Hugging Face's logo

eleferrand
/
XLSR_gwad

PyTorch
wav2vec2
Model card Files
xet
Community
1
eleferrand commited on
Commit
eb4c7b6
·
verified ·
1 Parent(s): f3b7ba5

Upload 10 files

Browse files
Files changed (10) hide show
  1. config.json +117 -0
  2. optimizer.pt +3 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. tokenizer_config.json +13 -0
  8. trainer_state.json +193 -0
  9. training_args.bin +3 -0
  10. vocab.json +41 -0
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LeBenchmark/wav2vec2-FR-7K-large",
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": true,
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": true,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.0,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.0,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.05,
77
+ "mask_time_selection": "static",
78
+ "model_type": "wav2vec2",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 24,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 1024,
89
+ "pad_token_id": 41,
90
+ "proj_codevector_dim": 256,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.31.0",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 42,
116
+ "xvector_output_dim": 512
117
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81213e931f52015c4961510971756d68080d51199517039814153bac8a3d864e
3
+ size 2524103674
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": true,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4403ca6c4be75cdea84d3adecb6830188786ad9eb1e1cae9ff469cd245850911
3
+ size 1262074538
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce3b6aa659266b00a34c0633854f963f4144fe79c90f3a4dc4bba18c8b86b376
3
+ size 14308
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e8e95333725c66085694b7eddc5b23417db2ab532228e9fbe8e3ea0dc5adfcc
3
+ size 1064
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
trainer_state.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 20.0,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_loss": 3.1823601722717285,
13
+ "eval_runtime": 1.8503,
14
+ "eval_samples_per_second": 126.469,
15
+ "eval_steps_per_second": 16.214,
16
+ "eval_wer": 1.0,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_loss": 2.933835983276367,
22
+ "eval_runtime": 1.8259,
23
+ "eval_samples_per_second": 128.156,
24
+ "eval_steps_per_second": 16.43,
25
+ "eval_wer": 1.0,
26
+ "step": 50
27
+ },
28
+ {
29
+ "epoch": 3.0,
30
+ "eval_loss": 2.8917059898376465,
31
+ "eval_runtime": 1.8294,
32
+ "eval_samples_per_second": 127.913,
33
+ "eval_steps_per_second": 16.399,
34
+ "eval_wer": 1.0,
35
+ "step": 75
36
+ },
37
+ {
38
+ "epoch": 4.0,
39
+ "eval_loss": 2.9372332096099854,
40
+ "eval_runtime": 1.8378,
41
+ "eval_samples_per_second": 127.327,
42
+ "eval_steps_per_second": 16.324,
43
+ "eval_wer": 1.0,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 5.0,
48
+ "eval_loss": 2.8342607021331787,
49
+ "eval_runtime": 1.843,
50
+ "eval_samples_per_second": 126.965,
51
+ "eval_steps_per_second": 16.278,
52
+ "eval_wer": 1.0,
53
+ "step": 125
54
+ },
55
+ {
56
+ "epoch": 6.0,
57
+ "eval_loss": 2.8205959796905518,
58
+ "eval_runtime": 1.8525,
59
+ "eval_samples_per_second": 126.315,
60
+ "eval_steps_per_second": 16.194,
61
+ "eval_wer": 1.0,
62
+ "step": 150
63
+ },
64
+ {
65
+ "epoch": 7.0,
66
+ "eval_loss": 2.7126834392547607,
67
+ "eval_runtime": 1.8471,
68
+ "eval_samples_per_second": 126.686,
69
+ "eval_steps_per_second": 16.242,
70
+ "eval_wer": 0.9917290271760536,
71
+ "step": 175
72
+ },
73
+ {
74
+ "epoch": 8.0,
75
+ "eval_loss": 2.2903497219085693,
76
+ "eval_runtime": 1.8549,
77
+ "eval_samples_per_second": 126.15,
78
+ "eval_steps_per_second": 16.173,
79
+ "eval_wer": 0.9279243796770382,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 9.0,
84
+ "eval_loss": 2.161506414413452,
85
+ "eval_runtime": 1.8637,
86
+ "eval_samples_per_second": 125.556,
87
+ "eval_steps_per_second": 16.097,
88
+ "eval_wer": 0.9641591177628988,
89
+ "step": 225
90
+ },
91
+ {
92
+ "epoch": 10.0,
93
+ "eval_loss": 1.8126736879348755,
94
+ "eval_runtime": 1.868,
95
+ "eval_samples_per_second": 125.265,
96
+ "eval_steps_per_second": 16.06,
97
+ "eval_wer": 0.790862544308783,
98
+ "step": 250
99
+ },
100
+ {
101
+ "epoch": 11.0,
102
+ "eval_loss": 1.8635412454605103,
103
+ "eval_runtime": 1.869,
104
+ "eval_samples_per_second": 125.203,
105
+ "eval_steps_per_second": 16.052,
106
+ "eval_wer": 0.7707758960220559,
107
+ "step": 275
108
+ },
109
+ {
110
+ "epoch": 12.0,
111
+ "eval_loss": 1.9644334316253662,
112
+ "eval_runtime": 1.8669,
113
+ "eval_samples_per_second": 125.34,
114
+ "eval_steps_per_second": 16.069,
115
+ "eval_wer": 0.7412367073651044,
116
+ "step": 300
117
+ },
118
+ {
119
+ "epoch": 13.0,
120
+ "eval_loss": 1.9838531017303467,
121
+ "eval_runtime": 1.8741,
122
+ "eval_samples_per_second": 124.858,
123
+ "eval_steps_per_second": 16.007,
124
+ "eval_wer": 0.7565970854667192,
125
+ "step": 325
126
+ },
127
+ {
128
+ "epoch": 14.0,
129
+ "eval_loss": 2.0554840564727783,
130
+ "eval_runtime": 1.874,
131
+ "eval_samples_per_second": 124.864,
132
+ "eval_steps_per_second": 16.008,
133
+ "eval_wer": 0.7400551398188263,
134
+ "step": 350
135
+ },
136
+ {
137
+ "epoch": 15.0,
138
+ "eval_loss": 2.204854965209961,
139
+ "eval_runtime": 1.8695,
140
+ "eval_samples_per_second": 125.17,
141
+ "eval_steps_per_second": 16.047,
142
+ "eval_wer": 0.7447814100039386,
143
+ "step": 375
144
+ },
145
+ {
146
+ "epoch": 16.0,
147
+ "eval_loss": 2.2302396297454834,
148
+ "eval_runtime": 1.8667,
149
+ "eval_samples_per_second": 125.353,
150
+ "eval_steps_per_second": 16.071,
151
+ "eval_wer": 0.7443875541551792,
152
+ "step": 400
153
+ },
154
+ {
155
+ "epoch": 17.0,
156
+ "eval_loss": 2.2742059230804443,
157
+ "eval_runtime": 1.8774,
158
+ "eval_samples_per_second": 124.639,
159
+ "eval_steps_per_second": 15.979,
160
+ "eval_wer": 0.7581725088617566,
161
+ "step": 425
162
+ },
163
+ {
164
+ "epoch": 18.0,
165
+ "eval_loss": 2.375885248184204,
166
+ "eval_runtime": 1.8762,
167
+ "eval_samples_per_second": 124.719,
168
+ "eval_steps_per_second": 15.99,
169
+ "eval_wer": 0.7487199684915321,
170
+ "step": 450
171
+ },
172
+ {
173
+ "epoch": 19.0,
174
+ "eval_loss": 2.4379167556762695,
175
+ "eval_runtime": 1.8721,
176
+ "eval_samples_per_second": 124.99,
177
+ "eval_steps_per_second": 16.024,
178
+ "eval_wer": 0.759747932256794,
179
+ "step": 475
180
+ },
181
+ {
182
+ "epoch": 20.0,
183
+ "learning_rate": 0.0001008,
184
+ "loss": 1.9367,
185
+ "step": 500
186
+ }
187
+ ],
188
+ "max_steps": 750,
189
+ "num_train_epochs": 30,
190
+ "total_flos": 2.2993843982800115e+18,
191
+ "trial_name": null,
192
+ "trial_params": null
193
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb96705f8ad7a122b68cd7562c01df4c1edf884ebf043373e62ce111811b754
3
+ size 4408
vocab.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 1,
3
+ "a": 2,
4
+ "b": 3,
5
+ "c": 4,
6
+ "d": 5,
7
+ "e": 6,
8
+ "f": 7,
9
+ "g": 8,
10
+ "h": 9,
11
+ "i": 10,
12
+ "j": 11,
13
+ "k": 12,
14
+ "l": 13,
15
+ "m": 14,
16
+ "n": 15,
17
+ "o": 16,
18
+ "p": 17,
19
+ "q": 18,
20
+ "r": 19,
21
+ "s": 20,
22
+ "t": 21,
23
+ "u": 22,
24
+ "v": 23,
25
+ "w": 24,
26
+ "x": 25,
27
+ "y": 26,
28
+ "z": 27,
29
+ "|": 0,
30
+ "à": 28,
31
+ "â": 29,
32
+ "ç": 30,
33
+ "è": 31,
34
+ "é": 32,
35
+ "ê": 33,
36
+ "ë": 34,
37
+ "î": 35,
38
+ "ï": 36,
39
+ "ò": 37,
40
+ "ù": 38
41
+ }