DeepBeepMeep commited on
Commit
1be8bab
·
verified ·
1 Parent(s): dc7ca6f

Upload 5 files

Browse files
whisper-tiny/config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-tiny",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "d_model": 384,
15
+ "decoder_attention_heads": 6,
16
+ "decoder_ffn_dim": 1536,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 4,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.0,
21
+ "encoder_attention_heads": 6,
22
+ "encoder_ffn_dim": 1536,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 4,
25
+ "eos_token_id": 50257,
26
+ "forced_decoder_ids": [
27
+ [
28
+ 1,
29
+ 50259
30
+ ],
31
+ [
32
+ 2,
33
+ 50359
34
+ ],
35
+ [
36
+ 3,
37
+ 50363
38
+ ]
39
+ ],
40
+ "init_std": 0.02,
41
+ "is_encoder_decoder": true,
42
+ "max_length": 448,
43
+ "max_source_positions": 1500,
44
+ "max_target_positions": 448,
45
+ "model_type": "whisper",
46
+ "num_hidden_layers": 4,
47
+ "num_mel_bins": 80,
48
+ "pad_token_id": 50257,
49
+ "scale_embedding": false,
50
+ "suppress_tokens": [
51
+ 1,
52
+ 2,
53
+ 7,
54
+ 8,
55
+ 9,
56
+ 10,
57
+ 14,
58
+ 25,
59
+ 26,
60
+ 27,
61
+ 28,
62
+ 29,
63
+ 31,
64
+ 58,
65
+ 59,
66
+ 60,
67
+ 61,
68
+ 62,
69
+ 63,
70
+ 90,
71
+ 91,
72
+ 92,
73
+ 93,
74
+ 359,
75
+ 503,
76
+ 522,
77
+ 542,
78
+ 873,
79
+ 893,
80
+ 902,
81
+ 918,
82
+ 922,
83
+ 931,
84
+ 1350,
85
+ 1853,
86
+ 1982,
87
+ 2460,
88
+ 2627,
89
+ 3246,
90
+ 3253,
91
+ 3268,
92
+ 3536,
93
+ 3846,
94
+ 3961,
95
+ 4183,
96
+ 4667,
97
+ 6585,
98
+ 6647,
99
+ 7273,
100
+ 9061,
101
+ 9383,
102
+ 10428,
103
+ 10929,
104
+ 11938,
105
+ 12033,
106
+ 12331,
107
+ 12562,
108
+ 13793,
109
+ 14157,
110
+ 14635,
111
+ 15265,
112
+ 15618,
113
+ 16553,
114
+ 16604,
115
+ 18362,
116
+ 18956,
117
+ 20075,
118
+ 21675,
119
+ 22520,
120
+ 26130,
121
+ 26161,
122
+ 26435,
123
+ 28279,
124
+ 29464,
125
+ 31650,
126
+ 32302,
127
+ 32470,
128
+ 36865,
129
+ 42863,
130
+ 47425,
131
+ 49870,
132
+ 50254,
133
+ 50258,
134
+ 50358,
135
+ 50359,
136
+ 50360,
137
+ 50361,
138
+ 50362
139
+ ],
140
+ "torch_dtype": "float32",
141
+ "transformers_version": "4.27.0.dev0",
142
+ "use_cache": true,
143
+ "vocab_size": 51865
144
+ }
whisper-tiny/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ebd0e69e78190ffe1438491fa05cc1f5c1aa3a4c4db3bc1723adbb551ea2395
3
+ size 151061672
whisper-tiny/preprocessor_config.json ADDED
The diff for this file is too large to render. See raw diff
 
whisper-tiny/special_tokens_map.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|startoftranscript|>",
5
+ "<|en|>",
6
+ "<|zh|>",
7
+ "<|de|>",
8
+ "<|es|>",
9
+ "<|ru|>",
10
+ "<|ko|>",
11
+ "<|fr|>",
12
+ "<|ja|>",
13
+ "<|pt|>",
14
+ "<|tr|>",
15
+ "<|pl|>",
16
+ "<|ca|>",
17
+ "<|nl|>",
18
+ "<|ar|>",
19
+ "<|sv|>",
20
+ "<|it|>",
21
+ "<|id|>",
22
+ "<|hi|>",
23
+ "<|fi|>",
24
+ "<|vi|>",
25
+ "<|he|>",
26
+ "<|uk|>",
27
+ "<|el|>",
28
+ "<|ms|>",
29
+ "<|cs|>",
30
+ "<|ro|>",
31
+ "<|da|>",
32
+ "<|hu|>",
33
+ "<|ta|>",
34
+ "<|no|>",
35
+ "<|th|>",
36
+ "<|ur|>",
37
+ "<|hr|>",
38
+ "<|bg|>",
39
+ "<|lt|>",
40
+ "<|la|>",
41
+ "<|mi|>",
42
+ "<|ml|>",
43
+ "<|cy|>",
44
+ "<|sk|>",
45
+ "<|te|>",
46
+ "<|fa|>",
47
+ "<|lv|>",
48
+ "<|bn|>",
49
+ "<|sr|>",
50
+ "<|az|>",
51
+ "<|sl|>",
52
+ "<|kn|>",
53
+ "<|et|>",
54
+ "<|mk|>",
55
+ "<|br|>",
56
+ "<|eu|>",
57
+ "<|is|>",
58
+ "<|hy|>",
59
+ "<|ne|>",
60
+ "<|mn|>",
61
+ "<|bs|>",
62
+ "<|kk|>",
63
+ "<|sq|>",
64
+ "<|sw|>",
65
+ "<|gl|>",
66
+ "<|mr|>",
67
+ "<|pa|>",
68
+ "<|si|>",
69
+ "<|km|>",
70
+ "<|sn|>",
71
+ "<|yo|>",
72
+ "<|so|>",
73
+ "<|af|>",
74
+ "<|oc|>",
75
+ "<|ka|>",
76
+ "<|be|>",
77
+ "<|tg|>",
78
+ "<|sd|>",
79
+ "<|gu|>",
80
+ "<|am|>",
81
+ "<|yi|>",
82
+ "<|lo|>",
83
+ "<|uz|>",
84
+ "<|fo|>",
85
+ "<|ht|>",
86
+ "<|ps|>",
87
+ "<|tk|>",
88
+ "<|nn|>",
89
+ "<|mt|>",
90
+ "<|sa|>",
91
+ "<|lb|>",
92
+ "<|my|>",
93
+ "<|bo|>",
94
+ "<|tl|>",
95
+ "<|mg|>",
96
+ "<|as|>",
97
+ "<|tt|>",
98
+ "<|haw|>",
99
+ "<|ln|>",
100
+ "<|ha|>",
101
+ "<|ba|>",
102
+ "<|jw|>",
103
+ "<|su|>",
104
+ "<|translate|>",
105
+ "<|transcribe|>",
106
+ "<|startoflm|>",
107
+ "<|startofprev|>",
108
+ "<|nocaptions|>",
109
+ "<|notimestamps|>"
110
+ ],
111
+ "bos_token": {
112
+ "content": "<|endoftext|>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<|endoftext|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": {
126
+ "content": "<|endoftext|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ },
132
+ "unk_token": {
133
+ "content": "<|endoftext|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ }
139
+ }
whisper-tiny/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff