Adding ONNX file of this model

Beep boop I am the [ONNX export bot 🤖🏎️](https://huggingface.co/spaces/onnx/export). On behalf of [Chillarmo](https://huggingface.co/Chillarmo), I would like to add to this repository the model converted to ONNX.

What is ONNX? It stands for "Open Neural Network Exchange", and is the most commonly used open standard for machine learning interoperability. You can find out more at [onnx.ai](https://onnx.ai/)!

The exported ONNX model can be then be consumed by various backends as TensorRT or TVM, or simply be used in a few lines with 🤗 Optimum through ONNX Runtime, check out how [here](https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/models)!

.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
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -9,14 +9,15 @@ tags:
 - Chillarmo/common_voice_20_armenian
 - mms
 - generated_from_trainer
+- onnx
 metrics:
 - wer
-model-index:
-- name: wav2vec2-common_voice_20-hy-mms-finetune
-  results: []
 datasets:
 - Chillarmo/common_voice_20_armenian
 pipeline_tag: automatic-speech-recognition
+model-index:
+- name: wav2vec2-common_voice_20-hy-mms-finetune
+  results: []
 ---
 
 # wav2vec2-common_voice_20-hy-mms-finetune

onnx/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 59,
+  "<s>": 58
+}

onnx/config.json

@@ -0,0 +1,108 @@
+{
+  "_attn_implementation_autoset": true,
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 57,
+  "proj_codevector_dim": 1024,
+  "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": "4.51.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 60,
+  "xvector_output_dim": 512
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d45aa9d1fc08a08f96b6af96ca05f533c49d0d925731ff06818f9cfd0887f8cb
+size 1392416

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522fd94d264c2c1f9ecfb766f6e73e05e46153cb472a712fa13ba839483ddc6c
+size 3858892800

onnx/preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

onnx/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

onnx/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "56": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "59": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "hyw",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

onnx/vocab.json

@@ -0,0 +1,62 @@
+{
+  "hyw": {
+    "(": 1,
+    ")": 2,
+    ":": 3,
+    "[PAD]": 57,
+    "[UNK]": 56,
+    "`": 4,
+    "|": 0,
+    "«": 5,
+    "´": 6,
+    "»": 7,
+    "՚": 8,
+    "՛": 9,
+    "՜": 10,
+    "՝": 11,
+    "՞": 12,
+    "ա": 13,
+    "բ": 14,
+    "գ": 15,
+    "դ": 16,
+    "ե": 17,
+    "զ": 18,
+    "է": 19,
+    "ը": 20,
+    "թ": 21,
+    "ժ": 22,
+    "ի": 23,
+    "լ": 24,
+    "խ": 25,
+    "ծ": 26,
+    "կ": 27,
+    "հ": 28,
+    "ձ": 29,
+    "ղ": 30,
+    "ճ": 31,
+    "մ": 32,
+    "յ": 33,
+    "ն": 34,
+    "շ": 35,
+    "ո": 36,
+    "չ": 37,
+    "պ": 38,
+    "ջ": 39,
+    "ռ": 40,
+    "ս": 41,
+    "վ": 42,
+    "տ": 43,
+    "ր": 44,
+    "ց": 45,
+    "ւ": 46,
+    "փ": 47,
+    "ք": 48,
+    "օ": 49,
+    "ֆ": 50,
+    "և": 51,
+    "։": 52,
+    "֊": 53,
+    "’": 54,
+    "…": 55
+  }
+}