Hugging Face's logo

halcyonzhou
/
unispeech-sat-base

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
unispeech-sat
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
halcyonzhou commited on
Commit
d6aff12
·
verified ·
1 Parent(s): c49322b

Training in progress, step 500

Browse files
Files changed (9) hide show
  1. config.json +104 -104
  2. model.safetensors +1 -1
  3. preprocessor_config.json +10 -10
  4. runs/Aug30_20-40-57_zjh/events.out.tfevents.1756557678.zjh.6440.0 +3 -0
  5. runs/Aug30_20-55-14_zjh/events.out.tfevents.1756558533.zjh.13840.0 +3 -0
  6. special_tokens_map.json +30 -6
  7. tokenizer_config.json +51 -51
  8. training_args.bin +2 -2
  9. vocab.json +34 -34
config.json CHANGED
@@ -1,104 +1,104 @@
1
- {
2
- "activation_dropout": 0.1,
3
- "apply_spec_augment": true,
4
- "architectures": [
5
- "UniSpeechSatForCTC"
6
- ],
7
- "attention_dropout": 0.1,
8
- "bos_token_id": 1,
9
- "classifier_proj_size": 256,
10
- "codevector_dim": 256,
11
- "contrastive_logits_temperature": 0.1,
12
- "conv_bias": false,
13
- "conv_dim": [
14
- 512,
15
- 512,
16
- 512,
17
- 512,
18
- 512,
19
- 512,
20
- 512
21
- ],
22
- "conv_kernel": [
23
- 10,
24
- 3,
25
- 3,
26
- 3,
27
- 3,
28
- 2,
29
- 2
30
- ],
31
- "conv_stride": [
32
- 5,
33
- 2,
34
- 2,
35
- 2,
36
- 2,
37
- 2,
38
- 2
39
- ],
40
- "ctc_loss_reduction": "mean",
41
- "ctc_zero_infinity": false,
42
- "diversity_loss_weight": 0.1,
43
- "do_stable_layer_norm": false,
44
- "eos_token_id": 2,
45
- "feat_extract_activation": "gelu",
46
- "feat_extract_dropout": 0.0,
47
- "feat_extract_norm": "group",
48
- "feat_proj_dropout": 0.1,
49
- "feat_quantizer_dropout": 0.0,
50
- "final_dropout": 0.1,
51
- "hidden_act": "gelu",
52
- "hidden_dropout": 0.1,
53
- "hidden_dropout_prob": 0.1,
54
- "hidden_size": 768,
55
- "initializer_range": 0.02,
56
- "intermediate_size": 3072,
57
- "layer_norm_eps": 1e-05,
58
- "layerdrop": 0.1,
59
- "mask_feature_length": 10,
60
- "mask_feature_min_masks": 0,
61
- "mask_feature_prob": 0.0,
62
- "mask_time_length": 10,
63
- "mask_time_min_masks": 2,
64
- "mask_time_prob": 0.05,
65
- "model_type": "unispeech-sat",
66
- "num_attention_heads": 12,
67
- "num_clusters": 504,
68
- "num_codevector_groups": 2,
69
- "num_codevectors_per_group": 320,
70
- "num_conv_pos_embedding_groups": 16,
71
- "num_conv_pos_embeddings": 128,
72
- "num_feat_extract_layers": 7,
73
- "num_hidden_layers": 12,
74
- "num_negatives": 100,
75
- "pad_token_id": 0,
76
- "proj_codevector_dim": 256,
77
- "tdnn_dilation": [
78
- 1,
79
- 2,
80
- 3,
81
- 1,
82
- 1
83
- ],
84
- "tdnn_dim": [
85
- 512,
86
- 512,
87
- 512,
88
- 512,
89
- 1500
90
- ],
91
- "tdnn_kernel": [
92
- 5,
93
- 3,
94
- 3,
95
- 1,
96
- 1
97
- ],
98
- "tokenizer_class": "Wav2Vec2CTCTokenizer",
99
- "torch_dtype": "float32",
100
- "transformers_version": "4.55.4",
101
- "use_weighted_layer_sum": false,
102
- "vocab_size": 32,
103
- "xvector_output_dim": 512
104
- }
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "UniSpeechSatForCTC"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "classifier_proj_size": 256,
10
+ "codevector_dim": 256,
11
+ "contrastive_logits_temperature": 0.1,
12
+ "conv_bias": false,
13
+ "conv_dim": [
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "conv_kernel": [
23
+ 10,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 2,
29
+ 2
30
+ ],
31
+ "conv_stride": [
32
+ 5,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2
39
+ ],
40
+ "ctc_loss_reduction": "mean",
41
+ "ctc_zero_infinity": false,
42
+ "diversity_loss_weight": 0.1,
43
+ "do_stable_layer_norm": false,
44
+ "eos_token_id": 2,
45
+ "feat_extract_activation": "gelu",
46
+ "feat_extract_dropout": 0.0,
47
+ "feat_extract_norm": "group",
48
+ "feat_proj_dropout": 0.1,
49
+ "feat_quantizer_dropout": 0.0,
50
+ "final_dropout": 0.1,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout": 0.1,
53
+ "hidden_dropout_prob": 0.1,
54
+ "hidden_size": 768,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 3072,
57
+ "layer_norm_eps": 1e-05,
58
+ "layerdrop": 0.1,
59
+ "mask_feature_length": 10,
60
+ "mask_feature_min_masks": 0,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_masks": 2,
64
+ "mask_time_prob": 0.05,
65
+ "model_type": "unispeech-sat",
66
+ "num_attention_heads": 12,
67
+ "num_clusters": 504,
68
+ "num_codevector_groups": 2,
69
+ "num_codevectors_per_group": 320,
70
+ "num_conv_pos_embedding_groups": 16,
71
+ "num_conv_pos_embeddings": 128,
72
+ "num_feat_extract_layers": 7,
73
+ "num_hidden_layers": 12,
74
+ "num_negatives": 100,
75
+ "pad_token_id": 0,
76
+ "proj_codevector_dim": 256,
77
+ "tdnn_dilation": [
78
+ 1,
79
+ 2,
80
+ 3,
81
+ 1,
82
+ 1
83
+ ],
84
+ "tdnn_dim": [
85
+ 512,
86
+ 512,
87
+ 512,
88
+ 512,
89
+ 1500
90
+ ],
91
+ "tdnn_kernel": [
92
+ 5,
93
+ 3,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
99
+ "torch_dtype": "float32",
100
+ "transformers_version": "4.51.0",
101
+ "use_weighted_layer_sum": false,
102
+ "vocab_size": 32,
103
+ "xvector_output_dim": 512
104
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77defddc818ed32ce3fc8e7d34a9f0836438e896b2f1b688076e4f125929e98f
3
  size 377612176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7449f5c3d4a726fea7d5e044718ce92bd6538d64d2f5a28ca5f8ce90ddb7f32e
3
  size 377612176
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,
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,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
runs/Aug30_20-40-57_zjh/events.out.tfevents.1756557678.zjh.6440.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c95212c7b40f954547156bbacb653e80e4b6a82335b8e10fb6f3f10c115c026
3
+ size 6454
runs/Aug30_20-55-14_zjh/events.out.tfevents.1756558533.zjh.13840.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb5b2b2c48ccb96efce9d3a70ac5db04f01c62bc6865c55d6be3e64ed3c7487
3
+ size 7616
special_tokens_map.json CHANGED
@@ -1,6 +1,30 @@
1
- {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "<pad>",
5
- "unk_token": "<unk>"
6
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 CHANGED
@@ -1,51 +1,51 @@
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": false,
38
- "do_lower_case": false,
39
- "do_normalize": true,
40
- "eos_token": "</s>",
41
- "extra_special_tokens": {},
42
- "model_max_length": 1000000000000000019884624838656,
43
- "pad_token": "<pad>",
44
- "processor_class": "Wav2Vec2Processor",
45
- "replace_word_delimiter_char": " ",
46
- "return_attention_mask": false,
47
- "target_lang": null,
48
- "tokenizer_class": "Wav2Vec2CTCTokenizer",
49
- "unk_token": "<unk>",
50
- "word_delimiter_token": "|"
51
- }
 
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": false,
38
+ "do_lower_case": false,
39
+ "do_normalize": true,
40
+ "eos_token": "</s>",
41
+ "extra_special_tokens": {},
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
44
+ "processor_class": "Wav2Vec2Processor",
45
+ "replace_word_delimiter_char": " ",
46
+ "return_attention_mask": false,
47
+ "target_lang": null,
48
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
49
+ "unk_token": "<unk>",
50
+ "word_delimiter_token": "|"
51
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06eb1c8779ef8e5e3734b6722b7314ecdd2a5ec4f7bbd188e009331c4f1d0a90
3
- size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c435b9d5561145c5daeafcfeba272f458bc3f34316d2c713bfd87c43ef17f3ea
3
+ size 5713
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
+ }