Hugging Face's logo

ivangtorre
/
wav2vec2-xlsr-300m-kotiria

Automatic Speech Recognition
Transformers
PyTorch
Guanano
wav2vec2
audio
speech
kotiria
xlsr-fine-tuning
Eval Results
Inference Endpoints
Model card Files Community
ivangtorre commited on
Commit
6049946
•
1 Parent(s): 1c55859

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +115 -0
  2. preprocessor_config.json +10 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +6 -0
  5. tokenizer_config.json +13 -0
  6. vocab.json +88 -0
config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "adapter_kernel_size": 3,
4
+ "adapter_stride": 2,
5
+ "add_adapter": false,
6
+ "apply_spec_augment": true,
7
+ "architectures": [
8
+ "Wav2Vec2ForCTC"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 1,
12
+ "classifier_proj_size": 256,
13
+ "codevector_dim": 768,
14
+ "contrastive_logits_temperature": 0.1,
15
+ "conv_bias": true,
16
+ "conv_dim": [
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512
24
+ ],
25
+ "conv_kernel": [
26
+ 10,
27
+ 3,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 2,
32
+ 2
33
+ ],
34
+ "conv_stride": [
35
+ 5,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2
42
+ ],
43
+ "ctc_loss_reduction": "sum",
44
+ "ctc_zero_infinity": false,
45
+ "diversity_loss_weight": 0.1,
46
+ "do_stable_layer_norm": true,
47
+ "eos_token_id": 2,
48
+ "feat_extract_activation": "gelu",
49
+ "feat_extract_dropout": 0.0,
50
+ "feat_extract_norm": "layer",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "gradient_checkpointing": false,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.1,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.5,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "num_adapter_layers": 3,
78
+ "num_attention_heads": 16,
79
+ "num_codevector_groups": 2,
80
+ "num_codevectors_per_group": 320,
81
+ "num_conv_pos_embedding_groups": 16,
82
+ "num_conv_pos_embeddings": 128,
83
+ "num_feat_extract_layers": 7,
84
+ "num_hidden_layers": 24,
85
+ "num_negatives": 100,
86
+ "output_hidden_size": 1024,
87
+ "pad_token_id": 0,
88
+ "proj_codevector_dim": 768,
89
+ "tdnn_dilation": [
90
+ 1,
91
+ 2,
92
+ 3,
93
+ 1,
94
+ 1
95
+ ],
96
+ "tdnn_dim": [
97
+ 512,
98
+ 512,
99
+ 512,
100
+ 512,
101
+ 1500
102
+ ],
103
+ "tdnn_kernel": [
104
+ 5,
105
+ 3,
106
+ 3,
107
+ 1,
108
+ 1
109
+ ],
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.29.2",
112
+ "use_weighted_layer_sum": false,
113
+ "vocab_size": 86,
114
+ "xvector_output_dim": 512
115
+ }
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": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc0b8472ac3e156ffb9e1f0d4fa1c31e76b87ccf7663da1dbc0bc235c35af736
3
+ size 1262249002
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
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
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "<unk>",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<s>": 1,
3
+ "<pad>": 0,
4
+ "</s>": 2,
5
+ "<unk>": 3,
6
+ "|": 4,
7
+ "a": 5,
8
+ "i": 6,
9
+ "o": 7,
10
+ "r": 8,
11
+ "h": 9,
12
+ "t": 10,
13
+ "n": 11,
14
+ "e": 12,
15
+ "U": 13,
16
+ "k": 14,
17
+ "u": 15,
18
+ "'": 16,
19
+ "m": 17,
20
+ "s": 18,
21
+ "p": 19,
22
+ "y": 20,
23
+ ".": 21,
24
+ "w": 22,
25
+ "d": 23,
26
+ "~": 24,
27
+ "b": 25,
28
+ "c": 26,
29
+ ":": 27,
30
+ "ã": 28,
31
+ ",": 29,
32
+ "l": 30,
33
+ "ñ": 31,
34
+ "õ": 32,
35
+ "g": 33,
36
+ "(": 34,
37
+ ")": 35,
38
+ "v": 36,
39
+ "´": 37,
40
+ "f": 38,
41
+ "q": 39,
42
+ "ç": 40,
43
+ "?": 41,
44
+ "j": 42,
45
+ "A": 43,
46
+ "K": 44,
47
+ "z": 45,
48
+ "é": 46,
49
+ "T": 47,
50
+ "\t": 48,
51
+ "N": 49,
52
+ "M": 50,
53
+ "!": 51,
54
+ "D": 52,
55
+ "Y": 53,
56
+ "P": 54,
57
+ "H": 55,
58
+ "ó": 56,
59
+ "á": 57,
60
+ "J": 58,
61
+ "R": 59,
62
+ "x": 60,
63
+ "W": 61,
64
+ "ú": 62,
65
+ "0": 63,
66
+ "B": 64,
67
+ "í": 65,
68
+ "E": 66,
69
+ "2": 67,
70
+ "1": 68,
71
+ "I": 69,
72
+ "3": 70,
73
+ "-": 71,
74
+ "S": 72,
75
+ "C": 73,
76
+ "L": 74,
77
+ "8": 75,
78
+ "G": 76,
79
+ "F": 77,
80
+ "Ã": 78,
81
+ "9": 79,
82
+ "6": 80,
83
+ "Q": 81,
84
+ "4": 82,
85
+ "Ñ": 83,
86
+ "O": 84,
87
+ "7": 85
88
+ }