Hugging Face's logo

danielrosehill
/
daniel_whisper_finetune_tiny_v2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files
xet
 Metrics Community
danielrosehill commited on
Commit
8e127cd
·
verified ·
1 Parent(s): 2fb091d

Training in progress, step 100

Browse files
Files changed (6) hide show
  1. config.json +47 -0
  2. generation_config.json +240 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +15 -0
  5. runs/Nov20_23-09-53_modal/events.out.tfevents.1763680194.modal.2.0 +3 -0
  6. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": null,
10
+ "bos_token_id": 50257,
11
+ "classifier_proj_size": 256,
12
+ "d_model": 384,
13
+ "decoder_attention_heads": 6,
14
+ "decoder_ffn_dim": 1536,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 4,
17
+ "decoder_start_token_id": 50258,
18
+ "dropout": 0.0,
19
+ "dtype": "float32",
20
+ "encoder_attention_heads": 6,
21
+ "encoder_ffn_dim": 1536,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 4,
24
+ "eos_token_id": 50257,
25
+ "forced_decoder_ids": null,
26
+ "init_std": 0.02,
27
+ "is_encoder_decoder": true,
28
+ "mask_feature_length": 10,
29
+ "mask_feature_min_masks": 0,
30
+ "mask_feature_prob": 0.0,
31
+ "mask_time_length": 10,
32
+ "mask_time_min_masks": 2,
33
+ "mask_time_prob": 0.05,
34
+ "max_length": null,
35
+ "max_source_positions": 1500,
36
+ "max_target_positions": 448,
37
+ "median_filter_width": 7,
38
+ "model_type": "whisper",
39
+ "num_hidden_layers": 4,
40
+ "num_mel_bins": 80,
41
+ "pad_token_id": 50257,
42
+ "scale_embedding": false,
43
+ "transformers_version": "4.57.1",
44
+ "use_cache": false,
45
+ "use_weighted_layer_sum": false,
46
+ "vocab_size": 51865
47
+ }
generation_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "forced_decoder_ids": null,
36
+ "is_multilingual": true,
37
+ "lang_to_id": {
38
+ "<|af|>": 50327,
39
+ "<|am|>": 50334,
40
+ "<|ar|>": 50272,
41
+ "<|as|>": 50350,
42
+ "<|az|>": 50304,
43
+ "<|ba|>": 50355,
44
+ "<|be|>": 50330,
45
+ "<|bg|>": 50292,
46
+ "<|bn|>": 50302,
47
+ "<|bo|>": 50347,
48
+ "<|br|>": 50309,
49
+ "<|bs|>": 50315,
50
+ "<|ca|>": 50270,
51
+ "<|cs|>": 50283,
52
+ "<|cy|>": 50297,
53
+ "<|da|>": 50285,
54
+ "<|de|>": 50261,
55
+ "<|el|>": 50281,
56
+ "<|en|>": 50259,
57
+ "<|es|>": 50262,
58
+ "<|et|>": 50307,
59
+ "<|eu|>": 50310,
60
+ "<|fa|>": 50300,
61
+ "<|fi|>": 50277,
62
+ "<|fo|>": 50338,
63
+ "<|fr|>": 50265,
64
+ "<|gl|>": 50319,
65
+ "<|gu|>": 50333,
66
+ "<|haw|>": 50352,
67
+ "<|ha|>": 50354,
68
+ "<|he|>": 50279,
69
+ "<|hi|>": 50276,
70
+ "<|hr|>": 50291,
71
+ "<|ht|>": 50339,
72
+ "<|hu|>": 50286,
73
+ "<|hy|>": 50312,
74
+ "<|id|>": 50275,
75
+ "<|is|>": 50311,
76
+ "<|it|>": 50274,
77
+ "<|ja|>": 50266,
78
+ "<|jw|>": 50356,
79
+ "<|ka|>": 50329,
80
+ "<|kk|>": 50316,
81
+ "<|km|>": 50323,
82
+ "<|kn|>": 50306,
83
+ "<|ko|>": 50264,
84
+ "<|la|>": 50294,
85
+ "<|lb|>": 50345,
86
+ "<|ln|>": 50353,
87
+ "<|lo|>": 50336,
88
+ "<|lt|>": 50293,
89
+ "<|lv|>": 50301,
90
+ "<|mg|>": 50349,
91
+ "<|mi|>": 50295,
92
+ "<|mk|>": 50308,
93
+ "<|ml|>": 50296,
94
+ "<|mn|>": 50314,
95
+ "<|mr|>": 50320,
96
+ "<|ms|>": 50282,
97
+ "<|mt|>": 50343,
98
+ "<|my|>": 50346,
99
+ "<|ne|>": 50313,
100
+ "<|nl|>": 50271,
101
+ "<|nn|>": 50342,
102
+ "<|no|>": 50288,
103
+ "<|oc|>": 50328,
104
+ "<|pa|>": 50321,
105
+ "<|pl|>": 50269,
106
+ "<|ps|>": 50340,
107
+ "<|pt|>": 50267,
108
+ "<|ro|>": 50284,
109
+ "<|ru|>": 50263,
110
+ "<|sa|>": 50344,
111
+ "<|sd|>": 50332,
112
+ "<|si|>": 50322,
113
+ "<|sk|>": 50298,
114
+ "<|sl|>": 50305,
115
+ "<|sn|>": 50324,
116
+ "<|so|>": 50326,
117
+ "<|sq|>": 50317,
118
+ "<|sr|>": 50303,
119
+ "<|su|>": 50357,
120
+ "<|sv|>": 50273,
121
+ "<|sw|>": 50318,
122
+ "<|ta|>": 50287,
123
+ "<|te|>": 50299,
124
+ "<|tg|>": 50331,
125
+ "<|th|>": 50289,
126
+ "<|tk|>": 50341,
127
+ "<|tl|>": 50348,
128
+ "<|tr|>": 50268,
129
+ "<|tt|>": 50351,
130
+ "<|uk|>": 50280,
131
+ "<|ur|>": 50290,
132
+ "<|uz|>": 50337,
133
+ "<|vi|>": 50278,
134
+ "<|yi|>": 50335,
135
+ "<|yo|>": 50325,
136
+ "<|zh|>": 50260
137
+ },
138
+ "max_initial_timestamp_index": 50,
139
+ "max_length": 448,
140
+ "no_timestamps_token_id": 50363,
141
+ "pad_token_id": 50257,
142
+ "prev_sot_token_id": 50361,
143
+ "return_timestamps": false,
144
+ "suppress_tokens": [
145
+ 1,
146
+ 2,
147
+ 7,
148
+ 8,
149
+ 9,
150
+ 10,
151
+ 14,
152
+ 25,
153
+ 26,
154
+ 27,
155
+ 28,
156
+ 29,
157
+ 31,
158
+ 58,
159
+ 59,
160
+ 60,
161
+ 61,
162
+ 62,
163
+ 63,
164
+ 90,
165
+ 91,
166
+ 92,
167
+ 93,
168
+ 359,
169
+ 503,
170
+ 522,
171
+ 542,
172
+ 873,
173
+ 893,
174
+ 902,
175
+ 918,
176
+ 922,
177
+ 931,
178
+ 1350,
179
+ 1853,
180
+ 1982,
181
+ 2460,
182
+ 2627,
183
+ 3246,
184
+ 3253,
185
+ 3268,
186
+ 3536,
187
+ 3846,
188
+ 3961,
189
+ 4183,
190
+ 4667,
191
+ 6585,
192
+ 6647,
193
+ 7273,
194
+ 9061,
195
+ 9383,
196
+ 10428,
197
+ 10929,
198
+ 11938,
199
+ 12033,
200
+ 12331,
201
+ 12562,
202
+ 13793,
203
+ 14157,
204
+ 14635,
205
+ 15265,
206
+ 15618,
207
+ 16553,
208
+ 16604,
209
+ 18362,
210
+ 18956,
211
+ 20075,
212
+ 21675,
213
+ 22520,
214
+ 26130,
215
+ 26161,
216
+ 26435,
217
+ 28279,
218
+ 29464,
219
+ 31650,
220
+ 32302,
221
+ 32470,
222
+ 36865,
223
+ 42863,
224
+ 47425,
225
+ 49870,
226
+ 50254,
227
+ 50258,
228
+ 50358,
229
+ 50359,
230
+ 50360,
231
+ 50361,
232
+ 50362
233
+ ],
234
+ "task_to_id": {
235
+ "transcribe": 50359,
236
+ "translate": 50358
237
+ },
238
+ "transformers_version": "4.57.1",
239
+ "use_cache": false
240
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb40c5f0bba2338cf0dbe5b87975012ffe0a8f880ab47c0ab9bb952385b27f50
3
+ size 151061672
preprocessor_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "processor_class": "WhisperProcessor",
13
+ "return_attention_mask": false,
14
+ "sampling_rate": 16000
15
+ }
runs/Nov20_23-09-53_modal/events.out.tfevents.1763680194.modal.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3cbf6a5341ccf52140f4e4ff2f03d54fb6df116f03328f5121d96d34acf6c1
3
+ size 8111
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6f8a1a2d04b629d177c8cf9fd2c7b12b19dab967dab59c599ed76b25f05415
3
+ size 6033