Hugging Face's logo

utakumi
/
Hubert-common_voice-phoneme-debug-warmup500

Automatic Speech Recognition
Transformers
Safetensors
Japanese
hubert
mozilla-foundation/common_voice_13_0
Generated from Trainer
Inference Endpoints
Model card Files Community
utakumi commited on
Commit
43e5129
•
1 Parent(s): b73b811

Training in progress, step 400

Browse files
Files changed (8) hide show
  1. added_tokens.json +4 -0
  2. config.json +73 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +10 -0
  5. special_tokens_map.json +30 -0
  6. tokenizer_config.json +153 -0
  7. training_args.bin +3 -0
  8. vocab.json +43 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 42,
3
+ "<s>": 41
4
+ }
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "rinna/japanese-hubert-base",
3
+ "activation_dropout": 0.0,
4
+ "add_adapter": false,
5
+ "apply_spec_augment": true,
6
+ "architectures": [
7
+ "HubertForCTC"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 1,
11
+ "classifier_proj_size": 256,
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": true,
42
+ "do_stable_layer_norm": false,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_norm": "group",
46
+ "feat_proj_dropout": 0.0,
47
+ "feat_proj_layer_norm": true,
48
+ "final_dropout": 0.0,
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.0,
51
+ "hidden_size": 768,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 3072,
54
+ "layer_norm_eps": 1e-05,
55
+ "layerdrop": 0.0,
56
+ "mask_feature_length": 10,
57
+ "mask_feature_min_masks": 0,
58
+ "mask_feature_prob": 0.0,
59
+ "mask_time_length": 10,
60
+ "mask_time_min_masks": 2,
61
+ "mask_time_prob": 0.05,
62
+ "model_type": "hubert",
63
+ "num_attention_heads": 12,
64
+ "num_conv_pos_embedding_groups": 16,
65
+ "num_conv_pos_embeddings": 128,
66
+ "num_feat_extract_layers": 7,
67
+ "num_hidden_layers": 12,
68
+ "pad_token_id": 40,
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.47.0.dev0",
71
+ "use_weighted_layer_sum": false,
72
+ "vocab_size": 43
73
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017481f0b5e04893fa21ce217ae40127220338b8947a39302c2f0a742cbb8864
3
+ size 377644548
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
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 ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
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 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "6": {
4
+ "content": "by",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "7": {
12
+ "content": "ch",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "8": {
20
+ "content": "cl",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "10": {
28
+ "content": "dy",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "14": {
36
+ "content": "gy",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "16": {
44
+ "content": "hy",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "20": {
52
+ "content": "ky",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "22": {
60
+ "content": "my",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "24": {
68
+ "content": "ny",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "27": {
76
+ "content": "py",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "29": {
84
+ "content": "ry",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "31": {
92
+ "content": "sh",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "33": {
100
+ "content": "ts",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "39": {
108
+ "content": "[UNK]",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "40": {
116
+ "content": "[PAD]",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "41": {
124
+ "content": "<s>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "42": {
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ }
139
+ },
140
+ "bos_token": "<s>",
141
+ "clean_up_tokenization_spaces": false,
142
+ "do_lower_case": false,
143
+ "eos_token": "</s>",
144
+ "extra_special_tokens": {},
145
+ "model_max_length": 1000000000000000019884624838656,
146
+ "pad_token": "[PAD]",
147
+ "processor_class": "Wav2Vec2Processor",
148
+ "replace_word_delimiter_char": " ",
149
+ "target_lang": null,
150
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
151
+ "unk_token": "[UNK]",
152
+ "word_delimiter_token": "|"
153
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f5998f6869636a05123bb820d13833ffb6465a42b3a7eb6b368866c6bd8d92e
3
+ size 5368
vocab.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "I": 1,
3
+ "N": 2,
4
+ "U": 3,
5
+ "[PAD]": 40,
6
+ "[UNK]": 39,
7
+ "a": 4,
8
+ "b": 5,
9
+ "by": 6,
10
+ "ch": 7,
11
+ "cl": 8,
12
+ "d": 9,
13
+ "dy": 10,
14
+ "e": 11,
15
+ "f": 12,
16
+ "g": 13,
17
+ "gy": 14,
18
+ "h": 15,
19
+ "hy": 16,
20
+ "i": 17,
21
+ "j": 18,
22
+ "k": 19,
23
+ "ky": 20,
24
+ "m": 21,
25
+ "my": 22,
26
+ "n": 23,
27
+ "ny": 24,
28
+ "o": 25,
29
+ "p": 26,
30
+ "py": 27,
31
+ "r": 28,
32
+ "ry": 29,
33
+ "s": 30,
34
+ "sh": 31,
35
+ "t": 32,
36
+ "ts": 33,
37
+ "u": 34,
38
+ "v": 35,
39
+ "w": 36,
40
+ "y": 37,
41
+ "z": 38,
42
+ "|": 0
43
+ }