Hugging Face's logo

ylacombe
/
wav2vec2-bert-CV16-en-libri

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
librispeech_asr
Generated from Trainer
Model card Files
xet
 Metrics Community
ylacombe commited on
Commit
4e8dad9
·
verified ·
1 Parent(s): 3071e6a

Training in progress, step 500

Browse files
Files changed (13) hide show
  1. config.json +82 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +11 -0
  4. runs/Jan16_10-18-11_vorace/events.out.tfevents.1705400484.vorace.450227.0 +3 -0
  5. runs/Jan16_10-22-26_vorace/events.out.tfevents.1705400669.vorace.452915.0 +3 -0
  6. runs/Jan16_10-29-35_vorace/events.out.tfevents.1705401019.vorace.456076.0 +3 -0
  7. runs/Jan16_10-31-26_vorace/events.out.tfevents.1705401186.vorace.457346.0 +3 -0
  8. runs/Jan16_10-33-37_vorace/events.out.tfevents.1705401365.vorace.458738.0 +3 -0
  9. runs/Jan16_10-42-05_vorace/events.out.tfevents.1705401761.vorace.462641.0 +3 -0
  10. special_tokens_map.json +30 -0
  11. tokenizer_config.json +48 -0
  12. training_args.bin +3 -0
  13. vocab.json +35 -0
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/w2v-bert-2.0",
3
+ "activation_dropout": 0.05,
4
+ "adapter_act": "relu",
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": true,
8
+ "apply_spec_augment": false,
9
+ "architectures": [
10
+ "Wav2Vec2BertForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 768,
15
+ "codevector_dim": 768,
16
+ "conformer_conv_dropout": 0.1,
17
+ "contrastive_logits_temperature": 0.1,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "ctc_loss_reduction": "mean",
20
+ "ctc_zero_infinity": false,
21
+ "diversity_loss_weight": 0.1,
22
+ "eos_token_id": 2,
23
+ "feat_proj_dropout": 0.05,
24
+ "feat_quantizer_dropout": 0.0,
25
+ "feature_projection_input_dim": 160,
26
+ "final_dropout": 0.0,
27
+ "hidden_act": "swish",
28
+ "hidden_dropout": 0.05,
29
+ "hidden_size": 1024,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "layer_norm_eps": 1e-05,
33
+ "layerdrop": 0.0,
34
+ "left_max_position_embeddings": 64,
35
+ "mask_feature_length": 10,
36
+ "mask_feature_min_masks": 0,
37
+ "mask_feature_prob": 0.0,
38
+ "mask_time_length": 10,
39
+ "mask_time_min_masks": 2,
40
+ "mask_time_prob": 0.0,
41
+ "max_source_positions": 5000,
42
+ "model_type": "wav2vec2-bert",
43
+ "num_adapter_layers": 1,
44
+ "num_attention_heads": 16,
45
+ "num_codevector_groups": 2,
46
+ "num_codevectors_per_group": 320,
47
+ "num_hidden_layers": 24,
48
+ "num_negatives": 100,
49
+ "output_hidden_size": 1024,
50
+ "pad_token_id": 0,
51
+ "position_embeddings_type": "relative_key",
52
+ "proj_codevector_dim": 768,
53
+ "right_max_position_embeddings": 8,
54
+ "rotary_embedding_base": 10000,
55
+ "tdnn_dilation": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 1,
60
+ 1
61
+ ],
62
+ "tdnn_dim": [
63
+ 512,
64
+ 512,
65
+ 512,
66
+ 512,
67
+ 1500
68
+ ],
69
+ "tdnn_kernel": [
70
+ 5,
71
+ 3,
72
+ 3,
73
+ 1,
74
+ 1
75
+ ],
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.37.0.dev0",
78
+ "use_intermediate_ffn_before_adapter": false,
79
+ "use_weighted_layer_sum": false,
80
+ "vocab_size": 33,
81
+ "xvector_output_dim": 512
82
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:616db20c0308312afa7b216c415e6f34b53ff3a70a11908d6518efa102a32613
3
+ size 2422949860
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 1,
7
+ "processor_class": "Wav2Vec2BertProcessor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000,
10
+ "stride": 2
11
+ }
runs/Jan16_10-18-11_vorace/events.out.tfevents.1705400484.vorace.450227.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd1f6c22793b671641735c4652bd9860b0592b728b460ff0f0d4c41774e48a5
3
+ size 4136
runs/Jan16_10-22-26_vorace/events.out.tfevents.1705400669.vorace.452915.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664626530ebb7198b38653bd5f2e5c39b909fde96baf169fb20a20ac511c6daf
3
+ size 4136
runs/Jan16_10-29-35_vorace/events.out.tfevents.1705401019.vorace.456076.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3bce4519f63ca30a19ae284b376bcd99d271ef8f353b7c9a83830c1a7fe07e
3
+ size 4136
runs/Jan16_10-31-26_vorace/events.out.tfevents.1705401186.vorace.457346.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83577f0021aadf9a6daf82e90f378eae1cb9c09394536606353b2125784bff4
3
+ size 4136
runs/Jan16_10-33-37_vorace/events.out.tfevents.1705401365.vorace.458738.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec638eedf4f0ba56707aca5a84c1310422d4a75d25d25d5c0541e4990fa3143
3
+ size 7679
runs/Jan16_10-42-05_vorace/events.out.tfevents.1705401761.vorace.462641.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43cda48ef96a461bf9cdbb001ac96c8566467d001c6ac2c0c276524fb28eb8df
3
+ size 21994
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "<pad>",
42
+ "processor_class": "Wav2Vec2BertProcessor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "<unk>",
47
+ "word_delimiter_token": "|"
48
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ced92d4aecf114078bdeb07542d2c0505deaf40887bb290821a738a3033d039
3
+ size 4728
vocab.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 5,
3
+ "-": 6,
4
+ "</s>": 2,
5
+ "<pad>": 0,
6
+ "<s>": 1,
7
+ "<unk>": 3,
8
+ "a": 7,
9
+ "b": 8,
10
+ "c": 9,
11
+ "d": 10,
12
+ "e": 11,
13
+ "f": 12,
14
+ "g": 13,
15
+ "h": 14,
16
+ "i": 15,
17
+ "j": 16,
18
+ "k": 17,
19
+ "l": 18,
20
+ "m": 19,
21
+ "n": 20,
22
+ "o": 21,
23
+ "p": 22,
24
+ "q": 23,
25
+ "r": 24,
26
+ "s": 25,
27
+ "t": 26,
28
+ "u": 27,
29
+ "v": 28,
30
+ "w": 29,
31
+ "x": 30,
32
+ "y": 31,
33
+ "z": 32,
34
+ "|": 4
35
+ }