patrickvonplaten commited on
Commit
1365444
1 Parent(s): 3b05449

upload weights

Browse files
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-1b",
3
+ "activation_dropout": 0.05,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.05,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 1024,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.05,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.05,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.05,
57
+ "hidden_size": 1280,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 5120,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.05,
62
+ "mask_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.05,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_attn_adapters": 1,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 48,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1280,
80
+ "pad_token_id": 0,
81
+ "proj_codevector_dim": 1024,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.30.0.dev0",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 154,
107
+ "xvector_output_dim": 512
108
+ }
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 sha256:5abcbd07e793c49e2d2bbba9ad1e9acf7b1e277089e35f4d13a414c46cc7c509
3
+ size 3859750093
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 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 75,
3
+ "\"": 62,
4
+ "$": 48,
5
+ "%": 47,
6
+ "&": 57,
7
+ "'": 31,
8
+ "+": 56,
9
+ ",": 44,
10
+ "-": 32,
11
+ ".": 37,
12
+ "/": 45,
13
+ "0": 27,
14
+ "1": 30,
15
+ "2": 35,
16
+ "3": 41,
17
+ "4": 39,
18
+ "5": 38,
19
+ "6": 40,
20
+ "7": 43,
21
+ "8": 42,
22
+ "9": 36,
23
+ ":": 46,
24
+ ";": 52,
25
+ "</s>": 2,
26
+ "<pad>": 0,
27
+ "<s>": 1,
28
+ "<unk>": 3,
29
+ "[": 59,
30
+ "]": 60,
31
+ "`": 92,
32
+ "a": 7,
33
+ "b": 24,
34
+ "c": 16,
35
+ "d": 15,
36
+ "e": 5,
37
+ "f": 19,
38
+ "g": 21,
39
+ "h": 13,
40
+ "i": 9,
41
+ "j": 29,
42
+ "k": 26,
43
+ "l": 14,
44
+ "m": 18,
45
+ "n": 10,
46
+ "o": 8,
47
+ "p": 20,
48
+ "q": 34,
49
+ "r": 12,
50
+ "s": 11,
51
+ "t": 6,
52
+ "u": 17,
53
+ "v": 25,
54
+ "w": 23,
55
+ "x": 28,
56
+ "y": 22,
57
+ "z": 33,
58
+ "|": 4,
59
+ "£": 68,
60
+ "¥": 53,
61
+ "§": 139,
62
+ "°": 58,
63
+ "²": 76,
64
+ "ß": 82,
65
+ "à": 84,
66
+ "á": 49,
67
+ "â": 81,
68
+ "ã": 66,
69
+ "ä": 78,
70
+ "å": 123,
71
+ "æ": 110,
72
+ "ç": 64,
73
+ "è": 79,
74
+ "é": 55,
75
+ "ê": 88,
76
+ "ë": 87,
77
+ "í": 50,
78
+ "î": 97,
79
+ "ï": 85,
80
+ "ð": 98,
81
+ "ñ": 83,
82
+ "ò": 105,
83
+ "ó": 67,
84
+ "ô": 86,
85
+ "õ": 69,
86
+ "ö": 74,
87
+ "ø": 91,
88
+ "ú": 70,
89
+ "û": 99,
90
+ "ü": 54,
91
+ "ý": 112,
92
+ "þ": 132,
93
+ "ā": 100,
94
+ "ă": 102,
95
+ "ć": 94,
96
+ "č": 89,
97
+ "ē": 143,
98
+ "ę": 119,
99
+ "ě": 140,
100
+ "ğ": 153,
101
+ "ī": 107,
102
+ "ı": 103,
103
+ "ł": 73,
104
+ "ń": 118,
105
+ "ň": 137,
106
+ "ō": 80,
107
+ "ő": 120,
108
+ "œ": 96,
109
+ "ř": 108,
110
+ "ş": 116,
111
+ "š": 90,
112
+ "ū": 101,
113
+ "ž": 95,
114
+ "ș": 104,
115
+ "ə": 138,
116
+ "ʻ": 115,
117
+ "́": 93,
118
+ "̇": 77,
119
+ "α": 106,
120
+ "κ": 109,
121
+ "π": 117,
122
+ "χ": 141,
123
+ "а": 144,
124
+ "в": 124,
125
+ "е": 125,
126
+ "з": 130,
127
+ "и": 113,
128
+ "й": 127,
129
+ "к": 114,
130
+ "л": 126,
131
+ "н": 128,
132
+ "ь": 131,
133
+ "я": 129,
134
+ "נ": 147,
135
+ "ע": 148,
136
+ "ṃ": 121,
137
+ "ạ": 111,
138
+ "ả": 145,
139
+ "ị": 146,
140
+ "ụ": 122,
141
+ "​": 71,
142
+ "–": 61,
143
+ "—": 51,
144
+ "‘": 72,
145
+ "’": 65,
146
+ "”": 63,
147
+ "≡": 142,
148
+ "京": 149,
149
+ "先": 135,
150
+ "大": 151,
151
+ "尚": 134,
152
+ "时": 133,
153
+ "生": 136,
154
+ "都": 150,
155
+ "阪": 152
156
+ }