breco commited on
Commit
22bf9d6
1 Parent(s): 8ffd036

Model save

Browse files
Files changed (3) hide show
  1. README.md +84 -0
  2. generation_config.json +240 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: openai/whisper-tiny
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: whisper-tiny-1000-diverse-audios
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # whisper-tiny-1000-diverse-audios
18
+
19
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1835
22
+ - Wer: 42.9577
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 1e-05
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 16
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 25
50
+ - training_steps: 500
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
57
+ | 3.7684 | 0.4425 | 25 | 2.2485 | 135.5131 |
58
+ | 1.5347 | 0.8850 | 50 | 0.9286 | 75.5533 |
59
+ | 0.8425 | 1.3274 | 75 | 0.5561 | 56.4386 |
60
+ | 0.5722 | 1.7699 | 100 | 0.4103 | 43.4608 |
61
+ | 0.3867 | 2.2124 | 125 | 0.3423 | 40.5433 |
62
+ | 0.3107 | 2.6549 | 150 | 0.2967 | 51.0060 |
63
+ | 0.2931 | 3.0973 | 175 | 0.2656 | 78.8732 |
64
+ | 0.2031 | 3.5398 | 200 | 0.2421 | 57.8471 |
65
+ | 0.2004 | 3.9823 | 225 | 0.2305 | 51.8109 |
66
+ | 0.1254 | 4.4248 | 250 | 0.2198 | 22.4346 |
67
+ | 0.1332 | 4.8673 | 275 | 0.2070 | 22.2334 |
68
+ | 0.1089 | 5.3097 | 300 | 0.2049 | 51.4085 |
69
+ | 0.0627 | 5.7522 | 325 | 0.1988 | 28.5714 |
70
+ | 0.0959 | 6.1947 | 350 | 0.1948 | 31.6901 |
71
+ | 0.0794 | 6.6372 | 375 | 0.1910 | 28.8732 |
72
+ | 0.0696 | 7.0796 | 400 | 0.1879 | 43.5614 |
73
+ | 0.0458 | 7.5221 | 425 | 0.1861 | 43.4608 |
74
+ | 0.0524 | 7.9646 | 450 | 0.1841 | 53.5211 |
75
+ | 0.0453 | 8.4071 | 475 | 0.1832 | 40.4427 |
76
+ | 0.0485 | 8.8496 | 500 | 0.1835 | 42.9577 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.44.2
82
+ - Pytorch 2.4.1+cu121
83
+ - Datasets 3.0.0
84
+ - Tokenizers 0.19.1
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
+ "is_multilingual": true,
36
+ "lang_to_id": {
37
+ "<|af|>": 50327,
38
+ "<|am|>": 50334,
39
+ "<|ar|>": 50272,
40
+ "<|as|>": 50350,
41
+ "<|az|>": 50304,
42
+ "<|ba|>": 50355,
43
+ "<|be|>": 50330,
44
+ "<|bg|>": 50292,
45
+ "<|bn|>": 50302,
46
+ "<|bo|>": 50347,
47
+ "<|br|>": 50309,
48
+ "<|bs|>": 50315,
49
+ "<|ca|>": 50270,
50
+ "<|cs|>": 50283,
51
+ "<|cy|>": 50297,
52
+ "<|da|>": 50285,
53
+ "<|de|>": 50261,
54
+ "<|el|>": 50281,
55
+ "<|en|>": 50259,
56
+ "<|es|>": 50262,
57
+ "<|et|>": 50307,
58
+ "<|eu|>": 50310,
59
+ "<|fa|>": 50300,
60
+ "<|fi|>": 50277,
61
+ "<|fo|>": 50338,
62
+ "<|fr|>": 50265,
63
+ "<|gl|>": 50319,
64
+ "<|gu|>": 50333,
65
+ "<|haw|>": 50352,
66
+ "<|ha|>": 50354,
67
+ "<|he|>": 50279,
68
+ "<|hi|>": 50276,
69
+ "<|hr|>": 50291,
70
+ "<|ht|>": 50339,
71
+ "<|hu|>": 50286,
72
+ "<|hy|>": 50312,
73
+ "<|id|>": 50275,
74
+ "<|is|>": 50311,
75
+ "<|it|>": 50274,
76
+ "<|ja|>": 50266,
77
+ "<|jw|>": 50356,
78
+ "<|ka|>": 50329,
79
+ "<|kk|>": 50316,
80
+ "<|km|>": 50323,
81
+ "<|kn|>": 50306,
82
+ "<|ko|>": 50264,
83
+ "<|la|>": 50294,
84
+ "<|lb|>": 50345,
85
+ "<|ln|>": 50353,
86
+ "<|lo|>": 50336,
87
+ "<|lt|>": 50293,
88
+ "<|lv|>": 50301,
89
+ "<|mg|>": 50349,
90
+ "<|mi|>": 50295,
91
+ "<|mk|>": 50308,
92
+ "<|ml|>": 50296,
93
+ "<|mn|>": 50314,
94
+ "<|mr|>": 50320,
95
+ "<|ms|>": 50282,
96
+ "<|mt|>": 50343,
97
+ "<|my|>": 50346,
98
+ "<|ne|>": 50313,
99
+ "<|nl|>": 50271,
100
+ "<|nn|>": 50342,
101
+ "<|no|>": 50288,
102
+ "<|oc|>": 50328,
103
+ "<|pa|>": 50321,
104
+ "<|pl|>": 50269,
105
+ "<|ps|>": 50340,
106
+ "<|pt|>": 50267,
107
+ "<|ro|>": 50284,
108
+ "<|ru|>": 50263,
109
+ "<|sa|>": 50344,
110
+ "<|sd|>": 50332,
111
+ "<|si|>": 50322,
112
+ "<|sk|>": 50298,
113
+ "<|sl|>": 50305,
114
+ "<|sn|>": 50324,
115
+ "<|so|>": 50326,
116
+ "<|sq|>": 50317,
117
+ "<|sr|>": 50303,
118
+ "<|su|>": 50357,
119
+ "<|sv|>": 50273,
120
+ "<|sw|>": 50318,
121
+ "<|ta|>": 50287,
122
+ "<|te|>": 50299,
123
+ "<|tg|>": 50331,
124
+ "<|th|>": 50289,
125
+ "<|tk|>": 50341,
126
+ "<|tl|>": 50348,
127
+ "<|tr|>": 50268,
128
+ "<|tt|>": 50351,
129
+ "<|uk|>": 50280,
130
+ "<|ur|>": 50290,
131
+ "<|uz|>": 50337,
132
+ "<|vi|>": 50278,
133
+ "<|yi|>": 50335,
134
+ "<|yo|>": 50325,
135
+ "<|zh|>": 50260
136
+ },
137
+ "language": "spanish",
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": "transcribe",
235
+ "task_to_id": {
236
+ "transcribe": 50359,
237
+ "translate": 50358
238
+ },
239
+ "transformers_version": "4.44.2"
240
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e486991aa80d8572771a694f7e7888a536307bbd27fecab21e9529d9f7c66597
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52a497deff188f259ca45bf44aff4a8557fd8c8057527ce98e70958b4039028
3
  size 151061672