Hugging Face's logo

anyspeech
/
ipa-align-small-speech

Transformers
PyTorch
whisper
Inference Endpoints
Model card Files Community
charsiu commited on
Commit
f4be3a7
•
1 Parent(s): 5d32b7c

Upload SpeechEncoder

Browse files
Files changed (2) hide show
  1. config.json +153 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "anyspeech/ipa-small-speech",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "SpeechEncoder"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 768,
17
+ "decoder_attention_heads": 12,
18
+ "decoder_ffn_dim": 3072,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "model_type": "whisper",
54
+ "num_hidden_layers": 12,
55
+ "num_mel_bins": 80,
56
+ "pad_token_id": 50257,
57
+ "pooling": "mean",
58
+ "proj_size": 512,
59
+ "scale_embedding": false,
60
+ "suppress_tokens": [
61
+ 1,
62
+ 2,
63
+ 7,
64
+ 8,
65
+ 9,
66
+ 10,
67
+ 14,
68
+ 25,
69
+ 26,
70
+ 27,
71
+ 28,
72
+ 29,
73
+ 31,
74
+ 58,
75
+ 59,
76
+ 60,
77
+ 61,
78
+ 62,
79
+ 63,
80
+ 90,
81
+ 91,
82
+ 92,
83
+ 93,
84
+ 359,
85
+ 503,
86
+ 522,
87
+ 542,
88
+ 873,
89
+ 893,
90
+ 902,
91
+ 918,
92
+ 922,
93
+ 931,
94
+ 1350,
95
+ 1853,
96
+ 1982,
97
+ 2460,
98
+ 2627,
99
+ 3246,
100
+ 3253,
101
+ 3268,
102
+ 3536,
103
+ 3846,
104
+ 3961,
105
+ 4183,
106
+ 4667,
107
+ 6585,
108
+ 6647,
109
+ 7273,
110
+ 9061,
111
+ 9383,
112
+ 10428,
113
+ 10929,
114
+ 11938,
115
+ 12033,
116
+ 12331,
117
+ 12562,
118
+ 13793,
119
+ 14157,
120
+ 14635,
121
+ 15265,
122
+ 15618,
123
+ 16553,
124
+ 16604,
125
+ 18362,
126
+ 18956,
127
+ 20075,
128
+ 21675,
129
+ 22520,
130
+ 26130,
131
+ 26161,
132
+ 26435,
133
+ 28279,
134
+ 29464,
135
+ 31650,
136
+ 32302,
137
+ 32470,
138
+ 36865,
139
+ 42863,
140
+ 47425,
141
+ 49870,
142
+ 50254,
143
+ 50258,
144
+ 50360,
145
+ 50361,
146
+ 50362
147
+ ],
148
+ "torch_dtype": "float32",
149
+ "transformers_version": "4.30.0",
150
+ "use_cache": true,
151
+ "use_weighted_layer_sum": false,
152
+ "vocab_size": 51865
153
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb75eca3bb73bd797571bdca4bfd03330e00d6d10a0f4cebdddcde075924d88c
3
+ size 354251646