Adding ONNX file of this model
Browse filesBeep boop I am the [ONNX export bot 🤖🏎️](https://huggingface.co/spaces/onnx/export). On behalf of [edbrdi](https://huggingface.co/edbrdi), 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)!
- onnx/added_tokens.json +4 -0
- onnx/config.json +117 -0
- onnx/model.onnx +3 -0
- onnx/preprocessor_config.json +9 -0
- onnx/special_tokens_map.json +28 -0
- onnx/tokenizer_config.json +172 -0
- onnx/vocab.json +45 -0
onnx/added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 44,
|
| 3 |
+
"<s>": 43
|
| 4 |
+
}
|
onnx/config.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ct-vikramanantha/phoneme-scorer-v2-wav2vec2",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForCTC"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 256,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": false,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "mean",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": false,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_norm": "group",
|
| 52 |
+
"feat_proj_dropout": 0.0,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"freeze_feat_extract_train": true,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.0,
|
| 58 |
+
"hidden_size": 768,
|
| 59 |
+
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 3072,
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.0,
|
| 63 |
+
"mask_channel_length": 10,
|
| 64 |
+
"mask_channel_min_space": 1,
|
| 65 |
+
"mask_channel_other": 0.0,
|
| 66 |
+
"mask_channel_prob": 0.0,
|
| 67 |
+
"mask_channel_selection": "static",
|
| 68 |
+
"mask_feature_length": 10,
|
| 69 |
+
"mask_feature_min_masks": 0,
|
| 70 |
+
"mask_feature_prob": 0.0,
|
| 71 |
+
"mask_time_length": 10,
|
| 72 |
+
"mask_time_min_masks": 2,
|
| 73 |
+
"mask_time_min_space": 1,
|
| 74 |
+
"mask_time_other": 0.0,
|
| 75 |
+
"mask_time_prob": 0.05,
|
| 76 |
+
"mask_time_selection": "static",
|
| 77 |
+
"model_type": "wav2vec2",
|
| 78 |
+
"no_mask_channel_overlap": false,
|
| 79 |
+
"no_mask_time_overlap": false,
|
| 80 |
+
"num_adapter_layers": 3,
|
| 81 |
+
"num_attention_heads": 12,
|
| 82 |
+
"num_codevector_groups": 2,
|
| 83 |
+
"num_codevectors_per_group": 320,
|
| 84 |
+
"num_conv_pos_embedding_groups": 16,
|
| 85 |
+
"num_conv_pos_embeddings": 128,
|
| 86 |
+
"num_feat_extract_layers": 7,
|
| 87 |
+
"num_hidden_layers": 12,
|
| 88 |
+
"num_negatives": 100,
|
| 89 |
+
"output_hidden_size": 768,
|
| 90 |
+
"pad_token_id": 42,
|
| 91 |
+
"proj_codevector_dim": 256,
|
| 92 |
+
"tdnn_dilation": [
|
| 93 |
+
1,
|
| 94 |
+
2,
|
| 95 |
+
3,
|
| 96 |
+
1,
|
| 97 |
+
1
|
| 98 |
+
],
|
| 99 |
+
"tdnn_dim": [
|
| 100 |
+
512,
|
| 101 |
+
512,
|
| 102 |
+
512,
|
| 103 |
+
512,
|
| 104 |
+
1500
|
| 105 |
+
],
|
| 106 |
+
"tdnn_kernel": [
|
| 107 |
+
5,
|
| 108 |
+
3,
|
| 109 |
+
3,
|
| 110 |
+
1,
|
| 111 |
+
1
|
| 112 |
+
],
|
| 113 |
+
"transformers_version": "4.37.2",
|
| 114 |
+
"use_weighted_layer_sum": false,
|
| 115 |
+
"vocab_size": 45,
|
| 116 |
+
"xvector_output_dim": 512
|
| 117 |
+
}
|
onnx/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f52e475268fd6b4a91bf255c062d28b86134da50ab3605c6b3c8204a85c6748
|
| 3 |
+
size 377927582
|
onnx/preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
onnx/special_tokens_map.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "</s>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"bos_token": "<s>",
|
| 19 |
+
"eos_token": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"pad_token": "[PAD]",
|
| 27 |
+
"unk_token": "[UNK]"
|
| 28 |
+
}
|
onnx/tokenizer_config.json
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"2": {
|
| 4 |
+
"content": "ow",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"6": {
|
| 12 |
+
"content": "ay",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"9": {
|
| 20 |
+
"content": "ee",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"15": {
|
| 28 |
+
"content": "oh",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": true,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"19": {
|
| 36 |
+
"content": "ch",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": true,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"20": {
|
| 44 |
+
"content": "oo",
|
| 45 |
+
"lstrip": true,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": true,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"25": {
|
| 52 |
+
"content": "bth",
|
| 53 |
+
"lstrip": true,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": true,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"26": {
|
| 60 |
+
"content": "ng",
|
| 61 |
+
"lstrip": true,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": true,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"28": {
|
| 68 |
+
"content": "oau",
|
| 69 |
+
"lstrip": true,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": true,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"29": {
|
| 76 |
+
"content": "oi",
|
| 77 |
+
"lstrip": true,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": true,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"30": {
|
| 84 |
+
"content": "aw",
|
| 85 |
+
"lstrip": true,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": true,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"31": {
|
| 92 |
+
"content": "or",
|
| 93 |
+
"lstrip": true,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": true,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"36": {
|
| 100 |
+
"content": "sh",
|
| 101 |
+
"lstrip": true,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": true,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"37": {
|
| 108 |
+
"content": "uoh",
|
| 109 |
+
"lstrip": true,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": true,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"40": {
|
| 116 |
+
"content": "th",
|
| 117 |
+
"lstrip": true,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": true,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"41": {
|
| 124 |
+
"content": "[UNK]",
|
| 125 |
+
"lstrip": true,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": true,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"42": {
|
| 132 |
+
"content": "[PAD]",
|
| 133 |
+
"lstrip": true,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": true,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"43": {
|
| 140 |
+
"content": "<s>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"44": {
|
| 148 |
+
"content": "</s>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"additional_special_tokens": [
|
| 157 |
+
"<s>",
|
| 158 |
+
"</s>"
|
| 159 |
+
],
|
| 160 |
+
"bos_token": "<s>",
|
| 161 |
+
"clean_up_tokenization_spaces": true,
|
| 162 |
+
"do_lower_case": false,
|
| 163 |
+
"eos_token": "<s>",
|
| 164 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 165 |
+
"pad_token": "[PAD]",
|
| 166 |
+
"processor_class": "Wav2Vec2Processor",
|
| 167 |
+
"replace_word_delimiter_char": " ",
|
| 168 |
+
"target_lang": null,
|
| 169 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 170 |
+
"unk_token": "[UNK]",
|
| 171 |
+
"word_delimiter_token": "|"
|
| 172 |
+
}
|
onnx/vocab.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"E": 39,
|
| 3 |
+
"I": 1,
|
| 4 |
+
"[PAD]": 42,
|
| 5 |
+
"[UNK]": 41,
|
| 6 |
+
"a": 24,
|
| 7 |
+
"aw": 30,
|
| 8 |
+
"ay": 6,
|
| 9 |
+
"b": 3,
|
| 10 |
+
"bth": 25,
|
| 11 |
+
"ch": 19,
|
| 12 |
+
"d": 4,
|
| 13 |
+
"e": 32,
|
| 14 |
+
"ee": 9,
|
| 15 |
+
"f": 7,
|
| 16 |
+
"g": 33,
|
| 17 |
+
"h": 8,
|
| 18 |
+
"i": 34,
|
| 19 |
+
"j": 5,
|
| 20 |
+
"k": 11,
|
| 21 |
+
"l": 12,
|
| 22 |
+
"m": 13,
|
| 23 |
+
"n": 14,
|
| 24 |
+
"ng": 26,
|
| 25 |
+
"o": 27,
|
| 26 |
+
"oau": 28,
|
| 27 |
+
"oh": 15,
|
| 28 |
+
"oi": 29,
|
| 29 |
+
"oo": 20,
|
| 30 |
+
"or": 31,
|
| 31 |
+
"ow": 2,
|
| 32 |
+
"p": 16,
|
| 33 |
+
"r": 35,
|
| 34 |
+
"s": 17,
|
| 35 |
+
"sh": 36,
|
| 36 |
+
"t": 18,
|
| 37 |
+
"th": 40,
|
| 38 |
+
"u": 38,
|
| 39 |
+
"uoh": 37,
|
| 40 |
+
"v": 21,
|
| 41 |
+
"w": 22,
|
| 42 |
+
"y": 10,
|
| 43 |
+
"z": 23,
|
| 44 |
+
"|": 0
|
| 45 |
+
}
|