Commit
•
7919309
1
Parent(s):
accb3f5
Training in progress, step 500
Browse files- config.json +110 -110
- model.safetensors +1 -1
- preprocessor_config.json +10 -10
- special_tokens_map.json +6 -6
- tokenizer_config.json +50 -50
- training_args.bin +1 -1
- vocab.json +34 -34
config.json
CHANGED
|
@@ -1,110 +1,110 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "facebook/wav2vec2-base-960h",
|
| 3 |
-
"activation_dropout": 0.1,
|
| 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": 0.1,
|
| 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_dropout": 0.0,
|
| 52 |
-
"feat_extract_norm": "group",
|
| 53 |
-
"feat_proj_dropout": 0.1,
|
| 54 |
-
"feat_quantizer_dropout": 0.0,
|
| 55 |
-
"final_dropout": 0.1,
|
| 56 |
-
"gradient_checkpointing": false,
|
| 57 |
-
"hidden_act": "gelu",
|
| 58 |
-
"hidden_dropout": 0.1,
|
| 59 |
-
"hidden_dropout_prob": 0.1,
|
| 60 |
-
"hidden_size": 768,
|
| 61 |
-
"initializer_range": 0.02,
|
| 62 |
-
"intermediate_size": 3072,
|
| 63 |
-
"layer_norm_eps": 1e-05,
|
| 64 |
-
"layerdrop": 0.1,
|
| 65 |
-
"mask_feature_length": 10,
|
| 66 |
-
"mask_feature_min_masks": 0,
|
| 67 |
-
"mask_feature_prob": 0.0,
|
| 68 |
-
"mask_time_length": 10,
|
| 69 |
-
"mask_time_min_masks": 2,
|
| 70 |
-
"mask_time_prob": 0.05,
|
| 71 |
-
"model_type": "wav2vec2",
|
| 72 |
-
"num_adapter_layers": 3,
|
| 73 |
-
"num_attention_heads": 12,
|
| 74 |
-
"num_codevector_groups": 2,
|
| 75 |
-
"num_codevectors_per_group": 320,
|
| 76 |
-
"num_conv_pos_embedding_groups": 16,
|
| 77 |
-
"num_conv_pos_embeddings": 128,
|
| 78 |
-
"num_feat_extract_layers": 7,
|
| 79 |
-
"num_hidden_layers": 12,
|
| 80 |
-
"num_negatives": 100,
|
| 81 |
-
"output_hidden_size": 768,
|
| 82 |
-
"pad_token_id": 0,
|
| 83 |
-
"proj_codevector_dim": 256,
|
| 84 |
-
"tdnn_dilation": [
|
| 85 |
-
1,
|
| 86 |
-
2,
|
| 87 |
-
3,
|
| 88 |
-
1,
|
| 89 |
-
1
|
| 90 |
-
],
|
| 91 |
-
"tdnn_dim": [
|
| 92 |
-
512,
|
| 93 |
-
512,
|
| 94 |
-
512,
|
| 95 |
-
512,
|
| 96 |
-
1500
|
| 97 |
-
],
|
| 98 |
-
"tdnn_kernel": [
|
| 99 |
-
5,
|
| 100 |
-
3,
|
| 101 |
-
3,
|
| 102 |
-
1,
|
| 103 |
-
1
|
| 104 |
-
],
|
| 105 |
-
"torch_dtype": "float32",
|
| 106 |
-
"transformers_version": "4.42.
|
| 107 |
-
"use_weighted_layer_sum": false,
|
| 108 |
-
"vocab_size": 32,
|
| 109 |
-
"xvector_output_dim": 512
|
| 110 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 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": 0.1,
|
| 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_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "group",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.1,
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.1,
|
| 59 |
+
"hidden_dropout_prob": 0.1,
|
| 60 |
+
"hidden_size": 768,
|
| 61 |
+
"initializer_range": 0.02,
|
| 62 |
+
"intermediate_size": 3072,
|
| 63 |
+
"layer_norm_eps": 1e-05,
|
| 64 |
+
"layerdrop": 0.1,
|
| 65 |
+
"mask_feature_length": 10,
|
| 66 |
+
"mask_feature_min_masks": 0,
|
| 67 |
+
"mask_feature_prob": 0.0,
|
| 68 |
+
"mask_time_length": 10,
|
| 69 |
+
"mask_time_min_masks": 2,
|
| 70 |
+
"mask_time_prob": 0.05,
|
| 71 |
+
"model_type": "wav2vec2",
|
| 72 |
+
"num_adapter_layers": 3,
|
| 73 |
+
"num_attention_heads": 12,
|
| 74 |
+
"num_codevector_groups": 2,
|
| 75 |
+
"num_codevectors_per_group": 320,
|
| 76 |
+
"num_conv_pos_embedding_groups": 16,
|
| 77 |
+
"num_conv_pos_embeddings": 128,
|
| 78 |
+
"num_feat_extract_layers": 7,
|
| 79 |
+
"num_hidden_layers": 12,
|
| 80 |
+
"num_negatives": 100,
|
| 81 |
+
"output_hidden_size": 768,
|
| 82 |
+
"pad_token_id": 0,
|
| 83 |
+
"proj_codevector_dim": 256,
|
| 84 |
+
"tdnn_dilation": [
|
| 85 |
+
1,
|
| 86 |
+
2,
|
| 87 |
+
3,
|
| 88 |
+
1,
|
| 89 |
+
1
|
| 90 |
+
],
|
| 91 |
+
"tdnn_dim": [
|
| 92 |
+
512,
|
| 93 |
+
512,
|
| 94 |
+
512,
|
| 95 |
+
512,
|
| 96 |
+
1500
|
| 97 |
+
],
|
| 98 |
+
"tdnn_kernel": [
|
| 99 |
+
5,
|
| 100 |
+
3,
|
| 101 |
+
3,
|
| 102 |
+
1,
|
| 103 |
+
1
|
| 104 |
+
],
|
| 105 |
+
"torch_dtype": "float32",
|
| 106 |
+
"transformers_version": "4.42.3",
|
| 107 |
+
"use_weighted_layer_sum": false,
|
| 108 |
+
"vocab_size": 32,
|
| 109 |
+
"xvector_output_dim": 512
|
| 110 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377611120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d72f7d537d2b1720d026957dd67703a65fe53dacb564e6bbe24b6a4054a0068b
|
| 3 |
size 377611120
|
preprocessor_config.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_normalize": true,
|
| 3 |
-
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
-
"feature_size": 1,
|
| 5 |
-
"padding_side": "right",
|
| 6 |
-
"padding_value": 0.0,
|
| 7 |
-
"processor_class": "Wav2Vec2Processor",
|
| 8 |
-
"return_attention_mask": false,
|
| 9 |
-
"sampling_rate": 16000
|
| 10 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": false,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
-
"eos_token": "</s>",
|
| 4 |
-
"pad_token": "<pad>",
|
| 5 |
-
"unk_token": "<unk>"
|
| 6 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -1,50 +1,50 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "<pad>",
|
| 5 |
-
"lstrip": true,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": true,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": false
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "<s>",
|
| 13 |
-
"lstrip": true,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": true,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": false
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "</s>",
|
| 21 |
-
"lstrip": true,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": true,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": false
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "<unk>",
|
| 29 |
-
"lstrip": true,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": true,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": false
|
| 34 |
-
}
|
| 35 |
-
},
|
| 36 |
-
"bos_token": "<s>",
|
| 37 |
-
"clean_up_tokenization_spaces": true,
|
| 38 |
-
"do_lower_case": false,
|
| 39 |
-
"do_normalize": true,
|
| 40 |
-
"eos_token": "</s>",
|
| 41 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
-
"pad_token": "<pad>",
|
| 43 |
-
"processor_class": "Wav2Vec2Processor",
|
| 44 |
-
"replace_word_delimiter_char": " ",
|
| 45 |
-
"return_attention_mask": false,
|
| 46 |
-
"target_lang": null,
|
| 47 |
-
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 48 |
-
"unk_token": "<unk>",
|
| 49 |
-
"word_delimiter_token": "|"
|
| 50 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": true,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": true,
|
| 38 |
+
"do_lower_case": false,
|
| 39 |
+
"do_normalize": true,
|
| 40 |
+
"eos_token": "</s>",
|
| 41 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
+
"pad_token": "<pad>",
|
| 43 |
+
"processor_class": "Wav2Vec2Processor",
|
| 44 |
+
"replace_word_delimiter_char": " ",
|
| 45 |
+
"return_attention_mask": false,
|
| 46 |
+
"target_lang": null,
|
| 47 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 48 |
+
"unk_token": "<unk>",
|
| 49 |
+
"word_delimiter_token": "|"
|
| 50 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d369f52336d929e645e2986fafb2cf70a22bf2f9d98f03ac2850f7e605106d4
|
| 3 |
size 5112
|
vocab.json
CHANGED
|
@@ -1,34 +1,34 @@
|
|
| 1 |
-
{
|
| 2 |
-
"'": 27,
|
| 3 |
-
"</s>": 2,
|
| 4 |
-
"<pad>": 0,
|
| 5 |
-
"<s>": 1,
|
| 6 |
-
"<unk>": 3,
|
| 7 |
-
"A": 7,
|
| 8 |
-
"B": 24,
|
| 9 |
-
"C": 19,
|
| 10 |
-
"D": 14,
|
| 11 |
-
"E": 5,
|
| 12 |
-
"F": 20,
|
| 13 |
-
"G": 21,
|
| 14 |
-
"H": 11,
|
| 15 |
-
"I": 10,
|
| 16 |
-
"J": 29,
|
| 17 |
-
"K": 26,
|
| 18 |
-
"L": 15,
|
| 19 |
-
"M": 17,
|
| 20 |
-
"N": 9,
|
| 21 |
-
"O": 8,
|
| 22 |
-
"P": 23,
|
| 23 |
-
"Q": 30,
|
| 24 |
-
"R": 13,
|
| 25 |
-
"S": 12,
|
| 26 |
-
"T": 6,
|
| 27 |
-
"U": 16,
|
| 28 |
-
"V": 25,
|
| 29 |
-
"W": 18,
|
| 30 |
-
"X": 28,
|
| 31 |
-
"Y": 22,
|
| 32 |
-
"Z": 31,
|
| 33 |
-
"|": 4
|
| 34 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"'": 27,
|
| 3 |
+
"</s>": 2,
|
| 4 |
+
"<pad>": 0,
|
| 5 |
+
"<s>": 1,
|
| 6 |
+
"<unk>": 3,
|
| 7 |
+
"A": 7,
|
| 8 |
+
"B": 24,
|
| 9 |
+
"C": 19,
|
| 10 |
+
"D": 14,
|
| 11 |
+
"E": 5,
|
| 12 |
+
"F": 20,
|
| 13 |
+
"G": 21,
|
| 14 |
+
"H": 11,
|
| 15 |
+
"I": 10,
|
| 16 |
+
"J": 29,
|
| 17 |
+
"K": 26,
|
| 18 |
+
"L": 15,
|
| 19 |
+
"M": 17,
|
| 20 |
+
"N": 9,
|
| 21 |
+
"O": 8,
|
| 22 |
+
"P": 23,
|
| 23 |
+
"Q": 30,
|
| 24 |
+
"R": 13,
|
| 25 |
+
"S": 12,
|
| 26 |
+
"T": 6,
|
| 27 |
+
"U": 16,
|
| 28 |
+
"V": 25,
|
| 29 |
+
"W": 18,
|
| 30 |
+
"X": 28,
|
| 31 |
+
"Y": 22,
|
| 32 |
+
"Z": 31,
|
| 33 |
+
"|": 4
|
| 34 |
+
}
|