 +size 127864258 diff --git a/kk/kk_KZ/issai/high/kk_KZ-issai-high.onnx.json b/kk/kk_KZ/issai/high/kk_KZ-issai-high.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..5f44472d8c625ccf51c2ac7edc98f776a89a1109 --- /dev/null +++ b/kk/kk_KZ/issai/high/kk_KZ-issai-high.onnx.json @@ -0,0 +1,416 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "kk" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 6, + "speaker_id_map": { + "ISSAI_KazakhTTS2_M2": 0, + "ISSAI_KazakhTTS_M1_Iseke": 1, + "ISSAI_KazakhTTS2_F3": 2, + "ISSAI_KazakhTTS_F1_Raya": 3, + "ISSAI_KazakhTTS2_F1": 4, + "ISSAI_KazakhTTS2_F2": 5 + } +} \ No newline at end of file diff --git a/kk/kk_KZ/raya/x_low/MODEL_CARD b/kk/kk_KZ/raya/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..b98b7b4993639908f910d076019c0fce87d7a326 --- /dev/null +++ b/kk/kk_KZ/raya/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for raya (x_low) + +* Language: kk_KZ (Kazakh, Kazakhstan) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/IS2AI/Kazakh_TTS +* License: CC-BY-4.0 + +## Training + +Trained from scratch. diff --git a/kk/kk_KZ/raya/x_low/kk_KZ-raya-x_low.onnx b/kk/kk_KZ/raya/x_low/kk_KZ-raya-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d8594cf3bea112fdc6e23d26b4cc77b1e7e0e513 --- /dev/null +++ b/kk/kk_KZ/raya/x_low/kk_KZ-raya-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75552af00254baee9f85b976877e039f9530ea86ddb83d70262b72925785a0aa +size 28130791 diff --git a/kk/kk_KZ/raya/x_low/kk_KZ-raya-x_low.onnx.json b/kk/kk_KZ/raya/x_low/kk_KZ-raya-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..17e690cad63f3660a1f15fcb47d9168b20b7bfa7 --- /dev/null +++ b/kk/kk_KZ/raya/x_low/kk_KZ-raya-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "kk" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/ne/ne_NP/google/medium/MODEL_CARD b/ne/ne_NP/google/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..e205115b5d390670e56f3a89c4ad84271589ddb7 --- /dev/null +++ b/ne/ne_NP/google/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for google (medium) + +* Language: ne_NP (Nepali, Nepal) +* Speakers: 18 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: http://www.openslr.org/43/ +* License: CC-BY-SA-4.0 International + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/ne/ne_NP/google/medium/ne_NP-google-medium.onnx b/ne/ne_NP/google/medium/ne_NP-google-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..632dfd16e441294c84e2125fdcffdc9775eead5f --- /dev/null +++ b/ne/ne_NP/google/medium/ne_NP-google-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3ff3cbf97a7c01ebf29263c7fa1899ebed15e27a2d819b93dcfb86e10d39eaa +size 76766385 diff --git a/ne/ne_NP/google/medium/ne_NP-google-medium.onnx.json b/ne/ne_NP/google/medium/ne_NP-google-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..697a4d4aa956262334b745302e39ff2213d92159 --- /dev/null +++ b/ne/ne_NP/google/medium/ne_NP-google-medium.onnx.json @@ -0,0 +1,502 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "ne" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 18, + "speaker_id_map": { + "0546": 0, + "3614": 1, + "2099": 2, + "3960": 3, + "6834": 4, + "7957": 5, + "6329": 6, + "9407": 7, + "6587": 8, + "0258": 9, + "2139": 10, + "5687": 11, + "0283": 12, + "3997": 13, + "3154": 14, + "0883": 15, + "2027": 16, + "0649": 17 + }, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/ne/ne_NP/google/x_low/MODEL_CARD b/ne/ne_NP/google/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..ffc4c3729bfc992c0c5c6037cc0d6d11e8b0654f --- /dev/null +++ b/ne/ne_NP/google/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for google (x_low) + +* Language: ne_NE (Nepali, Nepal) +* Speakers: 18 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: http://www.openslr.org/43/ +* License: CC-BY-SA-4.0 International + +## Training + +Trained from scratch. diff --git a/ne/ne_NP/google/x_low/ne_NE-google-x_low.onnx b/ne/ne_NP/google/x_low/ne_NE-google-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..577ee91e2a7b8c23b5acc6c277b5ced2f27efe1c --- /dev/null +++ b/ne/ne_NP/google/x_low/ne_NE-google-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:283431c1f89be9b13a40f885da818b23ac13f6ca536e2a0a414c970d3b13f0f2 +size 27693157 diff --git a/ne/ne_NP/google/x_low/ne_NE-google-x_low.onnx.json b/ne/ne_NP/google/x_low/ne_NE-google-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..99a74ae9d4c23a5c0419f2905ac5c155e78d7e88 --- /dev/null +++ b/ne/ne_NP/google/x_low/ne_NE-google-x_low.onnx.json @@ -0,0 +1,428 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "ne" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 18, + "speaker_id_map": { + "0546": 0, + "3614": 1, + "2099": 2, + "3960": 3, + "6834": 4, + "7957": 5, + "6329": 6, + "9407": 7, + "6587": 8, + "0258": 9, + "2139": 10, + "5687": 11, + "0283": 12, + "3997": 13, + "3154": 14, + "0883": 15, + "2027": 16, + "0649": 17 + } +} \ No newline at end of file diff --git a/nl/nl_BE/nathalie/medium/MODEL_CARD b/nl/nl_BE/nathalie/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..9874ec439afb104991f1e4c545d163c93744d267 --- /dev/null +++ b/nl/nl_BE/nathalie/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for nathalie (medium) + +* Language: nl_BE (Dutch, Belgium) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/rhasspy/dataset-voice-nathalie +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality) diff --git a/nl/nl_BE/nathalie/medium/nl_BE-nathalie-medium.onnx b/nl/nl_BE/nathalie/medium/nl_BE-nathalie-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ce24583163ae7d0a9b07d3f40746cf26c638f343 --- /dev/null +++ b/nl/nl_BE/nathalie/medium/nl_BE-nathalie-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49cf48023861f9fd42e13a8632f068fee67d1ce244a6ee38f29595afbf0a6be4 +size 63201294 diff --git a/nl/nl_BE/nathalie/medium/nl_BE-nathalie-medium.onnx.json b/nl/nl_BE/nathalie/medium/nl_BE-nathalie-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..5858d15b51c61a52f288b66566e81b6d486cb797 --- /dev/null +++ b/nl/nl_BE/nathalie/medium/nl_BE-nathalie-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "nl" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/nl/nl_BE/nathalie/x_low/MODEL_CARD b/nl/nl_BE/nathalie/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..d19063e8d6ae1451d4d4836b7cba079b1e0af582 --- /dev/null +++ b/nl/nl_BE/nathalie/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for nathalie (x_low) + +* Language: nl_BE (Dutch, Belgium) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/rhasspy/dataset-voice-nathalie +* License: CC0 + +## Training + +Trained from scratch. diff --git a/nl/nl_BE/nathalie/x_low/nl_BE-nathalie-x_low.onnx b/nl/nl_BE/nathalie/x_low/nl_BE-nathalie-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3ba4e1d212c583fe9575cf7d7ce1bd7b94c05c61 --- /dev/null +++ b/nl/nl_BE/nathalie/x_low/nl_BE-nathalie-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d005d2d9b3db4326fc4a1ac86b61ab40252ccf97b76d527f4ffd76d4e3f7dbe +size 20628813 diff --git a/nl/nl_BE/nathalie/x_low/nl_BE-nathalie-x_low.onnx.json b/nl/nl_BE/nathalie/x_low/nl_BE-nathalie-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..ef7ff0f9e4d7b469fb2459e98afcef71a36595f3 --- /dev/null +++ b/nl/nl_BE/nathalie/x_low/nl_BE-nathalie-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "nl" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/nl/nl_BE/rdh/medium/MODEL_CARD b/nl/nl_BE/rdh/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..2d2c9715d0a9296117466adcebb145cbd4daefd4 --- /dev/null +++ b/nl/nl_BE/rdh/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for rdh (medium) + +* Language: nl_BE (Dutch, Belgium) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/r-dh/dutch-vl-tts +* License: CC0 1.0 Universal + +## Training + +Trained from scratch. diff --git a/nl/nl_BE/rdh/medium/nl_BE-rdh-medium.onnx b/nl/nl_BE/rdh/medium/nl_BE-rdh-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..5f0e2865b9f0bd01815aa60b34a4ab29485419fc --- /dev/null +++ b/nl/nl_BE/rdh/medium/nl_BE-rdh-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb1a9d89ff53dbd510c5d10bd1365c36a5f76249c3ca603076646fd778003db1 +size 63104526 diff --git a/nl/nl_BE/rdh/medium/nl_BE-rdh-medium.onnx.json b/nl/nl_BE/rdh/medium/nl_BE-rdh-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..5c601920e5029964f421dbcbd5740bfb078cbdee --- /dev/null +++ b/nl/nl_BE/rdh/medium/nl_BE-rdh-medium.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "nl" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/nl/nl_BE/rdh/x_low/MODEL_CARD b/nl/nl_BE/rdh/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..4c3e8589d41d1c89a9c815906cd5147198e720cc --- /dev/null +++ b/nl/nl_BE/rdh/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for rdh (x_low) + +* Language: nl_BE (Dutch, Belgium) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/r-dh/dutch-vl-tts +* License: CC0 1.0 Universal + +## Training + +Trained from scratch. diff --git a/nl/nl_BE/rdh/x_low/nl_BE-rdh-x_low.onnx b/nl/nl_BE/rdh/x_low/nl_BE-rdh-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..9cfdbc359942544db0a11768c1a57afd07b28342 --- /dev/null +++ b/nl/nl_BE/rdh/x_low/nl_BE-rdh-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe43651248219b4e816e47d9708f2812f2a09af99470ed822113f3e913430d52 +size 20628813 diff --git a/nl/nl_BE/rdh/x_low/nl_BE-rdh-x_low.onnx.json b/nl/nl_BE/rdh/x_low/nl_BE-rdh-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..ef7ff0f9e4d7b469fb2459e98afcef71a36595f3 --- /dev/null +++ b/nl/nl_BE/rdh/x_low/nl_BE-rdh-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "nl" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/nl/nl_NL/mls_5809/low/MODEL_CARD b/nl/nl_NL/mls_5809/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..3679777c385815b5067eb73c1a05725ca574ffb2 --- /dev/null +++ b/nl/nl_NL/mls_5809/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for mls_5809 (low) + +* Language: nl_NL (Dutch, Netherlands) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: http://www.openslr.org/94/ +* License: CC BY 4.0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/nl/nl_NL/mls_5809/low/nl_NL-mls_5809-low.onnx b/nl/nl_NL/mls_5809/low/nl_NL-mls_5809-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..27edab369bc67560660d487ed7577999363b13df --- /dev/null +++ b/nl/nl_NL/mls_5809/low/nl_NL-mls_5809-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7860ada7fa27e5e29b08e7531b0e0d74b3f0602e466a22ff95f59f80a0c4327 +size 63104526 diff --git a/nl/nl_NL/mls_5809/low/nl_NL-mls_5809-low.onnx.json b/nl/nl_NL/mls_5809/low/nl_NL-mls_5809-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..ef7ff0f9e4d7b469fb2459e98afcef71a36595f3 --- /dev/null +++ b/nl/nl_NL/mls_5809/low/nl_NL-mls_5809-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "nl" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/nl/nl_NL/mls_7432/low/MODEL_CARD b/nl/nl_NL/mls_7432/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..c34092f687247d7bf5d7d9fd77d12794e80fb4a5 --- /dev/null +++ b/nl/nl_NL/mls_7432/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for mls_7432 (low) + +* Language: nl_NL (Dutch, Netherlands) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: http://www.openslr.org/94/ +* License: CC BY 4.0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/nl/nl_NL/mls_7432/low/nl_NL-mls_7432-low.onnx b/nl/nl_NL/mls_7432/low/nl_NL-mls_7432-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..678725f113ecd48ea117a9aa5e800ca7c95097fa --- /dev/null +++ b/nl/nl_NL/mls_7432/low/nl_NL-mls_7432-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02feb278732c77f34c4e106d0cdc446e7e577ce29c5d7051da85a9c241ee42f0 +size 63104526 diff --git a/nl/nl_NL/mls_7432/low/nl_NL-mls_7432-low.onnx.json b/nl/nl_NL/mls_7432/low/nl_NL-mls_7432-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..ef7ff0f9e4d7b469fb2459e98afcef71a36595f3 --- /dev/null +++ b/nl/nl_NL/mls_7432/low/nl_NL-mls_7432-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "nl" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/no/no_NO/talesyntese/medium/MODEL_CARD b/no/no_NO/talesyntese/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..31d48e4eaa4ef4988dba357fe1442552e0cd8fd7 --- /dev/null +++ b/no/no_NO/talesyntese/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for talesyntese (medium) + +* Language: no_NO (Norwegian, Norway) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-15/ +* License: CC0 + +## Training + +Fine-tuned from U.S. English lessac voice (medium quality). diff --git a/no/no_NO/talesyntese/medium/no_NO-talesyntese-medium.onnx b/no/no_NO/talesyntese/medium/no_NO-talesyntese-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..9b6bd3afe71a0bdc684ba8c1ae3255328174bc2e --- /dev/null +++ b/no/no_NO/talesyntese/medium/no_NO-talesyntese-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b763aebe02e72c4628c4074c4b8b448f05ffe523b975bfcd58e2c5d531270c13 +size 63201294 diff --git a/no/no_NO/talesyntese/medium/no_NO-talesyntese-medium.onnx.json b/no/no_NO/talesyntese/medium/no_NO-talesyntese-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..a9eed8316d16002409877c81d5497908ed5ba43f --- /dev/null +++ b/no/no_NO/talesyntese/medium/no_NO-talesyntese-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "nb" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/pl/pl_PL/darkman/medium/MODEL_CARD b/pl/pl_PL/darkman/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..36e4b5617fdd97e27ce334b04681ddbf6773c5ad --- /dev/null +++ b/pl/pl_PL/darkman/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for darkman (medium) + +* Language: pl_PL (Polish, Poland) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/NabuCasa/voice-datasets +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/pl/pl_PL/darkman/medium/pl_PL-darkman-medium.onnx b/pl/pl_PL/darkman/medium/pl_PL-darkman-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..a65f75aeb7b097a197ecc31151a89a38951679f4 --- /dev/null +++ b/pl/pl_PL/darkman/medium/pl_PL-darkman-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db505438a5364e8e2e0242c4324130a873ed660dfbe8d9689cef428ffb1b645f +size 63201294 diff --git a/pl/pl_PL/darkman/medium/pl_PL-darkman-medium.onnx.json b/pl/pl_PL/darkman/medium/pl_PL-darkman-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..a6b979beeb2fab082e9643d5de872316ac86f8d8 --- /dev/null +++ b/pl/pl_PL/darkman/medium/pl_PL-darkman-medium.onnx.json @@ -0,0 +1,477 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "pl" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/pl/pl_PL/gosia/medium/MODEL_CARD b/pl/pl_PL/gosia/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..ece4edd11b1ff75e7d67f6258794fe99cf4be2f6 --- /dev/null +++ b/pl/pl_PL/gosia/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for gosia (medium) + +* Language: pl_PL (Polish, Poland) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/NabuCasa/voice-datasets +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/pl/pl_PL/gosia/medium/pl_PL-gosia-medium.onnx b/pl/pl_PL/gosia/medium/pl_PL-gosia-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..bebc4ab63fb2dfc1a87d7ff4f8536f4c10034b25 --- /dev/null +++ b/pl/pl_PL/gosia/medium/pl_PL-gosia-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38f66464240ed74f186e6b7dc13c6e3b22e023426299f25c2b3cc9dfa9373fbc +size 63201294 diff --git a/pl/pl_PL/gosia/medium/pl_PL-gosia-medium.onnx.json b/pl/pl_PL/gosia/medium/pl_PL-gosia-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..a6b979beeb2fab082e9643d5de872316ac86f8d8 --- /dev/null +++ b/pl/pl_PL/gosia/medium/pl_PL-gosia-medium.onnx.json @@ -0,0 +1,477 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "pl" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/pl/pl_PL/mls_6892/low/MODEL_CARD b/pl/pl_PL/mls_6892/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..aa92e602122dc99373fc677b91e77c7a9127ad1f --- /dev/null +++ b/pl/pl_PL/mls_6892/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for mls_6892 (low) + +* Language: pl_PL (Polish, Polish) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: http://www.openslr.org/94/ +* License: CC BY 4.0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/pl/pl_PL/mls_6892/low/pl_PL-mls_6892-low.onnx b/pl/pl_PL/mls_6892/low/pl_PL-mls_6892-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..afe0168192a4b7d06c751a5527836a0b66bf0867 --- /dev/null +++ b/pl/pl_PL/mls_6892/low/pl_PL-mls_6892-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b572ab1a0f1d3b722b2a545e0b38834e6f932852cd0f11a44c022baa8f104c10 +size 63104526 diff --git a/pl/pl_PL/mls_6892/low/pl_PL-mls_6892-low.onnx.json b/pl/pl_PL/mls_6892/low/pl_PL-mls_6892-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..d2b00d109ec4c8ef6c1c87b6a47a0da1e4aa8da5 --- /dev/null +++ b/pl/pl_PL/mls_6892/low/pl_PL-mls_6892-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "pl" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/pt/pt_BR/edresson/low/MODEL_CARD b/pt/pt_BR/edresson/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..0c11733ca3e9bc68d2b754eb2dfaaad5a03730d1 --- /dev/null +++ b/pt/pt_BR/edresson/low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for edresson (low) + +* Language: pt_BR (Portuguese, Brazil) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/Edresson/TTS-Portuguese-Corpus +* License: CC BY 4.0 + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/pt/pt_BR/edresson/low/pt_BR-edresson-low.onnx b/pt/pt_BR/edresson/low/pt_BR-edresson-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d7807968b6dae66e14eea4dfacdb46683f548327 --- /dev/null +++ b/pt/pt_BR/edresson/low/pt_BR-edresson-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de4cecee38b30bb1a6378a337af605d59f0c377df702c6a6752870db8991cd84 +size 63104526 diff --git a/pt/pt_BR/edresson/low/pt_BR-edresson-low.onnx.json b/pt/pt_BR/edresson/low/pt_BR-edresson-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..d68c61b7981f5262ff50e2df7b98f668ff786297 --- /dev/null +++ b/pt/pt_BR/edresson/low/pt_BR-edresson-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "pt-br" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/pt/pt_BR/faber/medium/MODEL_CARD b/pt/pt_BR/faber/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..d20a0a0d7502c64f56c11d1becd2e5bdf3916fa2 --- /dev/null +++ b/pt/pt_BR/faber/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for faber (medium) + +* Language: pt_BR (Portuguese, Brazil) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/NabuCasa/voice-datasets +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/pt/pt_BR/faber/medium/pt_BR-faber-medium.onnx b/pt/pt_BR/faber/medium/pt_BR-faber-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..324a5f23579ef280c7aa0f5c32a0ac301a2f765a --- /dev/null +++ b/pt/pt_BR/faber/medium/pt_BR-faber-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:858555e3a064209c57088fe6bd70c4c3dc54d03eaa00c45d5ecaf43a33f95aa7 +size 63201294 diff --git a/pt/pt_BR/faber/medium/pt_BR-faber-medium.onnx.json b/pt/pt_BR/faber/medium/pt_BR-faber-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..d3b580b8b4e52de191ea6d554db4d38fb882969c --- /dev/null +++ b/pt/pt_BR/faber/medium/pt_BR-faber-medium.onnx.json @@ -0,0 +1,481 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "pt-br" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": { + "c": [ + "k" + ] + }, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/ru/ru_RU/denis/medium/MODEL_CARD b/ru/ru_RU/denis/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..930f8b52307a2a3a24700fe15d52cd6a58e7e092 --- /dev/null +++ b/ru/ru_RU/denis/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for denis (medium) + +* Language: ru_RU (Russian, Russia) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/NabuCasa/voice-datasets +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/ru/ru_RU/denis/medium/ru_RU-denis-medium.onnx b/ru/ru_RU/denis/medium/ru_RU-denis-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..033b78cd23a48ab42159be1019edba1ceca0499b --- /dev/null +++ b/ru/ru_RU/denis/medium/ru_RU-denis-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15fab56e11a097858ee115545d0f697fc2a316c41a291a5362349fb870411b0a +size 63201294 diff --git a/ru/ru_RU/denis/medium/ru_RU-denis-medium.onnx.json b/ru/ru_RU/denis/medium/ru_RU-denis-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..28429a696614f1f85e9807b06e45319b6c57eb21 --- /dev/null +++ b/ru/ru_RU/denis/medium/ru_RU-denis-medium.onnx.json @@ -0,0 +1,477 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "ru" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/ru/ru_RU/dmitri/medium/MODEL_CARD b/ru/ru_RU/dmitri/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..fad059bbfed2e3448cc4de4ab7428dda1be7bd68 --- /dev/null +++ b/ru/ru_RU/dmitri/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for dmitri (medium) + +* Language: ru_RU (Russian, Russia) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/NabuCasa/voice-datasets +* License: CC0 + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/ru/ru_RU/dmitri/medium/ru_RU-dmitri-medium.onnx b/ru/ru_RU/dmitri/medium/ru_RU-dmitri-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..9f92b87ee286884cfe34f4f352d037a32d5995c2 --- /dev/null +++ b/ru/ru_RU/dmitri/medium/ru_RU-dmitri-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f073356ebc4bd0f80c5af58df2953a5988bd5bdab1eb38635ce960b071fbefcb +size 63201294 diff --git a/ru/ru_RU/dmitri/medium/ru_RU-dmitri-medium.onnx.json b/ru/ru_RU/dmitri/medium/ru_RU-dmitri-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..28429a696614f1f85e9807b06e45319b6c57eb21 --- /dev/null +++ b/ru/ru_RU/dmitri/medium/ru_RU-dmitri-medium.onnx.json @@ -0,0 +1,477 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "ru" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/ru/ru_RU/irina/medium/MODEL_CARD b/ru/ru_RU/irina/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..20d6abef2a7f737b324ede38bf8422b5a5208bdc --- /dev/null +++ b/ru/ru_RU/irina/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for irina (medium) + +* Language: ru_RU (Russian, Russia) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/RHVoice/RHVoice +* License: Unknown + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/ru/ru_RU/irina/medium/ru_RU-irina-medium.onnx b/ru/ru_RU/irina/medium/ru_RU-irina-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0b0af08563ddb90c30573fd988d2f80cb8b85dad --- /dev/null +++ b/ru/ru_RU/irina/medium/ru_RU-irina-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ff38212d23da300bbe3705c645e6e5b9475f0bfde01558eb17813e22acaaaaa +size 63201294 diff --git a/ru/ru_RU/irina/medium/ru_RU-irina-medium.onnx.json b/ru/ru_RU/irina/medium/ru_RU-irina-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..3143ec5d2d33f7b9d0ae134b6545b7f153db4566 --- /dev/null +++ b/ru/ru_RU/irina/medium/ru_RU-irina-medium.onnx.json @@ -0,0 +1,473 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "ru" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/ru/ru_RU/ruslan/medium/MODEL_CARD b/ru/ru_RU/ruslan/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..81aad6ac008f24b986f97431cc1da8a50531c3aa --- /dev/null +++ b/ru/ru_RU/ruslan/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for ruslan (medium) + +* Language: ru_RU (Russian, Russia) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://ruslan-corpus.github.io/ +* License: https://creativecommons.org/licenses/by-nc-sa/4.0/ + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/ru/ru_RU/ruslan/medium/ru_RU-ruslan-medium.onnx b/ru/ru_RU/ruslan/medium/ru_RU-ruslan-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..b5b94ba353364fca86f4a54af269a991f5a7eede --- /dev/null +++ b/ru/ru_RU/ruslan/medium/ru_RU-ruslan-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a5f88e0b20928064eb45d88e1daa21f8af62d18613580d32cbb4aed48dcf7f +size 63201294 diff --git a/ru/ru_RU/ruslan/medium/ru_RU-ruslan-medium.onnx.json b/ru/ru_RU/ruslan/medium/ru_RU-ruslan-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..86d46d835d3e37ecd3ee85bfec452d145b97cd7d --- /dev/null +++ b/ru/ru_RU/ruslan/medium/ru_RU-ruslan-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "ru" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/sv/sv_SE/nst/medium/MODEL_CARD b/sv/sv_SE/nst/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..2ccd0d637630294f1b09c96cb0df727ad785169d --- /dev/null +++ b/sv/sv_SE/nst/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for nst (medium) + +* Language: sv_SE (Swedish, Sweden) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-17/ +* License: CC0 + +## Training + +Trained from scratch by KBLab at The National Library of Sweden. diff --git a/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx b/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..52debfb4c66b1aa2d051ad5ccbbb95435f53794a --- /dev/null +++ b/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df011f56825a59dd1efc080c38a65a1ef70407e60f63050e9246f43a3d7e471e +size 63104526 diff --git a/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx.json b/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..efe9c0de2389ace781e972cf59957f87391fbe83 --- /dev/null +++ b/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "sv" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/sw/sw_CD/lanfrica/medium/MODEL_CARD b/sw/sw_CD/lanfrica/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..13dee66d516c1572d982790c7009be065e8e609c --- /dev/null +++ b/sw/sw_CD/lanfrica/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for lanfrica (medium) + +* Language: sw_CD (Swahili, Democratic Republic of the Congo) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://lanfrica.com/record/kiswahili-tts-dataset +* License: See URL + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/sw/sw_CD/lanfrica/medium/sw_CD-lanfrica-medium.onnx b/sw/sw_CD/lanfrica/medium/sw_CD-lanfrica-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3dc7dd3bfcd8943913035969f5a5bbbaf6e5fb61 --- /dev/null +++ b/sw/sw_CD/lanfrica/medium/sw_CD-lanfrica-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f195ed12ca5e7875114618e5f00207af364602e21ca78c8a6d3d7674f9259fa +size 63201294 diff --git a/sw/sw_CD/lanfrica/medium/sw_CD-lanfrica-medium.onnx.json b/sw/sw_CD/lanfrica/medium/sw_CD-lanfrica-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..f247a71c72d5e886f92519e61498d51558607aa7 --- /dev/null +++ b/sw/sw_CD/lanfrica/medium/sw_CD-lanfrica-medium.onnx.json @@ -0,0 +1,483 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "sw" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/uk/uk_UK/lada/x_low/MODEL_CARD b/uk/uk_UK/lada/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..a1b6c4ac22a54e8928885db63a90fff08ff4019f --- /dev/null +++ b/uk/uk_UK/lada/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for lada (x_low) + +* Language: uk_UK (Ukranian, Ukraine) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/egorsmkv/ukrainian-tts-datasets/tree/main/lada +* License: Apache 2.0 + +## Training + +Trained from scratch. diff --git a/uk/uk_UK/lada/x_low/uk_UK-lada-x_low.onnx b/uk/uk_UK/lada/x_low/uk_UK-lada-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..b71c528cd4fca040052b2f4f51248f1abf0aebe1 --- /dev/null +++ b/uk/uk_UK/lada/x_low/uk_UK-lada-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d015d3fc19ea6bd8ac3ca1fd0c0fbac5054c609599ee73799235fd2cf5c786 +size 20628813 diff --git a/uk/uk_UK/lada/x_low/uk_UK-lada-x_low.onnx.json b/uk/uk_UK/lada/x_low/uk_UK-lada-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..9ac4aee351f5628bf19c75aba3c68a4d427f3daa --- /dev/null +++ b/uk/uk_UK/lada/x_low/uk_UK-lada-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "uk" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/uk/uk_UK/ukrainian_tts/medium/MODEL_CARD b/uk/uk_UK/ukrainian_tts/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..8d1ae9ea2d44f9703cf4585b24a9984377e67199 --- /dev/null +++ b/uk/uk_UK/ukrainian_tts/medium/MODEL_CARD @@ -0,0 +1,16 @@ +# Model card for ukrainian_tts (medium) + +* Language: uk_UK (Ukrainian, Ukraine) +* Speakers: 3 +* Quality: medium +* Samplerate: 22,050Hz +* Phonemes: text + +## Dataset + +* URL: https://github.com/NabuCasa/voice-datasets +* License: CC0 + +## Training + +Trained from scratch. diff --git a/uk/uk_UK/ukrainian_tts/medium/uk_UK-ukrainian_tts-medium.onnx b/uk/uk_UK/ukrainian_tts/medium/uk_UK-ukrainian_tts-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..355c89e8df1efc9df0fe0ce63e240196d6fd711e --- /dev/null +++ b/uk/uk_UK/ukrainian_tts/medium/uk_UK-ukrainian_tts-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7920419ac5f6fd8b6450520f24b52ed5a319cb53dd018fbcd71c9e079cbac84f +size 76735663 diff --git a/uk/uk_UK/ukrainian_tts/medium/uk_UK-ukrainian_tts-medium.onnx.json b/uk/uk_UK/ukrainian_tts/medium/uk_UK-ukrainian_tts-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..da21c82c79d2f35e0cd210e52dc88f7d0efbddb2 --- /dev/null +++ b/uk/uk_UK/ukrainian_tts/medium/uk_UK-ukrainian_tts-medium.onnx.json @@ -0,0 +1,172 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "uk" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "text", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + ",": [ + 6 + ], + "-": [ + 7 + ], + ".": [ + 8 + ], + ":": [ + 9 + ], + ";": [ + 10 + ], + "?": [ + 11 + ], + "а": [ + 12 + ], + "б": [ + 13 + ], + "в": [ + 14 + ], + "г": [ + 15 + ], + "ґ": [ + 16 + ], + "д": [ + 17 + ], + "е": [ + 18 + ], + "є": [ + 19 + ], + "ж": [ + 20 + ], + "з": [ + 21 + ], + "и": [ + 22 + ], + "і": [ + 23 + ], + "ї": [ + 24 + ], + "й": [ + 25 + ], + "к": [ + 26 + ], + "л": [ + 27 + ], + "м": [ + 28 + ], + "н": [ + 29 + ], + "о": [ + 30 + ], + "п": [ + 31 + ], + "р": [ + 32 + ], + "с": [ + 33 + ], + "т": [ + 34 + ], + "у": [ + 35 + ], + "ф": [ + 36 + ], + "х": [ + 37 + ], + "ц": [ + 38 + ], + "ч": [ + 39 + ], + "ш": [ + 40 + ], + "щ": [ + 41 + ], + "ь": [ + 42 + ], + "ю": [ + 43 + ], + "я": [ + 44 + ], + "́": [ + 45 + ], + "̆": [ + 46 + ], + "̈": [ + 47 + ], + "—": [ + 48 + ] + }, + "num_symbols": 256, + "num_speakers": 3, + "speaker_id_map": { + "lada": 0, + "mykyta": 1, + "tetiana": 2 + }, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/vi/vi_VN/25hours_single/low/MODEL_CARD b/vi/vi_VN/25hours_single/low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..265071298d4122a889b183ac9a369ef5218b20f3 --- /dev/null +++ b/vi/vi_VN/25hours_single/low/MODEL_CARD @@ -0,0 +1,16 @@ +# Model card for 25hours_single (low) + +* Language: vi_VN (Vietnamese, Vietnam) +* Speakers: 1 +* Quality: low +* Samplerate: 16,000Hz + +## Dataset + +* Name: InfoRe Technology 1 +* URL: https://github.com/TensorSpeech/TensorFlowASR/blob/main/README.md#vietnamese +* License: Unknown + +## Training + +Finetuned from U.S. English Ryan voice (low quality). diff --git a/vi/vi_VN/25hours_single/low/vi_VN-25hours_single-low.onnx b/vi/vi_VN/25hours_single/low/vi_VN-25hours_single-low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..de6c1b62de5ba6316f8ffb732bd5d2ad574dad40 --- /dev/null +++ b/vi/vi_VN/25hours_single/low/vi_VN-25hours_single-low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266945c4a80cb3301450c8ba6fcf6ba3542c56cf952a08a8ff3d2d4ff0ab5609 +size 63104526 diff --git a/vi/vi_VN/25hours_single/low/vi_VN-25hours_single-low.onnx.json b/vi/vi_VN/25hours_single/low/vi_VN-25hours_single-low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..e598f1c8fee8ef6fab1947f195740e0b98b4ba3c --- /dev/null +++ b/vi/vi_VN/25hours_single/low/vi_VN-25hours_single-low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "vi" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file diff --git a/vi/vi_VN/vais1000/medium/MODEL_CARD b/vi/vi_VN/vais1000/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..d77035517b7e2e9446d43b2c83769890e14b000c --- /dev/null +++ b/vi/vi_VN/vais1000/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for vais1000 (medium) + +* Language: vi_VN (Vietnamese, Vietnam) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://ieee-dataport.org/documents/vais-1000-vietnamese-speech-synthesis-corpus +* License: https://creativecommons.org/licenses/by/4.0/ + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/vi/vi_VN/vais1000/medium/vi_VN-vais1000-medium.onnx b/vi/vi_VN/vais1000/medium/vi_VN-vais1000-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..c9b9df265b718e05ed60899d377f98725a8dbc95 --- /dev/null +++ b/vi/vi_VN/vais1000/medium/vi_VN-vais1000-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7c89e2c85f4d1edc24b6120c18aaf1bda614f06b511567eb9c7c0de15e2dab +size 63201294 diff --git a/vi/vi_VN/vais1000/medium/vi_VN-vais1000-medium.onnx.json b/vi/vi_VN/vais1000/medium/vi_VN-vais1000-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..24fcd141332d4f36cefa79643816599b66bc94fc --- /dev/null +++ b/vi/vi_VN/vais1000/medium/vi_VN-vais1000-medium.onnx.json @@ -0,0 +1,482 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "vi" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ], + "̺": [ + 152 + ], + "̻": [ + 153 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} diff --git a/vi/vi_VN/vivos/x_low/MODEL_CARD b/vi/vi_VN/vivos/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..d3166a2c48d549df8060326344199e5a46d753ab --- /dev/null +++ b/vi/vi_VN/vivos/x_low/MODEL_CARD @@ -0,0 +1,16 @@ +# Model card for vivos (x_low) + +* Language: vi_VN (Vietnamese, Vietnam) +* Speakers: 65 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* Name: InfoRe Technology 1 +* URL: https://ailab.hcmus.edu.vn/vivos/ +* License: CC BY-NC-SA 4.0 + +## Training + +Trained from scratch. diff --git a/vi/vi_VN/vivos/x_low/vi_VN-vivos-x_low.onnx b/vi/vi_VN/vivos/x_low/vi_VN-vivos-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..edb732298bbecb0903c96467f1434c609b981cfb --- /dev/null +++ b/vi/vi_VN/vivos/x_low/vi_VN-vivos-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ab13374eb0862021a545befe7727aef59e16117f1c075aa9e0362237ecc98ae +size 27789413 diff --git a/vi/vi_VN/vivos/x_low/vi_VN-vivos-x_low.onnx.json b/vi/vi_VN/vivos/x_low/vi_VN-vivos-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..7c8f697131574d1607d4034994a256599f5c3bdd --- /dev/null +++ b/vi/vi_VN/vivos/x_low/vi_VN-vivos-x_low.onnx.json @@ -0,0 +1,475 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "vi" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 65, + "speaker_id_map": { + "VIVOSSPK13": 0, + "VIVOSSPK14": 1, + "VIVOSSPK15": 2, + "VIVOSSPK16": 3, + "VIVOSSPK17": 4, + "VIVOSSPK18": 5, + "VIVOSSPK19": 6, + "VIVOSSPK20": 7, + "VIVOSSPK21": 8, + "VIVOSSPK22": 9, + "VIVOSSPK26": 10, + "VIVOSSPK34": 11, + "VIVOSSPK40": 12, + "VIVOSSPK41": 13, + "VIVOSSPK42": 14, + "VIVOSSPK43": 15, + "VIVOSSPK44": 16, + "VIVOSSPK45": 17, + "VIVOSSPK46": 18, + "VIVOSSPK38": 19, + "VIVOSSPK31": 20, + "VIVOSSPK35": 21, + "VIVOSSPK01": 22, + "VIVOSSPK02": 23, + "VIVOSSPK03": 24, + "VIVOSSPK04": 25, + "VIVOSSPK05": 26, + "VIVOSSPK06": 27, + "VIVOSSPK07": 28, + "VIVOSSPK08": 29, + "VIVOSSPK09": 30, + "VIVOSSPK10": 31, + "VIVOSSPK11": 32, + "VIVOSSPK12": 33, + "VIVOSSPK27": 34, + "VIVOSSPK36": 35, + "VIVOSSPK33": 36, + "VIVOSSPK32": 37, + "VIVOSSPK29": 38, + "VIVOSSPK39": 39, + "VIVOSSPK25": 40, + "VIVOSSPK28": 41, + "VIVOSSPK30": 42, + "VIVOSSPK37": 43, + "VIVOSSPK23": 44, + "VIVOSSPK24": 45, + "VIVOSDEV02": 46, + "VIVOSDEV03": 47, + "VIVOSDEV01": 48, + "VIVOSDEV04": 49, + "VIVOSDEV05": 50, + "VIVOSDEV06": 51, + "VIVOSDEV07": 52, + "VIVOSDEV08": 53, + "VIVOSDEV09": 54, + "VIVOSDEV10": 55, + "VIVOSDEV11": 56, + "VIVOSDEV12": 57, + "VIVOSDEV13": 58, + "VIVOSDEV14": 59, + "VIVOSDEV15": 60, + "VIVOSDEV16": 61, + "VIVOSDEV17": 62, + "VIVOSDEV18": 63, + "VIVOSDEV19": 64 + } +} \ No newline at end of file diff --git a/voices.json b/voices.json new file mode 100644 index 0000000000000000000000000000000000000000..2e90476030025468532daa9bdc400fbfa595ef9e --- /dev/null +++ b/voices.json @@ -0,0 +1,1579 @@ +{ + "zh_CN-huayan-x_low": { + "name": "huayan", + "language": "zh_CN", + "quality": "x_low", + "files": { + "zh_CN-huayan-x_low.onnx": { + "size_bytes": 20628813, + "md5_digest": "2b96570db6becd09814a608c8d14a64f" + }, + "zh_CN-huayan-x_low.onnx.json": { + "size_bytes": 5774, + "md5_digest": "b086dd6808691b3ba114645ab225f24b" + }, + "MODEL_CARD": { + "size_bytes": 237, + "md5_digest": "715587a977945498c5741b74eb81a1fd" + } + } + }, + "zh_CN-huayan-medium": { + "name": "huayan", + "language": "zh_CN", + "quality": "medium", + "files": { + "zh_CN-huayan-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "40cdb7930ff91b81574d5f0489e076ea" + }, + "zh_CN-huayan-medium.onnx.json": { + "size_bytes": 6771, + "md5_digest": "a62132d9b2506e7ad04297528e35fe6c" + }, + "MODEL_CARD": { + "size_bytes": 276, + "md5_digest": "b23255ace0cda4c2e02134d8a70c2e03" + } + } + }, + "ru_RU-irina-medium": { + "name": "irina", + "language": "ru_RU", + "quality": "medium", + "files": { + "ru_RU-irina-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "21fbe77fdc68bdc35d7adb6bf4f52199" + }, + "ru_RU-irina-medium.onnx.json": { + "size_bytes": 6696, + "md5_digest": "ff90aed0c0932d0d274a1da44b591a1e" + }, + "MODEL_CARD": { + "size_bytes": 271, + "md5_digest": "397e67453b4ea5a95642673d0debb5ba" + } + } + }, + "ru_RU-dmitri-medium": { + "name": "dmitri", + "language": "ru_RU", + "quality": "medium", + "files": { + "ru_RU-dmitri-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "589ccc91745a1e2353508ff62c5941b7" + }, + "ru_RU-dmitri-medium.onnx.json": { + "size_bytes": 6770, + "md5_digest": "f96b3949813e206055cd587727337268" + }, + "MODEL_CARD": { + "size_bytes": 276, + "md5_digest": "c19f9eff768d0c0e1f476a4c6ca1ff1e" + } + } + }, + "ru_RU-denis-medium": { + "name": "denis", + "language": "ru_RU", + "quality": "medium", + "files": { + "ru_RU-denis-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "76c2f14e521fef3ed574f97ad492728e" + }, + "ru_RU-denis-medium.onnx.json": { + "size_bytes": 6770, + "md5_digest": "f96b3949813e206055cd587727337268" + }, + "MODEL_CARD": { + "size_bytes": 275, + "md5_digest": "6fe09e0e097e4538809cc420653974e4" + } + } + }, + "ru_RU-ruslan-medium": { + "name": "ruslan", + "language": "ru_RU", + "quality": "medium", + "files": { + "ru_RU-ruslan-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "731eb188e63b4c57320e38047ba2d850" + }, + "ru_RU-ruslan-medium.onnx.json": { + "size_bytes": 6856, + "md5_digest": "907f1cfa9aed04f134a7c702f2c10949" + }, + "MODEL_CARD": { + "size_bytes": 313, + "md5_digest": "7b50a255192cc1c44358d7cb20ddbb5c" + } + } + }, + "nl_BE-nathalie-x_low": { + "name": "nathalie", + "language": "nl_BE", + "quality": "x_low", + "files": { + "nl_BE-nathalie-x_low.onnx": { + "size_bytes": 20628813, + "md5_digest": "4a00803b60caecad30ea612bcd9f9344" + }, + "nl_BE-nathalie-x_low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "189e6fd4e40bf8322800f50a743b4778" + }, + "MODEL_CARD": { + "size_bytes": 246, + "md5_digest": "5df62094bde427374223f91f44476392" + } + } + }, + "nl_BE-nathalie-medium": { + "name": "nathalie", + "language": "nl_BE", + "quality": "medium", + "files": { + "nl_BE-nathalie-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "ab0c38b5f66764b59ad9e3e98b1c2172" + }, + "nl_BE-nathalie-medium.onnx.json": { + "size_bytes": 6856, + "md5_digest": "5cfa8e713729ac1f29a8d4204ca5b809" + }, + "MODEL_CARD": { + "size_bytes": 284, + "md5_digest": "ff335f87ca41a3f89180781498e02635" + } + } + }, + "nl_BE-rdh-x_low": { + "name": "rdh", + "language": "nl_BE", + "quality": "x_low", + "files": { + "nl_BE-rdh-x_low.onnx": { + "size_bytes": 20628813, + "md5_digest": "7d60d0de9ad9ec11a1d293665743afda" + }, + "nl_BE-rdh-x_low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "189e6fd4e40bf8322800f50a743b4778" + }, + "MODEL_CARD": { + "size_bytes": 242, + "md5_digest": "6d0157bcd5ff281717e663d56dab980e" + } + } + }, + "nl_BE-rdh-medium": { + "name": "rdh", + "language": "nl_BE", + "quality": "medium", + "files": { + "nl_BE-rdh-medium.onnx": { + "size_bytes": 63104526, + "md5_digest": "33d3469d745677ec4d7e96eb4145b09e" + }, + "nl_BE-rdh-medium.onnx.json": { + "size_bytes": 5773, + "md5_digest": "eaae3e21dcd4899d5b522067ec994fd9" + }, + "MODEL_CARD": { + "size_bytes": 244, + "md5_digest": "dc4487b06fcef6ff270c852ce12947b9" + } + } + }, + "nl_NL-mls_7432-low": { + "name": "mls_7432", + "language": "nl_NL", + "quality": "low", + "files": { + "nl_NL-mls_7432-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "044b69d583e191203997761434607273" + }, + "nl_NL-mls_7432-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "189e6fd4e40bf8322800f50a743b4778" + }, + "MODEL_CARD": { + "size_bytes": 260, + "md5_digest": "5d8ee8e955f077fc99cac61191d00892" + } + } + }, + "nl_NL-mls_5809-low": { + "name": "mls_5809", + "language": "nl_NL", + "quality": "low", + "files": { + "nl_NL-mls_5809-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "e69130a776b04c9962a1fefb4878d7d9" + }, + "nl_NL-mls_5809-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "189e6fd4e40bf8322800f50a743b4778" + }, + "MODEL_CARD": { + "size_bytes": 261, + "md5_digest": "ac4b35e581cea8418909947a29a671bb" + } + } + }, + "it_IT-riccardo-x_low": { + "name": "riccardo", + "language": "it_IT", + "quality": "x_low", + "files": { + "it_IT-riccardo-x_low.onnx": { + "size_bytes": 28130791, + "md5_digest": "2c564b67f6bfaf3ad02d28ab528929b8" + }, + "it_IT-riccardo-x_low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "2216aa093b516a5f07b7634f4c7fda1f" + }, + "MODEL_CARD": { + "size_bytes": 260, + "md5_digest": "3e70f29ab998ac0380edc0cec7395e80" + } + } + }, + "ne_NP-google-x_low": { + "name": "google", + "language": "ne_NP", + "quality": "x_low", + "files": { + "ne_NE-google-x_low.onnx": { + "size_bytes": 27693157, + "md5_digest": "b11030daccc781a7db64c9413197ca8a" + }, + "ne_NE-google-x_low.onnx.json": { + "size_bytes": 6128, + "md5_digest": "309124f6068864743fba1c021cb599f4" + }, + "MODEL_CARD": { + "size_bytes": 244, + "md5_digest": "5ea405c002a69df5961c8d43cadbb844" + } + } + }, + "ne_NP-google-medium": { + "name": "google", + "language": "ne_NP", + "quality": "medium", + "files": { + "ne_NP-google-medium.onnx": { + "size_bytes": 76766385, + "md5_digest": "2c24ccfe18eca2f14bccd0a188516109" + }, + "ne_NP-google-medium.onnx.json": { + "size_bytes": 7211, + "md5_digest": "c08b45f2b25b2ef1806d633c14c6191d" + }, + "MODEL_CARD": { + "size_bytes": 283, + "md5_digest": "afe022ba061870d0c9fe085fe9a9f31f" + } + } + }, + "el_GR-rapunzelina-low": { + "name": "rapunzelina", + "language": "el_GR", + "quality": "low", + "files": { + "el_GR-rapunzelina-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "04e0151b653bb64540b1cde027054140" + }, + "el_GR-rapunzelina-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "72e6d38fb08d93b9858f246653b63f88" + }, + "MODEL_CARD": { + "size_bytes": 303, + "md5_digest": "c75270b41e7bf60dacd351753a483574" + } + } + }, + "kk_KZ-issai-high": { + "name": "issai", + "language": "kk_KZ", + "quality": "high", + "files": { + "kk_KZ-issai-high.onnx": { + "size_bytes": 127864258, + "md5_digest": "d5a97c25feb0949c187ae5f8e72753e3" + }, + "kk_KZ-issai-high.onnx.json": { + "size_bytes": 5990, + "md5_digest": "5fc3ec6aee3d104c00a3e2ee0914e9d5" + }, + "MODEL_CARD": { + "size_bytes": 237, + "md5_digest": "30487d1011336ed15feabd156424cbd9" + } + } + }, + "kk_KZ-raya-x_low": { + "name": "raya", + "language": "kk_KZ", + "quality": "x_low", + "files": { + "kk_KZ-raya-x_low.onnx": { + "size_bytes": 28130791, + "md5_digest": "476ecc32e07cad26572a50f26d0ebe28" + }, + "kk_KZ-raya-x_low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "838be60c9b2760337eb8e54a671f317b" + }, + "MODEL_CARD": { + "size_bytes": 238, + "md5_digest": "fb34d2e65fac42f4d6e003d3d30c897e" + } + } + }, + "kk_KZ-iseke-x_low": { + "name": "iseke", + "language": "kk_KZ", + "quality": "x_low", + "files": { + "kk_KZ-iseke-x_low.onnx": { + "size_bytes": 28130791, + "md5_digest": "1674f3f4ce48981d77e500741afa4ff9" + }, + "kk_KZ-iseke-x_low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "838be60c9b2760337eb8e54a671f317b" + }, + "MODEL_CARD": { + "size_bytes": 239, + "md5_digest": "fce637093c4437a1f929280913a86aa5" + } + } + }, + "pt_BR-faber-medium": { + "name": "faber", + "language": "pt_BR", + "quality": "medium", + "files": { + "pt_BR-faber-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "e0724a2f07965f6523d2a1e96b488a4c" + }, + "pt_BR-faber-medium.onnx.json": { + "size_bytes": 6819, + "md5_digest": "b6c2c4e9755d9bd92485a65d4070cb2f" + }, + "MODEL_CARD": { + "size_bytes": 278, + "md5_digest": "a81a3840b1749cf34b0e31de1577ef47" + } + } + }, + "pt_BR-edresson-low": { + "name": "edresson", + "language": "pt_BR", + "quality": "low", + "files": { + "pt_BR-edresson-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "53e365c040dd07890fe1855b64c7cc58" + }, + "pt_BR-edresson-low.onnx.json": { + "size_bytes": 5776, + "md5_digest": "3ec806d00312e12c21743eb88e8c7c81" + }, + "MODEL_CARD": { + "size_bytes": 283, + "md5_digest": "62cde47b9a3214109e601f90eeadea11" + } + } + }, + "de_DE-eva_k-x_low": { + "name": "eva_k", + "language": "de_DE", + "quality": "x_low", + "files": { + "de_DE-eva_k-x_low.onnx": { + "size_bytes": 20628813, + "md5_digest": "51bfc52a58282c2e4fc01ae66567a708" + }, + "de_DE-eva_k-x_low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "1a46002d8bbef555078530e0953e61f9" + }, + "MODEL_CARD": { + "size_bytes": 246, + "md5_digest": "02b01f3d47b2798ece347b2c7e94c9e9" + } + } + }, + "de_DE-pavoque-low": { + "name": "pavoque", + "language": "de_DE", + "quality": "low", + "files": { + "de_DE-pavoque-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "bc37dccbad87fd65c8501c412c0c31ca" + }, + "de_DE-pavoque-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "1a46002d8bbef555078530e0953e61f9" + }, + "MODEL_CARD": { + "size_bytes": 309, + "md5_digest": "e0aacaf7b834938c4e3ad1fb3f68ef87" + } + } + }, + "de_DE-kerstin-low": { + "name": "kerstin", + "language": "de_DE", + "quality": "low", + "files": { + "de_DE-kerstin-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "1d5e5788cfddb04cbb34418f2841931e" + }, + "de_DE-kerstin-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "1a46002d8bbef555078530e0953e61f9" + }, + "MODEL_CARD": { + "size_bytes": 272, + "md5_digest": "69ec1bc99fc7e19c9ddcdf712920a6c7" + } + } + }, + "de_DE-thorsten-low": { + "name": "thorsten", + "language": "de_DE", + "quality": "low", + "files": { + "de_DE-thorsten-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "c06eb96aceb61895fcb09ffc30eef60b" + }, + "de_DE-thorsten-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "1a46002d8bbef555078530e0953e61f9" + }, + "MODEL_CARD": { + "size_bytes": 274, + "md5_digest": "203f58b93f0372564e745f1e05ea47bb" + } + } + }, + "de_DE-thorsten-medium": { + "name": "thorsten", + "language": "de_DE", + "quality": "medium", + "files": { + "de_DE-thorsten-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "a129b00fb3078df43c96bab6c94535c0" + }, + "de_DE-thorsten-medium.onnx.json": { + "size_bytes": 6770, + "md5_digest": "d66233afbd7afec773e80c569bd0a74d" + }, + "MODEL_CARD": { + "size_bytes": 285, + "md5_digest": "e84cf8b09957fccceb068a3c1664d0f3" + } + } + }, + "de_DE-ramona-low": { + "name": "ramona", + "language": "de_DE", + "quality": "low", + "files": { + "de_DE-ramona-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "b4aaf3673170a0d96519cdc992c23fda" + }, + "de_DE-ramona-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "1a46002d8bbef555078530e0953e61f9" + }, + "MODEL_CARD": { + "size_bytes": 255, + "md5_digest": "c970992423b5fc7a26340a9363e15952" + } + } + }, + "de_DE-karlsson-low": { + "name": "karlsson", + "language": "de_DE", + "quality": "low", + "files": { + "de_DE-karlsson-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "c94b5b8e8c7147b4b2c4a19ca5a3c41b" + }, + "de_DE-karlsson-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "1a46002d8bbef555078530e0953e61f9" + }, + "MODEL_CARD": { + "size_bytes": 289, + "md5_digest": "6e2f3eec10cf7fceb0b68b67eccd06a4" + } + } + }, + "da_DK-talesyntese-medium": { + "name": "talesyntese", + "language": "da_DK", + "quality": "medium", + "files": { + "da_DK-talesyntese-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "9c05494a3e0c1136337581e01222395d" + }, + "da_DK-talesyntese-medium.onnx.json": { + "size_bytes": 6826, + "md5_digest": "a2543c3488e94c36cc4ca7326a5d698e" + }, + "MODEL_CARD": { + "size_bytes": 308, + "md5_digest": "628cc03fca8f5d2c454824d6252955ad" + } + } + }, + "is_IS-ugla-medium": { + "name": "ugla", + "language": "is_IS", + "quality": "medium", + "files": { + "is_IS-ugla-medium.onnx": { + "size_bytes": 76495465, + "md5_digest": "722fcea3546f0113ad6664290aa97cab" + }, + "is_IS-ugla-medium.onnx.json": { + "size_bytes": 5773, + "md5_digest": "fe40a8dc0810d54d53f526ea9b97fac0" + }, + "MODEL_CARD": { + "size_bytes": 240, + "md5_digest": "a3ba0a35bc26d440ee3b0872e435fcd5" + } + } + }, + "is_IS-salka-medium": { + "name": "salka", + "language": "is_IS", + "quality": "medium", + "files": { + "is_IS-salka-medium.onnx": { + "size_bytes": 76495465, + "md5_digest": "5967c9456b931d6123687d7b78fd81a7" + }, + "is_IS-salka-medium.onnx.json": { + "size_bytes": 5773, + "md5_digest": "fe40a8dc0810d54d53f526ea9b97fac0" + }, + "MODEL_CARD": { + "size_bytes": 241, + "md5_digest": "0f3d286069e4c7bead9b40ece3bbefe6" + } + } + }, + "is_IS-steinn-medium": { + "name": "steinn", + "language": "is_IS", + "quality": "medium", + "files": { + "is_IS-steinn-medium.onnx": { + "size_bytes": 76495465, + "md5_digest": "fd8189eb0a72e78d525e70a71aaa792c" + }, + "is_IS-steinn-medium.onnx.json": { + "size_bytes": 5773, + "md5_digest": "fe40a8dc0810d54d53f526ea9b97fac0" + }, + "MODEL_CARD": { + "size_bytes": 242, + "md5_digest": "45ab46f37e5a6bdf739d58496752e6a0" + } + } + }, + "is_IS-bui-medium": { + "name": "bui", + "language": "is_IS", + "quality": "medium", + "files": { + "is_IS-bui-medium.onnx": { + "size_bytes": 76495465, + "md5_digest": "08332bb41a67b52a3361bd1e8e36fb10" + }, + "is_IS-bui-medium.onnx.json": { + "size_bytes": 5773, + "md5_digest": "fe40a8dc0810d54d53f526ea9b97fac0" + }, + "MODEL_CARD": { + "size_bytes": 246, + "md5_digest": "a055aad199d8cc58e52913ff2af461d8" + } + } + }, + "vi_VN-vivos-x_low": { + "name": "vivos", + "language": "vi_VN", + "quality": "x_low", + "files": { + "vi_VN-vivos-x_low.onnx": { + "size_bytes": 27789413, + "md5_digest": "d5880d32e340f57489dcb9d4f1f7aa04" + }, + "vi_VN-vivos-x_low.onnx.json": { + "size_bytes": 7458, + "md5_digest": "c578b42f2c512d8011c842a12af23134" + }, + "MODEL_CARD": { + "size_bytes": 272, + "md5_digest": "6bd1265a94a8f6bcce74a5b1145a7f95" + } + } + }, + "vi_VN-25hours_single-low": { + "name": "25hours_single", + "language": "vi_VN", + "quality": "low", + "files": { + "vi_VN-25hours_single-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "54ff8fb35b0084336377ddd10717e1fa" + }, + "vi_VN-25hours_single-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "9af5281977bb1d9d06297d4585c38597" + }, + "MODEL_CARD": { + "size_bytes": 343, + "md5_digest": "25eb4744418cd7b8da0a9096dcfa6e61" + } + } + }, + "vi_VN-vais1000-medium": { + "name": "vais1000", + "language": "vi_VN", + "quality": "medium", + "files": { + "vi_VN-vais1000-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "5e42428c4f6131f75557cf156c9c1526" + }, + "vi_VN-vais1000-medium.onnx.json": { + "size_bytes": 6827, + "md5_digest": "534d6342e0dae0fa30abcce484c4cd7f" + }, + "MODEL_CARD": { + "size_bytes": 361, + "md5_digest": "1beeecba9042e5925b0c5fbd138c779d" + } + } + }, + "sv_SE-nst-medium": { + "name": "nst", + "language": "sv_SE", + "quality": "medium", + "files": { + "sv_SE-nst-medium.onnx": { + "size_bytes": 63104526, + "md5_digest": "20266cf58e93ca2140444b77398aea04" + }, + "sv_SE-nst-medium.onnx.json": { + "size_bytes": 5773, + "md5_digest": "8ba2f8c640baa08bb1144f8e93b63d6e" + }, + "MODEL_CARD": { + "size_bytes": 306, + "md5_digest": "4a7cdb8f218a909b2b5e81d1903628da" + } + } + }, + "ca_ES-upc_ona-x_low": { + "name": "upc_ona", + "language": "ca_ES", + "quality": "x_low", + "files": { + "ca_ES-upc_ona-x_low.onnx": { + "size_bytes": 20628813, + "md5_digest": "ca22734cd8c5b01dd1fefbb42067ab06" + }, + "ca_ES-upc_ona-x_low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "44952d2434e8759aed8e780c6ae695fa" + }, + "MODEL_CARD": { + "size_bytes": 258, + "md5_digest": "1f555643ff6f7d9133679d730f3f6016" + } + } + }, + "ca_ES-upc_ona-medium": { + "name": "upc_ona", + "language": "ca_ES", + "quality": "medium", + "files": { + "ca_ES-upc_ona-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "58ff3b049b6b721a4c353a551ec5ef3a" + }, + "ca_ES-upc_ona-medium.onnx.json": { + "size_bytes": 6856, + "md5_digest": "1e79dd74c74e1de437b5424b40a2197e" + }, + "MODEL_CARD": { + "size_bytes": 296, + "md5_digest": "395c782a56632400f46e7c442c7718bb" + } + } + }, + "ca_ES-upc_pau-x_low": { + "name": "upc_pau", + "language": "ca_ES", + "quality": "x_low", + "files": { + "ca_ES-upc_pau-x_low.onnx": { + "size_bytes": 28130791, + "md5_digest": "504e8a643d5284fbfc95e9e392288b86" + }, + "ca_ES-upc_pau-x_low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "44952d2434e8759aed8e780c6ae695fa" + }, + "MODEL_CARD": { + "size_bytes": 258, + "md5_digest": "4ff8699c4439c9f49180457f0becc49e" + } + } + }, + "en_GB-southern_english_female-low": { + "name": "southern_english_female", + "language": "en_GB", + "quality": "low", + "files": { + "en_GB-southern_english_female-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "596c7ed4d8488cf64e027765dce2dad1" + }, + "en_GB-southern_english_female-low.onnx.json": { + "size_bytes": 5781, + "md5_digest": "9c7dc3e4f83524944b196c1646dc7fd6" + }, + "MODEL_CARD": { + "size_bytes": 296, + "md5_digest": "77ac998c8b37842ef98594567f141629" + } + } + }, + "en_GB-northern_english_male-medium": { + "name": "northern_english_male", + "language": "en_GB", + "quality": "medium", + "files": { + "en_GB-northern_english_male-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "4c9a9735bfb76ad67c8b31b23d6840a0" + }, + "en_GB-northern_english_male-medium.onnx.json": { + "size_bytes": 6778, + "md5_digest": "b46756986b58220e1051944148476b15" + }, + "MODEL_CARD": { + "size_bytes": 305, + "md5_digest": "8d1b725154c658ead4f068389c319c82" + } + } + }, + "en_GB-alba-medium": { + "name": "alba", + "language": "en_GB", + "quality": "medium", + "files": { + "en_GB-alba-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "c07f313752bb3aba8061041666251654" + }, + "en_GB-alba-medium.onnx.json": { + "size_bytes": 6864, + "md5_digest": "1b2417e1691fc4e2d6703d800615aaf7" + }, + "MODEL_CARD": { + "size_bytes": 324, + "md5_digest": "d5a8716acb311b20e0f28710d0fcc982" + } + } + }, + "en_GB-vctk-medium": { + "name": "vctk", + "language": "en_GB", + "quality": "medium", + "files": { + "en_GB-vctk-medium.onnx": { + "size_bytes": 76952753, + "md5_digest": "573025290fdc68812543b7438ace0c29" + }, + "en_GB-vctk-medium.onnx.json": { + "size_bytes": 9052, + "md5_digest": "950bdc6f8a64618734ffac6bdc7f221b" + }, + "MODEL_CARD": { + "size_bytes": 326, + "md5_digest": "b88a963e3bee27bc4fff84563f1be388" + } + } + }, + "en_GB-alan-low": { + "name": "alan", + "language": "en_GB", + "quality": "low", + "files": { + "en_GB-alan-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "2acae8c79395ab109a7572f0afa61fff" + }, + "en_GB-alan-low.onnx.json": { + "size_bytes": 5781, + "md5_digest": "9c7dc3e4f83524944b196c1646dc7fd6" + }, + "MODEL_CARD": { + "size_bytes": 309, + "md5_digest": "b116c3cbdebac99ade9af03807cb9301" + } + } + }, + "en_GB-alan-medium": { + "name": "alan", + "language": "en_GB", + "quality": "medium", + "files": { + "en_GB-alan-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "8f6b35eeb8ef6269021c6cb6d2414c9b" + }, + "en_GB-alan-medium.onnx.json": { + "size_bytes": 6864, + "md5_digest": "1b2417e1691fc4e2d6703d800615aaf7" + }, + "MODEL_CARD": { + "size_bytes": 320, + "md5_digest": "24a2232470ca1be071debf53c984666e" + } + } + }, + "en_GB-aru-medium": { + "name": "aru", + "language": "en_GB", + "quality": "medium", + "files": { + "en_GB-aru-medium.onnx": { + "size_bytes": 76754097, + "md5_digest": "7862d75539b8ef867e7c04e772d323ea" + }, + "en_GB-aru-medium.onnx.json": { + "size_bytes": 7075, + "md5_digest": "7fa8ec61857f02e448f460002ec6039e" + }, + "MODEL_CARD": { + "size_bytes": 368, + "md5_digest": "09496f38078e0eefe220a497b7b70631" + } + } + }, + "en_GB-jenny_dioco-medium": { + "name": "jenny_dioco", + "language": "en_GB", + "quality": "medium", + "files": { + "en_GB-jenny_dioco-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "d08f2f7edf0c858275a7eca74ff2a9e4" + }, + "en_GB-jenny_dioco-medium.onnx.json": { + "size_bytes": 6864, + "md5_digest": "1b2417e1691fc4e2d6703d800615aaf7" + }, + "MODEL_CARD": { + "size_bytes": 298, + "md5_digest": "ff351d05502764d5b4a074e0648e9434" + } + } + }, + "en_US-kusal-medium": { + "name": "kusal", + "language": "en_US", + "quality": "medium", + "files": { + "en_US-kusal-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "95334de7385a03c5c9de25b920c33492" + }, + "en_US-kusal-medium.onnx.json": { + "size_bytes": 6859, + "md5_digest": "a943690c845cd7f54bd5a7229951465e" + }, + "MODEL_CARD": { + "size_bytes": 279, + "md5_digest": "b627e950e8e10a1ec7b30e5f9b312a05" + } + } + }, + "en_US-libritts-high": { + "name": "libritts", + "language": "en_US", + "quality": "high", + "files": { + "en_US-libritts-high.onnx": { + "size_bytes": 136673811, + "md5_digest": "61d7845257f8abdc27476f606151ef8d" + }, + "en_US-libritts-high.onnx.json": { + "size_bytes": 24484, + "md5_digest": "ffab55eb698798ef8fcce3dc47bbcb26" + }, + "MODEL_CARD": { + "size_bytes": 255, + "md5_digest": "cdeac934f1154489924a071470b22365" + } + } + }, + "en_US-l2arctic-medium": { + "name": "l2arctic", + "language": "en_US", + "quality": "medium", + "files": { + "en_US-l2arctic-medium.onnx": { + "size_bytes": 76778673, + "md5_digest": "a71d8acf9b01676931cd548f739382cd" + }, + "en_US-l2arctic-medium.onnx.json": { + "size_bytes": 7322, + "md5_digest": "cf02a79aa726e13d35ed69788ccfb52a" + }, + "MODEL_CARD": { + "size_bytes": 365, + "md5_digest": "8d5e9dc31cba2a9b7ee68a2a70e084f2" + } + } + }, + "en_US-kathleen-low": { + "name": "kathleen", + "language": "en_US", + "quality": "low", + "files": { + "en_US-kathleen-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "dd1ab131724b1cff76fe388252bec47b" + }, + "en_US-kathleen-low.onnx.json": { + "size_bytes": 5776, + "md5_digest": "06b7255db7f49069a9abcb3037804cc5" + }, + "MODEL_CARD": { + "size_bytes": 281, + "md5_digest": "0585e0a798d093c9ee090b99d9c8f68e" + } + } + }, + "en_US-amy-low": { + "name": "amy", + "language": "en_US", + "quality": "low", + "files": { + "en_US-amy-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "3c3f6a6ec605f3a59763256d3b2db012" + }, + "en_US-amy-low.onnx.json": { + "size_bytes": 5776, + "md5_digest": "06b7255db7f49069a9abcb3037804cc5" + }, + "MODEL_CARD": { + "size_bytes": 273, + "md5_digest": "e1cdd84aa7493b8fbe1e6471f6f93cea" + } + } + }, + "en_US-amy-medium": { + "name": "amy", + "language": "en_US", + "quality": "medium", + "files": { + "en_US-amy-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "778d28aeb95fcdf8a882344d9df142fc" + }, + "en_US-amy-medium.onnx.json": { + "size_bytes": 6859, + "md5_digest": "a943690c845cd7f54bd5a7229951465e" + }, + "MODEL_CARD": { + "size_bytes": 281, + "md5_digest": "6fca05ee5bfe8b28211b88b86b47e822" + } + } + }, + "en_US-ryan-low": { + "name": "ryan", + "language": "en_US", + "quality": "low", + "files": { + "en_US-ryan-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "32f6a995d6d561cd040b20a76f4edb1e" + }, + "en_US-ryan-low.onnx.json": { + "size_bytes": 5777, + "md5_digest": "9cacb6725a72074808d677454d046cff" + }, + "MODEL_CARD": { + "size_bytes": 263, + "md5_digest": "030252d21b0bd1048c37a9eb7f94eb17" + } + } + }, + "en_US-ryan-high": { + "name": "ryan", + "language": "en_US", + "quality": "high", + "files": { + "en_US-ryan-high.onnx": { + "size_bytes": 120786792, + "md5_digest": "5d879a17bddf5007f76655b445ba78b4" + }, + "en_US-ryan-high.onnx.json": { + "size_bytes": 5776, + "md5_digest": "6023490bab8a15da7e59bb9fd3c29762" + }, + "MODEL_CARD": { + "size_bytes": 265, + "md5_digest": "9c966517ed0bfbffbfdb218e99dbeadd" + } + } + }, + "en_US-ryan-medium": { + "name": "ryan", + "language": "en_US", + "quality": "medium", + "files": { + "en_US-ryan-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "8f06d3aff8ded5a7f13f907e6bec32ac" + }, + "en_US-ryan-medium.onnx.json": { + "size_bytes": 6859, + "md5_digest": "a943690c845cd7f54bd5a7229951465e" + }, + "MODEL_CARD": { + "size_bytes": 306, + "md5_digest": "79d9200481a9dcabfa1803cb9e31c28a" + } + } + }, + "en_US-danny-low": { + "name": "danny", + "language": "en_US", + "quality": "low", + "files": { + "en_US-danny-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "73cc296e178ab3d2a5698179b629cd12" + }, + "en_US-danny-low.onnx.json": { + "size_bytes": 5776, + "md5_digest": "06b7255db7f49069a9abcb3037804cc5" + }, + "MODEL_CARD": { + "size_bytes": 275, + "md5_digest": "62d30d0cccea265949980cb48212ebee" + } + } + }, + "en_US-arctic-medium": { + "name": "arctic", + "language": "en_US", + "quality": "medium", + "files": { + "en_US-arctic-medium.onnx": { + "size_bytes": 76766385, + "md5_digest": "497c47037c2e279faf467e0a06f965d2" + }, + "en_US-arctic-medium.onnx.json": { + "size_bytes": 7196, + "md5_digest": "bd450bc646a3e00bda683ff812134a4a" + }, + "MODEL_CARD": { + "size_bytes": 289, + "md5_digest": "efe5b89e46cf8e0efa254203da8c7baf" + } + } + }, + "en_US-lessac-low": { + "name": "lessac", + "language": "en_US", + "quality": "low", + "files": { + "en_US-lessac-low.onnx": { + "size_bytes": 63201294, + "md5_digest": "31883a7506589feadf3c3474fd8ef658" + }, + "en_US-lessac-low.onnx.json": { + "size_bytes": 6860, + "md5_digest": "e0dc276d7eb8c21d687e43def347d53b" + }, + "MODEL_CARD": { + "size_bytes": 345, + "md5_digest": "999cbf2c337d8fb2f21b0fa2c95e9e85" + } + } + }, + "en_US-lessac-high": { + "name": "lessac", + "language": "en_US", + "quality": "high", + "files": { + "en_US-lessac-high.onnx": { + "size_bytes": 113895201, + "md5_digest": "99d1f6181a7f5ccbe3f117ba8ce63c93" + }, + "en_US-lessac-high.onnx.json": { + "size_bytes": 6859, + "md5_digest": "a943690c845cd7f54bd5a7229951465e" + }, + "MODEL_CARD": { + "size_bytes": 347, + "md5_digest": "2ff564555f6d6cde3c19dcc8f3815428" + } + } + }, + "en_US-lessac-medium": { + "name": "lessac", + "language": "en_US", + "quality": "medium", + "files": { + "en_US-lessac-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "2fc642b535197b6305c7c8f92dc8b24f" + }, + "en_US-lessac-medium.onnx.json": { + "size_bytes": 6860, + "md5_digest": "10428ba058a4238eb455219d4a50f17b" + }, + "MODEL_CARD": { + "size_bytes": 351, + "md5_digest": "42f2dd4a98149e12fc70b301d9579dfd" + } + } + }, + "en_US-joe-medium": { + "name": "joe", + "language": "en_US", + "quality": "medium", + "files": { + "en_US-joe-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "74fd6a4dc39e0aa9dce145d7f5acd4f6" + }, + "en_US-joe-medium.onnx.json": { + "size_bytes": 6729, + "md5_digest": "10eebc49ebf86c1a7749cd5f9392e2a3" + }, + "MODEL_CARD": { + "size_bytes": 280, + "md5_digest": "7d25cb111aa9699518764a1cb3943af1" + } + } + }, + "es_MX-ald-medium": { + "name": "ald", + "language": "es_MX", + "quality": "medium", + "files": { + "es_MX-ald-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "86374058e59b41ac3b7fe4181e1daad6" + }, + "es_MX-ald-medium.onnx.json": { + "size_bytes": 6872, + "md5_digest": "c17db4ddbef38305701e4047a3adbcf3" + }, + "MODEL_CARD": { + "size_bytes": 320, + "md5_digest": "a858af3698e0c7cda6c9ad5d0d11b651" + } + } + }, + "es_ES-mls_9772-low": { + "name": "mls_9772", + "language": "es_ES", + "quality": "low", + "files": { + "es_ES-mls_9972-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "587f2fc38dc3f582e771c3748465e2a2" + }, + "es_ES-mls_9972-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "a3750f9fff6ae97bc60de668c8107e5f" + }, + "MODEL_CARD": { + "size_bytes": 256, + "md5_digest": "4ba8c18ce72a202a49312ee1914ca6b0" + } + } + }, + "es_ES-davefx-medium": { + "name": "davefx", + "language": "es_ES", + "quality": "medium", + "files": { + "es_ES-davefx-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "dc515cd4ecc5f6f72fe14a941188fc9c" + }, + "es_ES-davefx-medium.onnx.json": { + "size_bytes": 6770, + "md5_digest": "d493f20191c47c69309c3b806cb1302b" + }, + "MODEL_CARD": { + "size_bytes": 275, + "md5_digest": "5569c0fb20448308466216428b52f392" + } + } + }, + "es_ES-sharvard-medium": { + "name": "sharvard", + "language": "es_ES", + "quality": "medium", + "files": { + "es_ES-sharvard-medium.onnx": { + "size_bytes": 76733615, + "md5_digest": "77e6f9c26e92799fb04bb90b46bf1834" + }, + "es_ES-sharvard-medium.onnx.json": { + "size_bytes": 6892, + "md5_digest": "398b0cc43670182e138d7e3e881c6a4e" + }, + "MODEL_CARD": { + "size_bytes": 392, + "md5_digest": "b600a21381af84fa21b29f519a3a829a" + } + } + }, + "es_ES-carlfm-x_low": { + "name": "carlfm", + "language": "es_ES", + "quality": "x_low", + "files": { + "es_ES-carlfm-x-low.onnx": { + "size_bytes": 28130791, + "md5_digest": "4137b5aee01ea6241080fc4dbe59a8ee" + }, + "es_ES-carlfm-x-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "a3750f9fff6ae97bc60de668c8107e5f" + }, + "MODEL_CARD": { + "size_bytes": 250, + "md5_digest": "19cb47bbe9e07e8d7937cfd39027d3a9" + } + } + }, + "es_ES-mls_10246-low": { + "name": "mls_10246", + "language": "es_ES", + "quality": "low", + "files": { + "es_ES-mls_10246-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "ab8e93c9d2714fd4481fbca4e2a38891" + }, + "es_ES-mls_10246-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "a3750f9fff6ae97bc60de668c8107e5f" + }, + "MODEL_CARD": { + "size_bytes": 257, + "md5_digest": "a345cefedda92347f53ea9a84d1b3983" + } + } + }, + "uk_UK-lada-x_low": { + "name": "lada", + "language": "uk_UK", + "quality": "x_low", + "files": { + "uk_UK-lada-x_low.onnx": { + "size_bytes": 20628813, + "md5_digest": "b84110e3923d64cdd4e0056a22090557" + }, + "uk_UK-lada-x_low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "0dc53021ef5b2086b9072b1f5ad90b18" + }, + "MODEL_CARD": { + "size_bytes": 267, + "md5_digest": "edf5a72d6b117b37f9a6ef1d56e77640" + } + } + }, + "uk_UK-ukrainian_tts-medium": { + "name": "ukrainian_tts", + "language": "uk_UK", + "quality": "medium", + "files": { + "uk_UK-ukrainian_tts-medium.onnx": { + "size_bytes": 76735663, + "md5_digest": "3366c3d4f31cb77966fb14d042956b4f" + }, + "uk_UK-ukrainian_tts-medium.onnx.json": { + "size_bytes": 2491, + "md5_digest": "b21ad4df81478d1bdb0c50ab95442884" + }, + "MODEL_CARD": { + "size_bytes": 266, + "md5_digest": "5d87c44f816de40700558256659fd13b" + } + } + }, + "sw_CD-lanfrica-medium": { + "name": "lanfrica", + "language": "sw_CD", + "quality": "medium", + "files": { + "sw_CD-lanfrica-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "7b28078f0e76cb201dc8b512ea4bf4d6" + }, + "sw_CD-lanfrica-medium.onnx.json": { + "size_bytes": 6856, + "md5_digest": "0d142b4edb3cd419b4fcac5dcf446268" + }, + "MODEL_CARD": { + "size_bytes": 315, + "md5_digest": "225cc22fc4a35a83f2039988499baa85" + } + } + }, + "fr_FR-siwis-low": { + "name": "siwis", + "language": "fr_FR", + "quality": "low", + "files": { + "fr_FR-siwis-low.onnx": { + "size_bytes": 28130791, + "md5_digest": "fcb614122005d70f27e4e61e58b4bb56" + }, + "fr_FR-siwis-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "c800dbf8a43eb67a1ec4d5438893c11c" + }, + "MODEL_CARD": { + "size_bytes": 274, + "md5_digest": "5d4a6b6e8d4a476e9b415ec0c1f030da" + } + } + }, + "fr_FR-siwis-medium": { + "name": "siwis", + "language": "fr_FR", + "quality": "medium", + "files": { + "fr_FR-siwis-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "20e876e8c839e9b11a26085858f2300c" + }, + "fr_FR-siwis-medium.onnx.json": { + "size_bytes": 6856, + "md5_digest": "ea90f292c155c1b6def5564061409ad0" + }, + "MODEL_CARD": { + "size_bytes": 284, + "md5_digest": "2b9ea48b15e9e1fd25f95b415caaf66f" + } + } + }, + "fr_FR-mls_1840-low": { + "name": "mls_1840", + "language": "fr_FR", + "quality": "low", + "files": { + "fr_FR-mls_1840-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "1873b5d95cb0aad9909d32d1747ae72b" + }, + "fr_FR-mls_1840-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "c800dbf8a43eb67a1ec4d5438893c11c" + }, + "MODEL_CARD": { + "size_bytes": 257, + "md5_digest": "35d860ab0a8497966c73da525728e711" + } + } + }, + "fr_FR-gilles-low": { + "name": "gilles", + "language": "fr_FR", + "quality": "low", + "files": { + "fr_FR-gilles-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "f984386d1f0927597f09a3ec10b11b5d" + }, + "fr_FR-gilles-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "c800dbf8a43eb67a1ec4d5438893c11c" + }, + "MODEL_CARD": { + "size_bytes": 300, + "md5_digest": "9317af9efdb0d9986d42357b180f06e2" + } + } + }, + "fi_FI-harri-low": { + "name": "harri", + "language": "fi_FI", + "quality": "low", + "files": { + "fi_FI-harri-low.onnx": { + "size_bytes": 69795191, + "md5_digest": "f44b67203de7fd488eabc4692d30b598" + }, + "fi_FI-harri-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "eba0de0dea4f2adb0cb5c4bcc3f636bc" + }, + "MODEL_CARD": { + "size_bytes": 284, + "md5_digest": "93ccf398abae82b7d7a3d420658e26f1" + } + } + }, + "fi_FI-harri-medium": { + "name": "harri", + "language": "fi_FI", + "quality": "medium", + "files": { + "fi_FI-harri-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "8e96b9e765f8db3e910943520aa0f475" + }, + "fi_FI-harri-medium.onnx.json": { + "size_bytes": 6856, + "md5_digest": "cdadec39c6a43b1f413a2866351d61be" + }, + "MODEL_CARD": { + "size_bytes": 304, + "md5_digest": "95d5aff86d27b69c8ee7deed6c056aff" + } + } + }, + "ka_GE-natia-medium": { + "name": "natia", + "language": "ka_GE", + "quality": "medium", + "files": { + "ka_GE-natia-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "83bd40f8d176a83d3d8d605fada2a5e7" + }, + "ka_GE-natia-medium.onnx.json": { + "size_bytes": 6770, + "md5_digest": "1a5e7dbbe5beb3a3776822fc9b3e01cb" + }, + "MODEL_CARD": { + "size_bytes": 288, + "md5_digest": "81ac71dd5b3dac89bf7762bf7b738c95" + } + } + }, + "pl_PL-darkman-medium": { + "name": "darkman", + "language": "pl_PL", + "quality": "medium", + "files": { + "pl_PL-darkman-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "27bf2d71e934b112657544fd0b100a7a" + }, + "pl_PL-darkman-medium.onnx.json": { + "size_bytes": 6770, + "md5_digest": "bc06cd7feea1c1f194f71b778443b233" + }, + "MODEL_CARD": { + "size_bytes": 276, + "md5_digest": "952772905864f6f6375df54a675895b7" + } + } + }, + "pl_PL-mls_6892-low": { + "name": "mls_6892", + "language": "pl_PL", + "quality": "low", + "files": { + "pl_PL-mls_6892-low.onnx": { + "size_bytes": 63104526, + "md5_digest": "8590d8e979292ca35d20e6e123bfa612" + }, + "pl_PL-mls_6892-low.onnx.json": { + "size_bytes": 5773, + "md5_digest": "ea661adb29682d6900dbfbd76e3f71bd" + }, + "MODEL_CARD": { + "size_bytes": 257, + "md5_digest": "74ebc618d120896113449ad2f957b7a4" + } + } + }, + "pl_PL-gosia-medium": { + "name": "gosia", + "language": "pl_PL", + "quality": "medium", + "files": { + "pl_PL-gosia-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "ecf817530e575025166e454adde1f382" + }, + "pl_PL-gosia-medium.onnx.json": { + "size_bytes": 6770, + "md5_digest": "bc06cd7feea1c1f194f71b778443b233" + }, + "MODEL_CARD": { + "size_bytes": 274, + "md5_digest": "e1355330fe5fab166e6f2e20af7e91e9" + } + } + }, + "no_NO-talesyntese-medium": { + "name": "talesyntese", + "language": "no_NO", + "quality": "medium", + "files": { + "no_NO-talesyntese-medium.onnx": { + "size_bytes": 63201294, + "md5_digest": "9fc876e7edc6593086b4f2f34889f44b" + }, + "no_NO-talesyntese-medium.onnx.json": { + "size_bytes": 6856, + "md5_digest": "0aaf1141170a1dc26d07adf6e643c60e" + }, + "MODEL_CARD": { + "size_bytes": 312, + "md5_digest": "5fe51d2a4a0e05e85c88a80373000ae1" + } + } + } +} \ No newline at end of file diff --git a/zh/zh_CN/huayan/medium/MODEL_CARD b/zh/zh_CN/huayan/medium/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..02b4fba5ae8353637e93af3443ddddacf14c663e --- /dev/null +++ b/zh/zh_CN/huayan/medium/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for huayan (medium) + +* Language: zh_CN (Chinese, China) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://github.com/PlayVoice/HuaYan_TTS +* License: Unknown + +## Training + +Finetuned from U.S. English lessac voice (medium quality). diff --git a/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx b/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx new file mode 100644 index 0000000000000000000000000000000000000000..6bf247ed7ba3cbc066b8a3f13f6392aed956bf74 --- /dev/null +++ b/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9929917bf8cabb26fd528ea44d3a6699c11e87317a14765312420be230be0f3d +size 63201294 diff --git a/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx.json b/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..5b56156a2a1ec3ee81ebc51e3ea8dcbd064b3d29 --- /dev/null +++ b/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx.json @@ -0,0 +1,477 @@ +{ + "audio": { + "sample_rate": 22050 + }, + "espeak": { + "voice": "cmn" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_type": "espeak", + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ], + "0": [ + 130 + ], + "1": [ + 131 + ], + "2": [ + 132 + ], + "3": [ + 133 + ], + "4": [ + 134 + ], + "5": [ + 135 + ], + "6": [ + 136 + ], + "7": [ + 137 + ], + "8": [ + 138 + ], + "9": [ + 139 + ], + "̧": [ + 140 + ], + "̃": [ + 141 + ], + "̪": [ + 142 + ], + "̯": [ + 143 + ], + "̩": [ + 144 + ], + "ʰ": [ + 145 + ], + "ˤ": [ + 146 + ], + "ε": [ + 147 + ], + "↓": [ + 148 + ], + "#": [ + 149 + ], + "\"": [ + 150 + ], + "↑": [ + 151 + ] + }, + "num_symbols": 256, + "num_speakers": 1, + "speaker_id_map": {}, + "piper_version": "1.0.0" +} \ No newline at end of file diff --git a/zh/zh_CN/huayan/x_low/MODEL_CARD b/zh/zh_CN/huayan/x_low/MODEL_CARD new file mode 100644 index 0000000000000000000000000000000000000000..00e271f38c3ea87822aed8298fa3a16fb1dacef4 --- /dev/null +++ b/zh/zh_CN/huayan/x_low/MODEL_CARD @@ -0,0 +1,15 @@ +# Model card for huayan (x_low) + +* Language: zh_CN (Chinese, China) +* Speakers: 1 +* Quality: x_low +* Samplerate: 16,000Hz + +## Dataset + +* URL: https://github.com/PlayVoice/HuaYan_TTS +* License: Unknown + +## Training + +Trained from scratch. diff --git a/zh/zh_CN/huayan/x_low/zh_CN-huayan-x_low.onnx b/zh/zh_CN/huayan/x_low/zh_CN-huayan-x_low.onnx new file mode 100644 index 0000000000000000000000000000000000000000..dec8441e6ae48ba3eacf311daf72a456a184696a --- /dev/null +++ b/zh/zh_CN/huayan/x_low/zh_CN-huayan-x_low.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d30b143fac66d821a1285aa013295adf5cd129d3cc11d70334e51c7b20662c37 +size 20628813 diff --git a/zh/zh_CN/huayan/x_low/zh_CN-huayan-x_low.onnx.json b/zh/zh_CN/huayan/x_low/zh_CN-huayan-x_low.onnx.json new file mode 100644 index 0000000000000000000000000000000000000000..a7988b921421305d7cf74ffbfca236483bdf9bed --- /dev/null +++ b/zh/zh_CN/huayan/x_low/zh_CN-huayan-x_low.onnx.json @@ -0,0 +1,409 @@ +{ + "audio": { + "sample_rate": 16000 + }, + "espeak": { + "voice": "cmn" + }, + "inference": { + "noise_scale": 0.667, + "length_scale": 1, + "noise_w": 0.8 + }, + "phoneme_map": {}, + "phoneme_id_map": { + "_": [ + 0 + ], + "^": [ + 1 + ], + "$": [ + 2 + ], + " ": [ + 3 + ], + "!": [ + 4 + ], + "'": [ + 5 + ], + "(": [ + 6 + ], + ")": [ + 7 + ], + ",": [ + 8 + ], + "-": [ + 9 + ], + ".": [ + 10 + ], + ":": [ + 11 + ], + ";": [ + 12 + ], + "?": [ + 13 + ], + "a": [ + 14 + ], + "b": [ + 15 + ], + "c": [ + 16 + ], + "d": [ + 17 + ], + "e": [ + 18 + ], + "f": [ + 19 + ], + "h": [ + 20 + ], + "i": [ + 21 + ], + "j": [ + 22 + ], + "k": [ + 23 + ], + "l": [ + 24 + ], + "m": [ + 25 + ], + "n": [ + 26 + ], + "o": [ + 27 + ], + "p": [ + 28 + ], + "q": [ + 29 + ], + "r": [ + 30 + ], + "s": [ + 31 + ], + "t": [ + 32 + ], + "u": [ + 33 + ], + "v": [ + 34 + ], + "w": [ + 35 + ], + "x": [ + 36 + ], + "y": [ + 37 + ], + "z": [ + 38 + ], + "æ": [ + 39 + ], + "ç": [ + 40 + ], + "ð": [ + 41 + ], + "ø": [ + 42 + ], + "ħ": [ + 43 + ], + "ŋ": [ + 44 + ], + "œ": [ + 45 + ], + "ǀ": [ + 46 + ], + "ǁ": [ + 47 + ], + "ǂ": [ + 48 + ], + "ǃ": [ + 49 + ], + "ɐ": [ + 50 + ], + "ɑ": [ + 51 + ], + "ɒ": [ + 52 + ], + "ɓ": [ + 53 + ], + "ɔ": [ + 54 + ], + "ɕ": [ + 55 + ], + "ɖ": [ + 56 + ], + "ɗ": [ + 57 + ], + "ɘ": [ + 58 + ], + "ə": [ + 59 + ], + "ɚ": [ + 60 + ], + "ɛ": [ + 61 + ], + "ɜ": [ + 62 + ], + "ɞ": [ + 63 + ], + "ɟ": [ + 64 + ], + "ɠ": [ + 65 + ], + "ɡ": [ + 66 + ], + "ɢ": [ + 67 + ], + "ɣ": [ + 68 + ], + "ɤ": [ + 69 + ], + "ɥ": [ + 70 + ], + "ɦ": [ + 71 + ], + "ɧ": [ + 72 + ], + "ɨ": [ + 73 + ], + "ɪ": [ + 74 + ], + "ɫ": [ + 75 + ], + "ɬ": [ + 76 + ], + "ɭ": [ + 77 + ], + "ɮ": [ + 78 + ], + "ɯ": [ + 79 + ], + "ɰ": [ + 80 + ], + "ɱ": [ + 81 + ], + "ɲ": [ + 82 + ], + "ɳ": [ + 83 + ], + "ɴ": [ + 84 + ], + "ɵ": [ + 85 + ], + "ɶ": [ + 86 + ], + "ɸ": [ + 87 + ], + "ɹ": [ + 88 + ], + "ɺ": [ + 89 + ], + "ɻ": [ + 90 + ], + "ɽ": [ + 91 + ], + "ɾ": [ + 92 + ], + "ʀ": [ + 93 + ], + "ʁ": [ + 94 + ], + "ʂ": [ + 95 + ], + "ʃ": [ + 96 + ], + "ʄ": [ + 97 + ], + "ʈ": [ + 98 + ], + "ʉ": [ + 99 + ], + "ʊ": [ + 100 + ], + "ʋ": [ + 101 + ], + "ʌ": [ + 102 + ], + "ʍ": [ + 103 + ], + "ʎ": [ + 104 + ], + "ʏ": [ + 105 + ], + "ʐ": [ + 106 + ], + "ʑ": [ + 107 + ], + "ʒ": [ + 108 + ], + "ʔ": [ + 109 + ], + "ʕ": [ + 110 + ], + "ʘ": [ + 111 + ], + "ʙ": [ + 112 + ], + "ʛ": [ + 113 + ], + "ʜ": [ + 114 + ], + "ʝ": [ + 115 + ], + "ʟ": [ + 116 + ], + "ʡ": [ + 117 + ], + "ʢ": [ + 118 + ], + "ʲ": [ + 119 + ], + "ˈ": [ + 120 + ], + "ˌ": [ + 121 + ], + "ː": [ + 122 + ], + "ˑ": [ + 123 + ], + "˞": [ + 124 + ], + "β": [ + 125 + ], + "θ": [ + 126 + ], + "χ": [ + 127 + ], + "ᵻ": [ + 128 + ], + "ⱱ": [ + 129 + ] + }, + "num_symbols": 130, + "num_speakers": 1, + "speaker_id_map": {} +} \ No newline at end of file