Automatic Speech Recognition
Transformers
German
Eval Results
Inference Endpoints
jimmymeister commited on
Commit
00d760c
·
1 Parent(s): 519b97e

feat: convert to ctranslate2

Browse files
Files changed (3) hide show
  1. config.json +220 -46
  2. model.bin +3 -0
  3. vocabulary.json +0 -0
config.json CHANGED
@@ -1,50 +1,224 @@
1
  {
2
- "_name_or_path": "flozi00/whisper-large-v3-turbo-german",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
- "apply_spec_augment": false,
6
- "architectures": [
7
- "WhisperForConditionalGeneration"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  ],
9
- "attention_dropout": 0.0,
10
- "begin_suppress_tokens": [
11
- 220,
12
- 50256
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ],
14
- "bos_token_id": 50257,
15
- "classifier_proj_size": 256,
16
- "d_model": 1280,
17
- "decoder_attention_heads": 20,
18
- "decoder_ffn_dim": 5120,
19
- "decoder_layerdrop": 0.0,
20
- "decoder_layers": 4,
21
- "decoder_start_token_id": 50258,
22
- "dropout": 0.0,
23
- "encoder_attention_heads": 20,
24
- "encoder_ffn_dim": 5120,
25
- "encoder_layerdrop": 0.0,
26
- "encoder_layers": 32,
27
- "eos_token_id": 50257,
28
- "forced_decoder_ids": null,
29
- "init_std": 0.02,
30
- "is_encoder_decoder": true,
31
- "mask_feature_length": 10,
32
- "mask_feature_min_masks": 0,
33
- "mask_feature_prob": 0.0,
34
- "mask_time_length": 10,
35
- "mask_time_min_masks": 2,
36
- "mask_time_prob": 0.05,
37
- "max_source_positions": 1500,
38
- "max_target_positions": 448,
39
- "median_filter_width": 7,
40
- "model_type": "whisper",
41
- "num_hidden_layers": 32,
42
- "num_mel_bins": 128,
43
- "pad_token_id": 50257,
44
- "scale_embedding": false,
45
- "torch_dtype": "bfloat16",
46
- "transformers_version": "4.45.1",
47
- "use_cache": true,
48
- "use_weighted_layer_sum": false,
49
- "vocab_size": 51866
50
  }
 
1
  {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 4
6
+ ],
7
+ [
8
+ 2,
9
+ 11
10
+ ],
11
+ [
12
+ 3,
13
+ 3
14
+ ],
15
+ [
16
+ 3,
17
+ 6
18
+ ],
19
+ [
20
+ 3,
21
+ 11
22
+ ],
23
+ [
24
+ 3,
25
+ 14
26
+ ]
27
  ],
28
+ "lang_ids": [
29
+ 50259,
30
+ 50260,
31
+ 50261,
32
+ 50262,
33
+ 50263,
34
+ 50264,
35
+ 50265,
36
+ 50266,
37
+ 50267,
38
+ 50268,
39
+ 50269,
40
+ 50270,
41
+ 50271,
42
+ 50272,
43
+ 50273,
44
+ 50274,
45
+ 50275,
46
+ 50276,
47
+ 50277,
48
+ 50278,
49
+ 50279,
50
+ 50280,
51
+ 50281,
52
+ 50282,
53
+ 50283,
54
+ 50284,
55
+ 50285,
56
+ 50286,
57
+ 50287,
58
+ 50288,
59
+ 50289,
60
+ 50290,
61
+ 50291,
62
+ 50292,
63
+ 50293,
64
+ 50294,
65
+ 50295,
66
+ 50296,
67
+ 50297,
68
+ 50298,
69
+ 50299,
70
+ 50300,
71
+ 50301,
72
+ 50302,
73
+ 50303,
74
+ 50304,
75
+ 50305,
76
+ 50306,
77
+ 50307,
78
+ 50308,
79
+ 50309,
80
+ 50310,
81
+ 50311,
82
+ 50312,
83
+ 50313,
84
+ 50314,
85
+ 50315,
86
+ 50316,
87
+ 50317,
88
+ 50318,
89
+ 50319,
90
+ 50320,
91
+ 50321,
92
+ 50322,
93
+ 50323,
94
+ 50324,
95
+ 50325,
96
+ 50326,
97
+ 50327,
98
+ 50328,
99
+ 50329,
100
+ 50330,
101
+ 50331,
102
+ 50332,
103
+ 50333,
104
+ 50334,
105
+ 50335,
106
+ 50336,
107
+ 50337,
108
+ 50338,
109
+ 50339,
110
+ 50340,
111
+ 50341,
112
+ 50342,
113
+ 50343,
114
+ 50344,
115
+ 50345,
116
+ 50346,
117
+ 50347,
118
+ 50348,
119
+ 50349,
120
+ 50350,
121
+ 50351,
122
+ 50352,
123
+ 50353,
124
+ 50354,
125
+ 50355,
126
+ 50356,
127
+ 50357,
128
+ 50358
129
+ ],
130
+ "suppress_ids": [
131
+ 1,
132
+ 2,
133
+ 7,
134
+ 8,
135
+ 9,
136
+ 10,
137
+ 14,
138
+ 25,
139
+ 26,
140
+ 27,
141
+ 28,
142
+ 29,
143
+ 31,
144
+ 58,
145
+ 59,
146
+ 60,
147
+ 61,
148
+ 62,
149
+ 63,
150
+ 90,
151
+ 91,
152
+ 92,
153
+ 93,
154
+ 359,
155
+ 503,
156
+ 522,
157
+ 542,
158
+ 873,
159
+ 893,
160
+ 902,
161
+ 918,
162
+ 922,
163
+ 931,
164
+ 1350,
165
+ 1853,
166
+ 1982,
167
+ 2460,
168
+ 2627,
169
+ 3246,
170
+ 3253,
171
+ 3268,
172
+ 3536,
173
+ 3846,
174
+ 3961,
175
+ 4183,
176
+ 4667,
177
+ 6585,
178
+ 6647,
179
+ 7273,
180
+ 9061,
181
+ 9383,
182
+ 10428,
183
+ 10929,
184
+ 11938,
185
+ 12033,
186
+ 12331,
187
+ 12562,
188
+ 13793,
189
+ 14157,
190
+ 14635,
191
+ 15265,
192
+ 15618,
193
+ 16553,
194
+ 16604,
195
+ 18362,
196
+ 18956,
197
+ 20075,
198
+ 21675,
199
+ 22520,
200
+ 26130,
201
+ 26161,
202
+ 26435,
203
+ 28279,
204
+ 29464,
205
+ 31650,
206
+ 32302,
207
+ 32470,
208
+ 36865,
209
+ 42863,
210
+ 47425,
211
+ 49870,
212
+ 50254,
213
+ 50258,
214
+ 50359,
215
+ 50360,
216
+ 50361,
217
+ 50362,
218
+ 50363
219
  ],
220
+ "suppress_ids_begin": [
221
+ 220,
222
+ 50257
223
+ ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
224
  }
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbf337ed600d7c58100c131943827350ae866dfabdfb4c0ae80ef44bfe6d6e2
3
+ size 1617884929
vocabulary.json ADDED
The diff for this file is too large to render. See raw diff