makhataei commited on
Commit
47054e3
1 Parent(s): 0d70375

End of training

Browse files
README.md ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - fa
4
+ license: apache-2.0
5
+ base_model: openai/whisper-small
6
+ tags:
7
+ - fa-asr
8
+ - generated_from_trainer
9
+ datasets:
10
+ - mozilla-foundation/common_voice_15_0
11
+ metrics:
12
+ - wer
13
+ model-index:
14
+ - name: Whisper Small Persian
15
+ results: []
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ # Whisper Small Persian
22
+
23
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 15.0 dataset.
24
+ It achieves the following results on the evaluation set:
25
+ - Loss: 0.9061
26
+ - Wer: 51.3701
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 1e-05
46
+ - train_batch_size: 14
47
+ - eval_batch_size: 10
48
+ - seed: 42
49
+ - gradient_accumulation_steps: 4
50
+ - total_train_batch_size: 56
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 50
54
+ - training_steps: 10000
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|
61
+ | 0.7495 | 0.39 | 100 | 0.8602 | 58.0774 |
62
+ | 0.3059 | 0.77 | 200 | 0.5538 | 55.2248 |
63
+ | 0.2002 | 1.16 | 300 | 0.5137 | 52.4615 |
64
+ | 0.1798 | 1.54 | 400 | 0.5103 | 51.6578 |
65
+ | 0.1678 | 1.93 | 500 | 0.4806 | 46.5512 |
66
+ | 0.0932 | 2.32 | 600 | 0.4936 | 47.4955 |
67
+ | 0.0944 | 2.7 | 700 | 0.5120 | 48.9160 |
68
+ | 0.0493 | 3.09 | 800 | 0.5198 | 48.2611 |
69
+ | 0.0506 | 3.47 | 900 | 0.5227 | 47.4128 |
70
+ | 0.0482 | 3.86 | 1000 | 0.5256 | 46.9498 |
71
+ | 0.0244 | 4.25 | 1100 | 0.5491 | 46.0849 |
72
+ | 0.0272 | 4.63 | 1200 | 0.5621 | 46.9167 |
73
+ | 0.0246 | 5.02 | 1300 | 0.5856 | 48.8036 |
74
+ | 0.0159 | 5.41 | 1400 | 0.6145 | 48.3041 |
75
+ | 0.0152 | 5.79 | 1500 | 0.6178 | 47.7568 |
76
+ | 0.008 | 6.18 | 1600 | 0.6191 | 48.0611 |
77
+ | 0.0077 | 6.56 | 1700 | 0.6309 | 46.3594 |
78
+ | 0.0097 | 6.95 | 1800 | 0.6272 | 47.9139 |
79
+ | 0.0056 | 7.34 | 1900 | 0.6594 | 46.5562 |
80
+ | 0.0049 | 7.72 | 2000 | 0.6581 | 47.5831 |
81
+ | 0.0042 | 8.11 | 2100 | 0.6953 | 48.0925 |
82
+ | 0.0038 | 8.49 | 2200 | 0.6857 | 48.3719 |
83
+ | 0.0033 | 8.88 | 2300 | 0.6983 | 49.6965 |
84
+ | 0.003 | 9.27 | 2400 | 0.7109 | 48.1173 |
85
+ | 0.0033 | 9.65 | 2500 | 0.6899 | 48.2363 |
86
+ | 0.0027 | 10.04 | 2600 | 0.7074 | 48.3405 |
87
+ | 0.0035 | 10.42 | 2700 | 0.7018 | 47.1003 |
88
+ | 0.0026 | 10.81 | 2800 | 0.7198 | 47.1251 |
89
+ | 0.0027 | 11.2 | 2900 | 0.7460 | 48.2760 |
90
+ | 0.0023 | 11.58 | 3000 | 0.7348 | 47.7154 |
91
+ | 0.0023 | 11.97 | 3100 | 0.7387 | 48.0081 |
92
+ | 0.0024 | 12.36 | 3200 | 0.7199 | 46.8687 |
93
+ | 0.0033 | 12.74 | 3300 | 0.7250 | 48.6895 |
94
+ | 0.0017 | 13.13 | 3400 | 0.7242 | 49.0450 |
95
+ | 0.0016 | 13.51 | 3500 | 0.7359 | 48.7010 |
96
+ | 0.0022 | 13.9 | 3600 | 0.7220 | 48.1371 |
97
+ | 0.0016 | 14.29 | 3700 | 0.7431 | 46.7563 |
98
+ | 0.0012 | 14.67 | 3800 | 0.7564 | 47.0143 |
99
+ | 0.0014 | 15.06 | 3900 | 0.7770 | 47.0242 |
100
+ | 0.0008 | 15.44 | 4000 | 0.8116 | 48.4695 |
101
+ | 0.0015 | 15.83 | 4100 | 0.7623 | 48.0925 |
102
+ | 0.002 | 16.22 | 4200 | 0.7699 | 47.7254 |
103
+ | 0.001 | 16.6 | 4300 | 0.7631 | 46.8754 |
104
+ | 0.0009 | 16.99 | 4400 | 0.7591 | 48.4166 |
105
+ | 0.0008 | 17.37 | 4500 | 0.7797 | 47.1780 |
106
+ | 0.0008 | 17.76 | 4600 | 0.7851 | 46.7662 |
107
+ | 0.0007 | 18.15 | 4700 | 0.7897 | 48.3157 |
108
+ | 0.0006 | 18.53 | 4800 | 0.7760 | 48.8069 |
109
+ | 0.0016 | 18.92 | 4900 | 0.7763 | 47.9718 |
110
+ | 0.0009 | 19.31 | 5000 | 0.8151 | 48.1586 |
111
+ | 0.0004 | 19.69 | 5100 | 0.7967 | 47.5567 |
112
+ | 0.0007 | 20.08 | 5200 | 0.8094 | 46.7861 |
113
+ | 0.001 | 20.46 | 5300 | 0.8206 | 47.1565 |
114
+ | 0.0008 | 20.85 | 5400 | 0.8015 | 47.6212 |
115
+ | 0.0004 | 21.24 | 5500 | 0.8104 | 47.2210 |
116
+ | 0.0003 | 21.62 | 5600 | 0.8020 | 48.1454 |
117
+ | 0.0004 | 22.01 | 5700 | 0.8295 | 46.9415 |
118
+ | 0.0004 | 22.39 | 5800 | 0.8228 | 46.6108 |
119
+ | 0.0005 | 22.78 | 5900 | 0.8386 | 48.0974 |
120
+ | 0.0007 | 23.17 | 6000 | 0.8415 | 46.6141 |
121
+ | 0.0003 | 23.55 | 6100 | 0.8283 | 46.3263 |
122
+ | 0.0005 | 23.94 | 6200 | 0.8342 | 45.9658 |
123
+ | 0.0002 | 24.32 | 6300 | 0.8379 | 46.6240 |
124
+ | 0.0005 | 24.71 | 6400 | 0.8371 | 48.0809 |
125
+ | 0.0002 | 25.1 | 6500 | 0.8258 | 47.5864 |
126
+ | 0.0001 | 25.48 | 6600 | 0.8396 | 47.2607 |
127
+ | 0.0002 | 25.87 | 6700 | 0.8491 | 47.5435 |
128
+ | 0.0005 | 26.25 | 6800 | 0.8444 | 48.9937 |
129
+ | 0.0001 | 26.64 | 6900 | 0.8540 | 48.0544 |
130
+ | 0.0001 | 27.03 | 7000 | 0.8605 | 48.5390 |
131
+ | 0.0001 | 27.41 | 7100 | 0.8613 | 48.9226 |
132
+ | 0.0001 | 27.8 | 7200 | 0.8673 | 48.9491 |
133
+ | 0.0001 | 28.19 | 7300 | 0.8688 | 48.7936 |
134
+ | 0.0001 | 28.57 | 7400 | 0.8711 | 48.8350 |
135
+ | 0.0001 | 28.96 | 7500 | 0.8728 | 48.8581 |
136
+ | 0.0001 | 29.34 | 7600 | 0.8736 | 49.8454 |
137
+ | 0.0001 | 29.73 | 7700 | 0.8759 | 49.9248 |
138
+ | 0.0001 | 30.12 | 7800 | 0.8786 | 49.6932 |
139
+ | 0.0001 | 30.5 | 7900 | 0.8809 | 49.7429 |
140
+ | 0.0001 | 30.89 | 8000 | 0.8826 | 49.9132 |
141
+ | 0.0001 | 31.27 | 8100 | 0.8840 | 50.4506 |
142
+ | 0.0001 | 31.66 | 8200 | 0.8859 | 50.2919 |
143
+ | 0.0001 | 32.05 | 8300 | 0.8888 | 50.5532 |
144
+ | 0.0001 | 32.43 | 8400 | 0.8924 | 50.6491 |
145
+ | 0.0001 | 32.82 | 8500 | 0.8928 | 50.9997 |
146
+ | 0.0001 | 33.2 | 8600 | 0.8920 | 51.3188 |
147
+ | 0.0001 | 33.59 | 8700 | 0.8946 | 51.1419 |
148
+ | 0.0001 | 33.98 | 8800 | 0.8956 | 51.1551 |
149
+ | 0.0001 | 34.36 | 8900 | 0.8988 | 50.7483 |
150
+ | 0.0001 | 34.75 | 9000 | 0.9003 | 50.8889 |
151
+ | 0.0001 | 35.14 | 9100 | 0.9011 | 50.9302 |
152
+ | 0.0001 | 35.52 | 9200 | 0.9020 | 50.9533 |
153
+ | 0.0001 | 35.91 | 9300 | 0.9019 | 51.5603 |
154
+ | 0.0001 | 36.29 | 9400 | 0.9033 | 51.6479 |
155
+ | 0.0001 | 36.68 | 9500 | 0.9040 | 51.6810 |
156
+ | 0.0001 | 37.07 | 9600 | 0.9049 | 51.6744 |
157
+ | 0.0001 | 37.45 | 9700 | 0.9053 | 51.6429 |
158
+ | 0.0001 | 37.84 | 9800 | 0.9057 | 51.5966 |
159
+ | 0.0001 | 38.22 | 9900 | 0.9060 | 51.7372 |
160
+ | 0.0001 | 38.61 | 10000 | 0.9061 | 51.3701 |
161
+
162
+
163
+ ### Framework versions
164
+
165
+ - Transformers 4.35.0
166
+ - Pytorch 2.0.1+cu117
167
+ - Datasets 2.14.6
168
+ - Tokenizers 0.14.1
generation_config.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
42
+ ]
43
+ ],
44
+ "begin_suppress_tokens": [
45
+ 220,
46
+ 50257
47
+ ],
48
+ "bos_token_id": 50257,
49
+ "decoder_start_token_id": 50258,
50
+ "eos_token_id": 50257,
51
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|zh|>": 50260
162
+ },
163
+ "max_initial_timestamp_index": 1,
164
+ "max_length": 448,
165
+ "no_timestamps_token_id": 50363,
166
+ "pad_token_id": 50257,
167
+ "return_timestamps": false,
168
+ "suppress_tokens": [
169
+ 1,
170
+ 2,
171
+ 7,
172
+ 8,
173
+ 9,
174
+ 10,
175
+ 14,
176
+ 25,
177
+ 26,
178
+ 27,
179
+ 28,
180
+ 29,
181
+ 31,
182
+ 58,
183
+ 59,
184
+ 60,
185
+ 61,
186
+ 62,
187
+ 63,
188
+ 90,
189
+ 91,
190
+ 92,
191
+ 93,
192
+ 359,
193
+ 503,
194
+ 522,
195
+ 542,
196
+ 873,
197
+ 893,
198
+ 902,
199
+ 918,
200
+ 922,
201
+ 931,
202
+ 1350,
203
+ 1853,
204
+ 1982,
205
+ 2460,
206
+ 2627,
207
+ 3246,
208
+ 3253,
209
+ 3268,
210
+ 3536,
211
+ 3846,
212
+ 3961,
213
+ 4183,
214
+ 4667,
215
+ 6585,
216
+ 6647,
217
+ 7273,
218
+ 9061,
219
+ 9383,
220
+ 10428,
221
+ 10929,
222
+ 11938,
223
+ 12033,
224
+ 12331,
225
+ 12562,
226
+ 13793,
227
+ 14157,
228
+ 14635,
229
+ 15265,
230
+ 15618,
231
+ 16553,
232
+ 16604,
233
+ 18362,
234
+ 18956,
235
+ 20075,
236
+ 21675,
237
+ 22520,
238
+ 26130,
239
+ 26161,
240
+ 26435,
241
+ 28279,
242
+ 29464,
243
+ 31650,
244
+ 32302,
245
+ 32470,
246
+ 36865,
247
+ 42863,
248
+ 47425,
249
+ 49870,
250
+ 50254,
251
+ 50258,
252
+ 50358,
253
+ 50359,
254
+ 50360,
255
+ 50361,
256
+ 50362
257
+ ],
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "transformers_version": "4.35.0"
263
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9379b3c154d906dbb3780c3bc0a0fdd4e8d06f41abb8ceb45f3fba0c6088646c
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24d169054a14f21115d4e61fc3961312bda1f8d71eb31e5d9172f09bdb547b81
3
  size 966995080
runs/Nov12_10-21-47_Software-AI/events.out.tfevents.1699771911.Software-AI.3561608.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0a3d38a319d2feedc9fab60215a58f05ad5e615403b72429380e4bf1f8028cf
3
- size 98777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9257960368d89931c4d2f20293d361fd35fb7070cfa520ac0b44f9d0abadd5b6
3
+ size 100077