Training in progress, step 1500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 115, "</s>": 116}

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.75,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 114,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 117,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8c7b116c5a51587a67bd2a44fc275e971a2822f2741e33cd29adc341bc845d
+size 1262403377

runs/Feb05_12-42-00_job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5/1644064956.4596171/events.out.tfevents.1644064956.job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5.15290.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4832b14e0dd21365d9ae855d53e492fb59de75394995ad967aefd48f47dd48
+size 4835

runs/Feb05_12-42-00_job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5/events.out.tfevents.1644064956.job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5.15290.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e13e3961b084db5223d016d1f2c02117dd74cd68b4bb664447e140a2cf66a4
+size 4991

runs/Feb05_12-45-15_job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5/1644065145.9674463/events.out.tfevents.1644065145.job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5.16686.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d822dd36aa14065668d9a7b194ceb3a7dde22664f20c9d6f74b7f87e5d0ea9cf
+size 4835

runs/Feb05_12-45-15_job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5/events.out.tfevents.1644065145.job-0167f55d-c17f-480c-9f0c-e77ccfce0ee5.16686.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553f9ed1b1788e4e16a0e3b733b27e0cb3f4b892586797909caae2b5998fb694
+size 5513

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "../data/common_voice_large/", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b5d7841a24f989c9a7bfcb8e67c7262c0a97d15b3ca0d9e21c4c1bb7d37c27
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"お": 0, "ぃ": 1, "も": 2, "で": 3, "え": 4, "ま": 5, "ん": 6, "ぜ": 7, "ぱ": 8, "あ": 9, "ね": 10, "り": 11, "&": 13, "q": 14, "の": 15, "ぎ": 16, "み": 17, "な": 18, "i": 19, "ぶ": 20, "ふ": 21, "ひ": 22, "ぢ": 23, "だ": 24, "ぁ": 25, "へ": 26, "s": 27, "べ": 28, "d": 29, "ら": 30, "ゆ": 31, "た": 32, "a": 33, "ぞ": 34, "ぅ": 35, "ほ": 36, "い": 37, "さ": 38, "ゔ": 39, "け": 40, "か": 41, "く": 42, "す": 43, "l": 44, "わ": 45, "づ": 46, "せ": 47, "々": 48, "g": 49, "ろ": 50, "と": 51, "そ": 52, "む": 53, "ー": 54, "ぬ": 55, "j": 56, "u": 57, "ざ": 58, "ち": 59, "じ": 60, "や": 61, "ぐ": 62, "ゖ": 63, "w": 64, "ぴ": 65, "e": 66, "ご": 67, "ど": 68, "b": 69, "て": 70, "o": 71, "y": 72, "げ": 73, "c": 74, "を": 75, "繫": 76, "は": 77, "び": 78, "ゅ": 79, "る": 80, "っ": 81, "う": 82, "ぽ": 83, "れ": 84, "h": 85, "に": 86, "ず": 87, "ぷ": 88, "ぼ": 89, "め": 90, "し": 91, "m": 92, "r": 93, "n": 94, "よ": 95, "こ": 96, "p": 97, "x": 98, "ぇ": 99, "k": 100, "ゃ": 101, "ぉ": 102, "ぺ": 103, "f": 104, "z": 105, "つ": 106, "が": 107, "き": 108, "t": 109, "ょ": 110, "v": 111, "ば": 112, "|": 12, "[UNK]": 113, "[PAD]": 114}