Hugging Face's logo

makhataei
/
Whisper-Small-Common-Voice

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Persian
whisper
fa-asr
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
makhataei commited on
Commit
e8c5851
•
1 Parent(s): d98d5d2

End of training

Browse files
Files changed (4) hide show
  1. README.md +109 -110
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Dec12_17-38-06_Software-AI/events.out.tfevents.1702390089.Software-AI.6644.0 +2 -2
README.md CHANGED
@@ -22,8 +22,8 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  This model is a fine-tuned version of [makhataei/Whisper-Small-Common-Voice](https://huggingface.co/makhataei/Whisper-Small-Common-Voice) on the Common Voice 15.0 dataset.
24
  It achieves the following results on the evaluation set:
25
- - Loss: 0.8843
26
- - Wer: 48.6448
27
 
28
  ## Model description
29
 
@@ -42,127 +42,126 @@ More information needed
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
- | 0.1801 | 0.39 | 100 | 0.4976 | 49.1260 |
62
- | 0.1597 | 0.79 | 200 | 0.4624 | 46.7497 |
63
- | 0.0776 | 1.18 | 300 | 0.4794 | 43.1761 |
64
- | 0.083 | 1.57 | 400 | 0.4823 | 43.8028 |
65
- | 0.0786 | 1.96 | 500 | 0.4883 | 44.3915 |
66
- | 0.0331 | 2.36 | 600 | 0.5385 | 46.2437 |
67
- | 0.0353 | 2.75 | 700 | 0.5605 | 44.9439 |
68
- | 0.0139 | 3.14 | 800 | 0.5941 | 45.2812 |
69
- | 0.0152 | 3.53 | 900 | 0.5978 | 49.2930 |
70
- | 0.0155 | 3.93 | 1000 | 0.6114 | 49.9777 |
71
- | 0.0063 | 4.32 | 1100 | 0.6467 | 50.0041 |
72
- | 0.0079 | 4.71 | 1200 | 0.6383 | 48.0875 |
73
- | 0.0046 | 5.1 | 1300 | 0.6500 | 45.4995 |
74
- | 0.0042 | 5.5 | 1400 | 0.6476 | 47.4492 |
75
- | 0.0052 | 5.89 | 1500 | 0.6685 | 52.1870 |
76
- | 0.0023 | 6.28 | 1600 | 0.6794 | 44.2510 |
77
- | 0.0032 | 6.67 | 1700 | 0.6724 | 45.7161 |
78
- | 0.0021 | 7.07 | 1800 | 0.6820 | 47.6013 |
79
- | 0.0015 | 7.46 | 1900 | 0.6925 | 46.6720 |
80
- | 0.0024 | 7.85 | 2000 | 0.7104 | 50.2902 |
81
- | 0.0029 | 8.24 | 2100 | 0.6837 | 46.4173 |
82
- | 0.0016 | 8.64 | 2200 | 0.7191 | 46.0088 |
83
- | 0.0017 | 9.03 | 2300 | 0.7105 | 47.5964 |
84
- | 0.0014 | 9.42 | 2400 | 0.7293 | 44.7603 |
85
- | 0.0018 | 9.81 | 2500 | 0.7365 | 49.8966 |
86
- | 0.0008 | 10.21 | 2600 | 0.7378 | 47.4740 |
87
- | 0.0016 | 10.6 | 2700 | 0.7303 | 45.9691 |
88
- | 0.0011 | 10.99 | 2800 | 0.7330 | 47.7254 |
89
- | 0.0014 | 11.38 | 2900 | 0.7448 | 44.8579 |
90
- | 0.0013 | 11.78 | 3000 | 0.7471 | 46.5116 |
91
- | 0.0015 | 12.17 | 3100 | 0.7513 | 47.5699 |
92
- | 0.0014 | 12.56 | 3200 | 0.7380 | 46.4008 |
93
- | 0.0015 | 12.95 | 3300 | 0.7520 | 45.9658 |
94
- | 0.0009 | 13.35 | 3400 | 0.7482 | 49.2269 |
95
- | 0.0021 | 13.74 | 3500 | 0.7619 | 47.1234 |
96
- | 0.0013 | 14.13 | 3600 | 0.7453 | 49.3956 |
97
- | 0.001 | 14.52 | 3700 | 0.7582 | 47.6741 |
98
- | 0.0009 | 14.92 | 3800 | 0.7637 | 46.9713 |
99
- | 0.0014 | 15.31 | 3900 | 0.7722 | 47.2706 |
100
- | 0.001 | 15.7 | 4000 | 0.7692 | 46.9663 |
101
- | 0.0003 | 16.09 | 4100 | 0.7744 | 47.1730 |
102
- | 0.0004 | 16.49 | 4200 | 0.7842 | 47.3351 |
103
- | 0.0003 | 16.88 | 4300 | 0.7784 | 47.0771 |
104
- | 0.0002 | 17.27 | 4400 | 0.7879 | 45.7641 |
105
- | 0.0005 | 17.66 | 4500 | 0.7965 | 50.0240 |
106
- | 0.0004 | 18.06 | 4600 | 0.8001 | 48.4381 |
107
- | 0.0002 | 18.45 | 4700 | 0.8016 | 49.0037 |
108
- | 0.0002 | 18.84 | 4800 | 0.8066 | 50.0868 |
109
- | 0.0009 | 19.23 | 4900 | 0.8021 | 47.2276 |
110
- | 0.0005 | 19.63 | 5000 | 0.8162 | 47.3500 |
111
- | 0.0003 | 20.02 | 5100 | 0.8091 | 48.7225 |
112
- | 0.0003 | 20.41 | 5200 | 0.8060 | 51.5024 |
113
- | 0.0003 | 20.8 | 5300 | 0.8220 | 51.4875 |
114
- | 0.0003 | 21.2 | 5400 | 0.8098 | 45.8617 |
115
- | 0.0003 | 21.59 | 5500 | 0.8132 | 44.8711 |
116
- | 0.0009 | 21.98 | 5600 | 0.8006 | 45.3937 |
117
- | 0.0003 | 22.37 | 5700 | 0.8008 | 45.6186 |
118
- | 0.0002 | 22.77 | 5800 | 0.8081 | 46.3247 |
119
- | 0.0002 | 23.16 | 5900 | 0.8082 | 46.1279 |
120
- | 0.0002 | 23.55 | 6000 | 0.8238 | 46.1775 |
121
- | 0.0005 | 23.95 | 6100 | 0.8119 | 49.9727 |
122
- | 0.0002 | 24.34 | 6200 | 0.8315 | 49.0863 |
123
- | 0.0001 | 24.73 | 6300 | 0.8224 | 47.2243 |
124
- | 0.0001 | 25.12 | 6400 | 0.8259 | 47.1681 |
125
- | 0.0001 | 25.52 | 6500 | 0.8219 | 48.5737 |
126
- | 0.0002 | 25.91 | 6600 | 0.8400 | 48.9077 |
127
- | 0.0005 | 26.3 | 6700 | 0.8319 | 47.5567 |
128
- | 0.0001 | 26.69 | 6800 | 0.8394 | 50.2357 |
129
- | 0.0001 | 27.09 | 6900 | 0.8480 | 48.4629 |
130
- | 0.0001 | 27.48 | 7000 | 0.8498 | 47.1151 |
131
- | 0.0002 | 27.87 | 7100 | 0.8342 | 48.9243 |
132
- | 0.0003 | 28.26 | 7200 | 0.8184 | 47.3731 |
133
- | 0.0001 | 28.66 | 7300 | 0.8278 | 47.9288 |
134
- | 0.0002 | 29.05 | 7400 | 0.8439 | 47.8610 |
135
- | 0.0001 | 29.44 | 7500 | 0.8461 | 49.9463 |
136
- | 0.0001 | 29.83 | 7600 | 0.8449 | 48.4861 |
137
- | 0.0001 | 30.23 | 7700 | 0.8512 | 49.0003 |
138
- | 0.0001 | 30.62 | 7800 | 0.8555 | 48.2777 |
139
- | 0.0001 | 31.01 | 7900 | 0.8543 | 48.6795 |
140
- | 0.0001 | 31.4 | 8000 | 0.8566 | 48.7655 |
141
- | 0.0001 | 31.8 | 8100 | 0.8605 | 48.6779 |
142
- | 0.0 | 32.19 | 8200 | 0.8634 | 49.3691 |
143
- | 0.0 | 32.58 | 8300 | 0.8663 | 50.0438 |
144
- | 0.0 | 32.97 | 8400 | 0.8685 | 49.7280 |
145
- | 0.0 | 33.37 | 8500 | 0.8704 | 49.1641 |
146
- | 0.0 | 33.76 | 8600 | 0.8724 | 48.8416 |
147
- | 0.0 | 34.15 | 8700 | 0.8736 | 49.2286 |
148
- | 0.0 | 34.54 | 8800 | 0.8755 | 48.6134 |
149
- | 0.0 | 34.94 | 8900 | 0.8767 | 48.9259 |
150
- | 0.0 | 35.33 | 9000 | 0.8778 | 48.9805 |
151
- | 0.0 | 35.72 | 9100 | 0.8791 | 49.3212 |
152
- | 0.0 | 36.11 | 9200 | 0.8801 | 49.3724 |
153
- | 0.0 | 36.51 | 9300 | 0.8813 | 49.4336 |
154
- | 0.0 | 36.9 | 9400 | 0.8819 | 49.1045 |
155
- | 0.0 | 37.29 | 9500 | 0.8826 | 49.2633 |
156
- | 0.0 | 37.68 | 9600 | 0.8832 | 49.4237 |
157
- | 0.0 | 38.08 | 9700 | 0.8837 | 48.6316 |
158
- | 0.0 | 38.47 | 9800 | 0.8841 | 48.6465 |
159
- | 0.0 | 38.86 | 9900 | 0.8842 | 48.9342 |
160
- | 0.0 | 39.25 | 10000 | 0.8843 | 48.6448 |
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
 
22
 
23
  This model is a fine-tuned version of [makhataei/Whisper-Small-Common-Voice](https://huggingface.co/makhataei/Whisper-Small-Common-Voice) on the Common Voice 15.0 dataset.
24
  It achieves the following results on the evaluation set:
25
+ - Loss: 0.9637
26
+ - Wer: 53.0122
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 1e-06
46
+ - train_batch_size: 10
47
  - eval_batch_size: 10
48
  - seed: 42
49
  - gradient_accumulation_steps: 4
50
+ - total_train_batch_size: 40
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 500
54
  - training_steps: 10000
 
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer |
59
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|
60
+ | 0.0003 | 0.14 | 100 | 0.8127 | 50.1960 |
61
+ | 0.0003 | 0.28 | 200 | 0.8106 | 50.8591 |
62
+ | 0.0003 | 0.42 | 300 | 0.8138 | 50.2935 |
63
+ | 0.0005 | 0.56 | 400 | 0.8216 | 51.2345 |
64
+ | 0.0003 | 0.7 | 500 | 0.8295 | 50.0918 |
65
+ | 0.0003 | 0.83 | 600 | 0.8331 | 53.4124 |
66
+ | 0.0003 | 0.97 | 700 | 0.8269 | 54.9288 |
67
+ | 0.0003 | 1.11 | 800 | 0.8295 | 51.0178 |
68
+ | 0.0005 | 1.25 | 900 | 0.8341 | 50.1149 |
69
+ | 0.0007 | 1.39 | 1000 | 0.8423 | 51.9819 |
70
+ | 0.0005 | 1.53 | 1100 | 0.8324 | 52.3706 |
71
+ | 0.0003 | 1.67 | 1200 | 0.8411 | 51.8662 |
72
+ | 0.0002 | 1.81 | 1300 | 0.8545 | 52.8402 |
73
+ | 0.0004 | 1.95 | 1400 | 0.8619 | 54.0242 |
74
+ | 0.0002 | 2.09 | 1500 | 0.8556 | 54.8296 |
75
+ | 0.0004 | 2.23 | 1600 | 0.8291 | 53.9581 |
76
+ | 0.0003 | 2.36 | 1700 | 0.8633 | 51.2047 |
77
+ | 0.0003 | 2.5 | 1800 | 0.8557 | 53.7249 |
78
+ | 0.0005 | 2.64 | 1900 | 0.8551 | 51.7190 |
79
+ | 0.0003 | 2.78 | 2000 | 0.8418 | 52.9030 |
80
+ | 0.0002 | 2.92 | 2100 | 0.8522 | 50.9467 |
81
+ | 0.0002 | 3.06 | 2200 | 0.8798 | 51.2047 |
82
+ | 0.0003 | 3.2 | 2300 | 0.8545 | 51.4395 |
83
+ | 0.0002 | 3.34 | 2400 | 0.8633 | 51.0212 |
84
+ | 0.0007 | 3.48 | 2500 | 0.8644 | 53.8440 |
85
+ | 0.0002 | 3.62 | 2600 | 0.8598 | 52.5029 |
86
+ | 0.0002 | 3.76 | 2700 | 0.8578 | 52.0679 |
87
+ | 0.0002 | 3.89 | 2800 | 0.8672 | 52.1027 |
88
+ | 0.0001 | 4.03 | 2900 | 0.8655 | 52.3706 |
89
+ | 0.0001 | 4.17 | 3000 | 0.8741 | 52.2350 |
90
+ | 0.0001 | 4.31 | 3100 | 0.8716 | 53.0056 |
91
+ | 0.0001 | 4.45 | 3200 | 0.8758 | 51.0327 |
92
+ | 0.0005 | 4.59 | 3300 | 0.8636 | 51.8662 |
93
+ | 0.0001 | 4.73 | 3400 | 0.8725 | 51.0807 |
94
+ | 0.0001 | 4.87 | 3500 | 0.8781 | 51.1700 |
95
+ | 0.0001 | 5.01 | 3600 | 0.8806 | 50.7450 |
96
+ | 0.0001 | 5.15 | 3700 | 0.8835 | 50.6210 |
97
+ | 0.0001 | 5.29 | 3800 | 0.8852 | 51.1121 |
98
+ | 0.0001 | 5.42 | 3900 | 0.8874 | 51.1700 |
99
+ | 0.0001 | 5.56 | 4000 | 0.8894 | 51.3998 |
100
+ | 0.0002 | 5.7 | 4100 | 0.8899 | 51.4246 |
101
+ | 0.0001 | 5.84 | 4200 | 0.8927 | 51.6992 |
102
+ | 0.0001 | 5.98 | 4300 | 0.8933 | 51.8993 |
103
+ | 0.0001 | 6.12 | 4400 | 0.8966 | 51.7835 |
104
+ | 0.0001 | 6.26 | 4500 | 0.8980 | 51.8381 |
105
+ | 0.0001 | 6.4 | 4600 | 0.8973 | 51.7107 |
106
+ | 0.0001 | 6.54 | 4700 | 0.9008 | 51.5553 |
107
+ | 0.0001 | 6.68 | 4800 | 0.9029 | 51.1220 |
108
+ | 0.0001 | 6.82 | 4900 | 0.9030 | 51.3221 |
109
+ | 0.0001 | 6.95 | 5000 | 0.9039 | 52.1605 |
110
+ | 0.0001 | 7.09 | 5100 | 0.9084 | 52.1440 |
111
+ | 0.0001 | 7.23 | 5200 | 0.9106 | 51.9505 |
112
+ | 0.0001 | 7.37 | 5300 | 0.9117 | 52.6219 |
113
+ | 0.0001 | 7.51 | 5400 | 0.9133 | 52.4830 |
114
+ | 0.0002 | 7.65 | 5500 | 0.9187 | 51.3320 |
115
+ | 0.0001 | 7.79 | 5600 | 0.9184 | 52.3954 |
116
+ | 0.0001 | 7.93 | 5700 | 0.9185 | 52.5392 |
117
+ | 0.0001 | 8.07 | 5800 | 0.9209 | 53.1263 |
118
+ | 0.0001 | 8.21 | 5900 | 0.9232 | 53.0965 |
119
+ | 0.0001 | 8.34 | 6000 | 0.9242 | 53.6737 |
120
+ | 0.0001 | 8.48 | 6100 | 0.9220 | 52.6996 |
121
+ | 0.0001 | 8.62 | 6200 | 0.9228 | 52.6500 |
122
+ | 0.0001 | 8.76 | 6300 | 0.9255 | 52.3838 |
123
+ | 0.0001 | 8.9 | 6400 | 0.9269 | 53.0138 |
124
+ | 0.0001 | 9.04 | 6500 | 0.9298 | 52.9345 |
125
+ | 0.0001 | 9.18 | 6600 | 0.9317 | 53.2222 |
126
+ | 0.0001 | 9.32 | 6700 | 0.9337 | 53.1974 |
127
+ | 0.0001 | 9.46 | 6800 | 0.9354 | 52.9130 |
128
+ | 0.0001 | 9.6 | 6900 | 0.9379 | 52.8865 |
129
+ | 0.0001 | 9.74 | 7000 | 0.9407 | 52.9560 |
130
+ | 0.0001 | 9.87 | 7100 | 0.9399 | 52.5045 |
131
+ | 0.0001 | 10.01 | 7200 | 0.9394 | 52.9113 |
132
+ | 0.0001 | 10.15 | 7300 | 0.9423 | 52.9064 |
133
+ | 0.0001 | 10.29 | 7400 | 0.9422 | 52.9477 |
134
+ | 0.0001 | 10.43 | 7500 | 0.9445 | 53.2305 |
135
+ | 0.0001 | 10.57 | 7600 | 0.9452 | 53.1842 |
136
+ | 0.0001 | 10.71 | 7700 | 0.9478 | 53.3562 |
137
+ | 0.0001 | 10.85 | 7800 | 0.9451 | 52.9113 |
138
+ | 0.0001 | 10.99 | 7900 | 0.9476 | 52.6616 |
139
+ | 0.0 | 11.13 | 8000 | 0.9502 | 52.3606 |
140
+ | 0.0 | 11.27 | 8100 | 0.9518 | 52.7294 |
141
+ | 0.0 | 11.4 | 8200 | 0.9523 | 52.8799 |
142
+ | 0.0 | 11.54 | 8300 | 0.9540 | 52.8419 |
143
+ | 0.0001 | 11.68 | 8400 | 0.9542 | 53.0486 |
144
+ | 0.0 | 11.82 | 8500 | 0.9569 | 53.0453 |
145
+ | 0.0 | 11.96 | 8600 | 0.9576 | 52.9576 |
146
+ | 0.0 | 12.1 | 8700 | 0.9589 | 53.2371 |
147
+ | 0.0 | 12.24 | 8800 | 0.9599 | 53.2057 |
148
+ | 0.0 | 12.38 | 8900 | 0.9605 | 53.3165 |
149
+ | 0.0 | 12.52 | 9000 | 0.9603 | 52.9576 |
150
+ | 0.0 | 12.66 | 9100 | 0.9608 | 52.5789 |
151
+ | 0.0 | 12.8 | 9200 | 0.9609 | 53.2288 |
152
+ | 0.0 | 12.93 | 9300 | 0.9611 | 53.1759 |
153
+ | 0.0 | 13.07 | 9400 | 0.9618 | 53.1296 |
154
+ | 0.0001 | 13.21 | 9500 | 0.9632 | 53.0618 |
155
+ | 0.0 | 13.35 | 9600 | 0.9632 | 52.9593 |
156
+ | 0.0 | 13.49 | 9700 | 0.9633 | 52.9923 |
157
+ | 0.0 | 13.63 | 9800 | 0.9635 | 53.1379 |
158
+ | 0.0 | 13.77 | 9900 | 0.9637 | 53.0122 |
159
+ | 0.0 | 13.91 | 10000 | 0.9637 | 53.0122 |
160
 
161
 
162
  ### Framework versions
163
 
164
+ - Transformers 4.35.2
165
  - Pytorch 2.0.1+cu117
166
+ - Datasets 2.15.0
167
+ - Tokenizers 0.15.0
generation_config.json CHANGED
@@ -259,5 +259,5 @@
259
  "transcribe": 50359,
260
  "translate": 50358
261
  },
262
- "transformers_version": "4.35.0"
263
  }
 
259
  "transcribe": 50359,
260
  "translate": 50358
261
  },
262
+ "transformers_version": "4.35.2"
263
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63ccf8aa97e1929569d16e6b62fc5c95c08286f0f46e931596f01fb635ead180
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7563df7fbf30652de9a8392c8387ebfb1763a4e9282247d522f7c46a20c31033
3
  size 966995080
runs/Dec12_17-38-06_Software-AI/events.out.tfevents.1702390089.Software-AI.6644.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc3a91391ea4af327e37eb7e1c1bc23e7103e2719b88b1115c57a500eab9b302
3
- size 97771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d36050c170e8b939626ed73addd1b7e5152a096b8d0a972d4c6217e245047a7
3
+ size 100017