Hugging Face's logo

Guerte
/
hbrt-ctc

Safetensors
hubert
Model card Files
xet
Community
Guerte commited on
Commit
3cb6571
·
verified ·
1 Parent(s): 65cbc84

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +73 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +10 -0
  4. tokenizer_config.json +49 -0
  5. vocab.json +90 -0
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "add_adapter": false,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "HubertForCTC"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_pos_batch_norm": false,
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": 87,
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.56.0.dev0",
71
+ "use_weighted_layer_sum": false,
72
+ "vocab_size": 90
73
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f34008109458169680756f4bf928616cbc5e38e403b302b437506feade686c
3
+ size 377789120
preprocessor_config.json ADDED
@@ -0,0 +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
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "86": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "87": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "88": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "89": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "target_lang": null,
46
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
47
+ "unk_token": "[UNK]",
48
+ "word_delimiter_token": "|"
49
+ }
vocab.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 1,
3
+ "1": 2,
4
+ "2": 3,
5
+ "3": 4,
6
+ "4": 5,
7
+ "8": 6,
8
+ "9": 7,
9
+ "[PAD]": 87,
10
+ "[UNK]": 86,
11
+ "_": 8,
12
+ "a": 9,
13
+ "b": 10,
14
+ "c": 11,
15
+ "d": 12,
16
+ "e": 13,
17
+ "f": 14,
18
+ "g": 15,
19
+ "h": 16,
20
+ "i": 17,
21
+ "j": 18,
22
+ "k": 19,
23
+ "l": 20,
24
+ "m": 21,
25
+ "n": 22,
26
+ "o": 23,
27
+ "p": 24,
28
+ "q": 25,
29
+ "r": 26,
30
+ "s": 27,
31
+ "t": 28,
32
+ "u": 29,
33
+ "v": 30,
34
+ "w": 31,
35
+ "x": 32,
36
+ "y": 33,
37
+ "z": 34,
38
+ "|": 0,
39
+ "µ": 35,
40
+ "à": 36,
41
+ "á": 37,
42
+ "â": 38,
43
+ "ã": 39,
44
+ "ä": 40,
45
+ "ç": 41,
46
+ "è": 42,
47
+ "é": 43,
48
+ "ê": 44,
49
+ "ë": 45,
50
+ "ì": 46,
51
+ "í": 47,
52
+ "î": 48,
53
+ "ï": 49,
54
+ "ð": 50,
55
+ "ñ": 51,
56
+ "ò": 52,
57
+ "ó": 53,
58
+ "ô": 54,
59
+ "õ": 55,
60
+ "ö": 56,
61
+ "ø": 57,
62
+ "ù": 58,
63
+ "ú": 59,
64
+ "û": 60,
65
+ "ü": 61,
66
+ "ý": 62,
67
+ "ā": 63,
68
+ "ă": 64,
69
+ "ą": 65,
70
+ "đ": 66,
71
+ "ĩ": 67,
72
+ "ł": 68,
73
+ "ń": 69,
74
+ "ŋ": 70,
75
+ "œ": 71,
76
+ "ş": 72,
77
+ "ƭ": 73,
78
+ "ɐ": 74,
79
+ "ɓ": 75,
80
+ "ɔ": 76,
81
+ "ɗ": 77,
82
+ "ə": 78,
83
+ "ˈ": 79,
84
+ "ː": 80,
85
+ "ẽ": 81,
86
+ "ị": 82,
87
+ "ồ": 83,
88
+ "ớ": 84,
89
+ "ὀ": 85
90
+ }