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
683bcba
•
1 Parent(s): 0b43003

End of training

Browse files
Files changed (3) hide show
  1. README.md +3 -114
  2. runs/Dec27_12-04-03_Software-AI/events.out.tfevents.1703666045.Software-AI.9199.0 +3 -0
  3. training_args.bin +1 -1
README.md CHANGED
@@ -7,9 +7,7 @@ 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: []
@@ -20,10 +18,7 @@ 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 [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: 0.8695
26
- - Wer: 50.4804
27
 
28
  ## Model description
29
 
@@ -42,7 +37,7 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 1e-08
46
  - train_batch_size: 10
47
  - eval_batch_size: 10
48
  - seed: 42
@@ -53,112 +48,6 @@ The following hyperparameters were used during training:
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
- | 0.0002 | 0.14 | 100 | 0.8627 | 50.5962 |
61
- | 0.0002 | 0.28 | 200 | 0.8627 | 50.5945 |
62
- | 0.0002 | 0.42 | 300 | 0.8628 | 50.5945 |
63
- | 0.0001 | 0.56 | 400 | 0.8631 | 50.2720 |
64
- | 0.0001 | 0.7 | 500 | 0.8634 | 50.2869 |
65
- | 0.0002 | 0.83 | 600 | 0.8637 | 50.2638 |
66
- | 0.0002 | 0.97 | 700 | 0.8638 | 50.2704 |
67
- | 0.0002 | 1.11 | 800 | 0.8639 | 50.2935 |
68
- | 0.0002 | 1.25 | 900 | 0.8640 | 50.2704 |
69
- | 0.0002 | 1.39 | 1000 | 0.8641 | 50.2340 |
70
- | 0.0002 | 1.53 | 1100 | 0.8644 | 50.2538 |
71
- | 0.0002 | 1.67 | 1200 | 0.8645 | 50.2522 |
72
- | 0.0002 | 1.81 | 1300 | 0.8646 | 50.2671 |
73
- | 0.0002 | 1.95 | 1400 | 0.8648 | 50.2241 |
74
- | 0.0002 | 2.09 | 1500 | 0.8650 | 50.2390 |
75
- | 0.0001 | 2.23 | 1600 | 0.8653 | 50.2274 |
76
- | 0.0001 | 2.36 | 1700 | 0.8653 | 50.2257 |
77
- | 0.0002 | 2.5 | 1800 | 0.8653 | 50.2290 |
78
- | 0.0002 | 2.64 | 1900 | 0.8653 | 50.2373 |
79
- | 0.0002 | 2.78 | 2000 | 0.8653 | 50.2307 |
80
- | 0.0001 | 2.92 | 2100 | 0.8655 | 50.2158 |
81
- | 0.0002 | 3.06 | 2200 | 0.8656 | 50.2175 |
82
- | 0.0002 | 3.2 | 2300 | 0.8658 | 50.2108 |
83
- | 0.0002 | 3.34 | 2400 | 0.8659 | 50.2175 |
84
- | 0.0001 | 3.48 | 2500 | 0.8660 | 50.2274 |
85
- | 0.0001 | 3.62 | 2600 | 0.8661 | 50.2257 |
86
- | 0.0002 | 3.76 | 2700 | 0.8662 | 50.2323 |
87
- | 0.0002 | 3.89 | 2800 | 0.8663 | 50.2108 |
88
- | 0.0002 | 4.03 | 2900 | 0.8665 | 50.1827 |
89
- | 0.0002 | 4.17 | 3000 | 0.8666 | 50.2158 |
90
- | 0.0001 | 4.31 | 3100 | 0.8668 | 50.2191 |
91
- | 0.0002 | 4.45 | 3200 | 0.8668 | 50.2224 |
92
- | 0.0002 | 4.59 | 3300 | 0.8669 | 50.1976 |
93
- | 0.0002 | 4.73 | 3400 | 0.8668 | 50.1893 |
94
- | 0.0002 | 4.87 | 3500 | 0.8668 | 50.1976 |
95
- | 0.0001 | 5.01 | 3600 | 0.8670 | 50.1976 |
96
- | 0.0002 | 5.15 | 3700 | 0.8671 | 50.1893 |
97
- | 0.0001 | 5.29 | 3800 | 0.8672 | 50.1893 |
98
- | 0.0002 | 5.42 | 3900 | 0.8673 | 50.1860 |
99
- | 0.0001 | 5.56 | 4000 | 0.8674 | 50.1728 |
100
- | 0.0002 | 5.7 | 4100 | 0.8674 | 50.1927 |
101
- | 0.0002 | 5.84 | 4200 | 0.8675 | 50.2935 |
102
- | 0.0001 | 5.98 | 4300 | 0.8676 | 50.1943 |
103
- | 0.0002 | 6.12 | 4400 | 0.8676 | 50.2009 |
104
- | 0.0002 | 6.26 | 4500 | 0.8677 | 50.2605 |
105
- | 0.0002 | 6.4 | 4600 | 0.8677 | 50.2737 |
106
- | 0.0002 | 6.54 | 4700 | 0.8679 | 50.2638 |
107
- | 0.0001 | 6.68 | 4800 | 0.8681 | 50.2621 |
108
- | 0.0002 | 6.82 | 4900 | 0.8681 | 50.2654 |
109
- | 0.0001 | 6.95 | 5000 | 0.8681 | 50.2770 |
110
- | 0.0001 | 7.09 | 5100 | 0.8682 | 50.2638 |
111
- | 0.0002 | 7.23 | 5200 | 0.8682 | 50.2737 |
112
- | 0.0002 | 7.37 | 5300 | 0.8682 | 50.2886 |
113
- | 0.0002 | 7.51 | 5400 | 0.8683 | 50.2820 |
114
- | 0.0002 | 7.65 | 5500 | 0.8683 | 50.3084 |
115
- | 0.0001 | 7.79 | 5600 | 0.8684 | 50.2803 |
116
- | 0.0001 | 7.93 | 5700 | 0.8685 | 50.2952 |
117
- | 0.0001 | 8.07 | 5800 | 0.8686 | 50.2770 |
118
- | 0.0001 | 8.21 | 5900 | 0.8687 | 50.2803 |
119
- | 0.0001 | 8.34 | 6000 | 0.8688 | 50.2820 |
120
- | 0.0001 | 8.48 | 6100 | 0.8689 | 50.3018 |
121
- | 0.0002 | 8.62 | 6200 | 0.8689 | 50.2853 |
122
- | 0.0001 | 8.76 | 6300 | 0.8689 | 50.2886 |
123
- | 0.0002 | 8.9 | 6400 | 0.8689 | 50.2753 |
124
- | 0.0001 | 9.04 | 6500 | 0.8689 | 50.4606 |
125
- | 0.0001 | 9.18 | 6600 | 0.8690 | 50.4721 |
126
- | 0.0001 | 9.32 | 6700 | 0.8690 | 50.4754 |
127
- | 0.0002 | 9.46 | 6800 | 0.8690 | 50.4738 |
128
- | 0.0002 | 9.6 | 6900 | 0.8691 | 50.4655 |
129
- | 0.0001 | 9.74 | 7000 | 0.8692 | 50.4672 |
130
- | 0.0002 | 9.87 | 7100 | 0.8692 | 50.4705 |
131
- | 0.0002 | 10.01 | 7200 | 0.8692 | 50.4688 |
132
- | 0.0001 | 10.15 | 7300 | 0.8692 | 50.4771 |
133
- | 0.0001 | 10.29 | 7400 | 0.8692 | 50.4771 |
134
- | 0.0001 | 10.43 | 7500 | 0.8692 | 50.4771 |
135
- | 0.0001 | 10.57 | 7600 | 0.8692 | 50.4837 |
136
- | 0.0001 | 10.71 | 7700 | 0.8693 | 50.4820 |
137
- | 0.0001 | 10.85 | 7800 | 0.8693 | 50.4887 |
138
- | 0.0001 | 10.99 | 7900 | 0.8693 | 50.4820 |
139
- | 0.0001 | 11.13 | 8000 | 0.8694 | 50.4887 |
140
- | 0.0001 | 11.27 | 8100 | 0.8694 | 50.4804 |
141
- | 0.0002 | 11.4 | 8200 | 0.8694 | 50.4754 |
142
- | 0.0001 | 11.54 | 8300 | 0.8694 | 50.4721 |
143
- | 0.0002 | 11.68 | 8400 | 0.8694 | 50.4771 |
144
- | 0.0001 | 11.82 | 8500 | 0.8694 | 50.4738 |
145
- | 0.0002 | 11.96 | 8600 | 0.8695 | 50.4771 |
146
- | 0.0002 | 12.1 | 8700 | 0.8695 | 50.4787 |
147
- | 0.0001 | 12.24 | 8800 | 0.8695 | 50.4787 |
148
- | 0.0001 | 12.38 | 8900 | 0.8695 | 50.4754 |
149
- | 0.0001 | 12.52 | 9000 | 0.8695 | 50.4787 |
150
- | 0.0001 | 12.66 | 9100 | 0.8695 | 50.4787 |
151
- | 0.0001 | 12.8 | 9200 | 0.8695 | 50.4804 |
152
- | 0.0001 | 12.93 | 9300 | 0.8695 | 50.4804 |
153
- | 0.0001 | 13.07 | 9400 | 0.8695 | 50.4804 |
154
- | 0.0002 | 13.21 | 9500 | 0.8695 | 50.4804 |
155
- | 0.0002 | 13.35 | 9600 | 0.8695 | 50.4804 |
156
- | 0.0001 | 13.49 | 9700 | 0.8695 | 50.4804 |
157
- | 0.0002 | 13.63 | 9800 | 0.8695 | 50.4804 |
158
- | 0.0002 | 13.77 | 9900 | 0.8695 | 50.4804 |
159
- | 0.0001 | 13.91 | 10000 | 0.8695 | 50.4804 |
160
-
161
-
162
  ### Framework versions
163
 
164
  - Transformers 4.35.2
 
7
  - fa-asr
8
  - generated_from_trainer
9
  datasets:
10
+ - mozilla-foundation/common_voice_16_0
 
 
11
  model-index:
12
  - name: Whisper Small Persian
13
  results: []
 
18
 
19
  # Whisper Small Persian
20
 
21
+ 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 16.0 dataset.
 
 
 
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 1e-07
41
  - train_batch_size: 10
42
  - eval_batch_size: 10
43
  - seed: 42
 
48
  - lr_scheduler_warmup_steps: 500
49
  - training_steps: 10000
50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  ### Framework versions
52
 
53
  - Transformers 4.35.2
runs/Dec27_12-04-03_Software-AI/events.out.tfevents.1703666045.Software-AI.9199.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986fbb9a9c9d3ab3d3df7fe1ff4facf6a84048044c83d9828dd9580f1ff425a4
3
+ size 100017
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f76d41f8a3c1dfc3e6ec9bca76c0c7a523a407b3ddd3e3c775553d8dff6ec5b3
3
  size 4283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:857db0f07bcdc1487b45ec233722b44ae580aa4b373b9951c2878ff086f8ddab
3
  size 4283