Hugging Face's logo

makhataei
/
Whisper-Small-Ctejarat

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Persian
whisper
fa-asr
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
makhataei commited on
Commit
50bc39b
·
verified ·
1 Parent(s): 7ead878

End of training

Browse files
Files changed (3) hide show
  1. README.md +53 -53
  2. model.safetensors +1 -1
  3. runs/Mar24_06-25-05_Software-AI/events.out.tfevents.1711248906.Software-AI.917997.0 +2 -2
README.md CHANGED
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [makhataei/Whisper-Small-Ctejarat](https://huggingface.co/makhataei/Whisper-Small-Ctejarat) on the Ctejarat dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0096
24
- - Wer: 14.7297
25
 
26
  ## Model description
27
 
@@ -40,7 +40,7 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 1e-06
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 42
@@ -55,56 +55,56 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:------:|:----:|:---------------:|:-------:|
58
- | 0.0042 | 9.88 | 100 | 0.0098 | 15.0170 |
59
- | 0.0011 | 19.75 | 200 | 0.0096 | 14.6775 |
60
- | 0.0004 | 29.63 | 300 | 0.0096 | 14.7558 |
61
- | 0.0002 | 39.51 | 400 | 0.0096 | 14.7819 |
62
- | 0.0001 | 49.38 | 500 | 0.0096 | 14.7558 |
63
- | 0.0001 | 59.26 | 600 | 0.0095 | 14.7819 |
64
- | 0.0001 | 69.14 | 700 | 0.0095 | 14.8080 |
65
- | 0.0001 | 79.01 | 800 | 0.0095 | 14.8342 |
66
- | 0.0001 | 88.89 | 900 | 0.0095 | 14.8864 |
67
- | 0.0001 | 98.77 | 1000 | 0.0095 | 14.9125 |
68
- | 0.0 | 108.64 | 1100 | 0.0095 | 14.9647 |
69
- | 0.0 | 118.52 | 1200 | 0.0095 | 15.0170 |
70
- | 0.0 | 128.4 | 1300 | 0.0095 | 15.0431 |
71
- | 0.0 | 138.27 | 1400 | 0.0095 | 15.0431 |
72
- | 0.0 | 148.15 | 1500 | 0.0095 | 15.0431 |
73
- | 0.0 | 158.02 | 1600 | 0.0095 | 15.0431 |
74
- | 0.0 | 167.9 | 1700 | 0.0095 | 15.0431 |
75
- | 0.0 | 177.78 | 1800 | 0.0095 | 15.0692 |
76
- | 0.0 | 187.65 | 1900 | 0.0095 | 15.0692 |
77
- | 0.0 | 197.53 | 2000 | 0.0095 | 15.0953 |
78
- | 0.0 | 207.41 | 2100 | 0.0095 | 15.0953 |
79
- | 0.0 | 217.28 | 2200 | 0.0095 | 15.1214 |
80
- | 0.0 | 227.16 | 2300 | 0.0095 | 15.1214 |
81
- | 0.0 | 237.04 | 2400 | 0.0095 | 15.1214 |
82
- | 0.0 | 246.91 | 2500 | 0.0095 | 15.1214 |
83
- | 0.0 | 256.79 | 2600 | 0.0095 | 15.1476 |
84
- | 0.0 | 266.67 | 2700 | 0.0095 | 15.1476 |
85
- | 0.0 | 276.54 | 2800 | 0.0095 | 15.1737 |
86
- | 0.0 | 286.42 | 2900 | 0.0095 | 15.1737 |
87
- | 0.0 | 296.3 | 3000 | 0.0095 | 15.1998 |
88
- | 0.0 | 306.17 | 3100 | 0.0096 | 14.9386 |
89
- | 0.0 | 316.05 | 3200 | 0.0096 | 14.9386 |
90
- | 0.0 | 325.93 | 3300 | 0.0096 | 14.9386 |
91
- | 0.0 | 335.8 | 3400 | 0.0096 | 14.9386 |
92
- | 0.0 | 345.68 | 3500 | 0.0096 | 14.9386 |
93
- | 0.0 | 355.56 | 3600 | 0.0096 | 14.9386 |
94
- | 0.0 | 365.43 | 3700 | 0.0096 | 14.9386 |
95
- | 0.0 | 375.31 | 3800 | 0.0096 | 14.5469 |
96
- | 0.0 | 385.19 | 3900 | 0.0096 | 14.5730 |
97
- | 0.0 | 395.06 | 4000 | 0.0096 | 14.5730 |
98
- | 0.0 | 404.94 | 4100 | 0.0096 | 14.5991 |
99
- | 0.0 | 414.81 | 4200 | 0.0096 | 14.5991 |
100
- | 0.0 | 424.69 | 4300 | 0.0096 | 14.7036 |
101
- | 0.0 | 434.57 | 4400 | 0.0096 | 14.7297 |
102
- | 0.0 | 444.44 | 4500 | 0.0096 | 14.7297 |
103
- | 0.0 | 454.32 | 4600 | 0.0096 | 14.7297 |
104
- | 0.0 | 464.2 | 4700 | 0.0096 | 14.7297 |
105
- | 0.0 | 474.07 | 4800 | 0.0096 | 14.7297 |
106
- | 0.0 | 483.95 | 4900 | 0.0096 | 14.7297 |
107
- | 0.0 | 493.83 | 5000 | 0.0096 | 14.7297 |
108
 
109
 
110
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [makhataei/Whisper-Small-Ctejarat](https://huggingface.co/makhataei/Whisper-Small-Ctejarat) on the Ctejarat dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0031
24
+ - Wer: 13.3353
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 1e-07
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 42
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Wer |
57
  |:-------------:|:------:|:----:|:---------------:|:-------:|
58
+ | 0.0032 | 9.52 | 100 | 0.0031 | 13.1328 |
59
+ | 0.0027 | 19.05 | 200 | 0.0031 | 13.0171 |
60
+ | 0.002 | 28.57 | 300 | 0.0031 | 13.0171 |
61
+ | 0.0015 | 38.1 | 400 | 0.0031 | 13.0749 |
62
+ | 0.0005 | 47.62 | 500 | 0.0031 | 13.3642 |
63
+ | 0.0003 | 57.14 | 600 | 0.0031 | 13.3353 |
64
+ | 0.0002 | 66.67 | 700 | 0.0031 | 13.3353 |
65
+ | 0.0002 | 76.19 | 800 | 0.0031 | 13.3353 |
66
+ | 0.0001 | 85.71 | 900 | 0.0031 | 13.3063 |
67
+ | 0.0001 | 95.24 | 1000 | 0.0031 | 13.3063 |
68
+ | 0.0001 | 104.76 | 1100 | 0.0031 | 13.3063 |
69
+ | 0.0001 | 114.29 | 1200 | 0.0031 | 13.3931 |
70
+ | 0.0001 | 123.81 | 1300 | 0.0031 | 13.3931 |
71
+ | 0.0001 | 133.33 | 1400 | 0.0031 | 13.3642 |
72
+ | 0.0001 | 142.86 | 1500 | 0.0031 | 13.3931 |
73
+ | 0.0001 | 152.38 | 1600 | 0.0031 | 13.3931 |
74
+ | 0.0001 | 161.9 | 1700 | 0.0031 | 13.3642 |
75
+ | 0.0 | 171.43 | 1800 | 0.0031 | 13.3642 |
76
+ | 0.0001 | 180.95 | 1900 | 0.0031 | 13.3642 |
77
+ | 0.0 | 190.48 | 2000 | 0.0031 | 13.3642 |
78
+ | 0.0 | 200.0 | 2100 | 0.0031 | 13.3642 |
79
+ | 0.0 | 209.52 | 2200 | 0.0031 | 13.3642 |
80
+ | 0.0 | 219.05 | 2300 | 0.0031 | 13.3642 |
81
+ | 0.0 | 228.57 | 2400 | 0.0031 | 13.3642 |
82
+ | 0.0 | 238.1 | 2500 | 0.0031 | 13.3353 |
83
+ | 0.0 | 247.62 | 2600 | 0.0031 | 13.3353 |
84
+ | 0.0 | 257.14 | 2700 | 0.0031 | 13.3353 |
85
+ | 0.0 | 266.67 | 2800 | 0.0031 | 13.3353 |
86
+ | 0.0 | 276.19 | 2900 | 0.0031 | 13.3353 |
87
+ | 0.0 | 285.71 | 3000 | 0.0031 | 13.3353 |
88
+ | 0.0 | 295.24 | 3100 | 0.0031 | 13.3353 |
89
+ | 0.0 | 304.76 | 3200 | 0.0031 | 13.3353 |
90
+ | 0.0 | 314.29 | 3300 | 0.0031 | 13.3642 |
91
+ | 0.0 | 323.81 | 3400 | 0.0031 | 13.3642 |
92
+ | 0.0 | 333.33 | 3500 | 0.0031 | 13.3642 |
93
+ | 0.0 | 342.86 | 3600 | 0.0031 | 13.3642 |
94
+ | 0.0 | 352.38 | 3700 | 0.0031 | 13.3353 |
95
+ | 0.0 | 361.9 | 3800 | 0.0031 | 13.3353 |
96
+ | 0.0 | 371.43 | 3900 | 0.0031 | 13.3353 |
97
+ | 0.0 | 380.95 | 4000 | 0.0031 | 13.3353 |
98
+ | 0.0 | 390.48 | 4100 | 0.0031 | 13.3353 |
99
+ | 0.0 | 400.0 | 4200 | 0.0031 | 13.3353 |
100
+ | 0.0 | 409.52 | 4300 | 0.0031 | 13.3353 |
101
+ | 0.0 | 419.05 | 4400 | 0.0031 | 13.3353 |
102
+ | 0.0 | 428.57 | 4500 | 0.0031 | 13.3353 |
103
+ | 0.0 | 438.1 | 4600 | 0.0031 | 13.3353 |
104
+ | 0.0 | 447.62 | 4700 | 0.0031 | 13.3353 |
105
+ | 0.0 | 457.14 | 4800 | 0.0031 | 13.3353 |
106
+ | 0.0 | 466.67 | 4900 | 0.0031 | 13.3353 |
107
+ | 0.0 | 476.19 | 5000 | 0.0031 | 13.3353 |
108
 
109
 
110
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cceaf5bb0744b45fd63d8efc4875a4b18525c9187fc67b7f2992265f563098ae
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385660d16f52cfd70301472efa6531d989c3fe2e5ce2cd5e1e6481364b15b6bc
3
  size 966995080
runs/Mar24_06-25-05_Software-AI/events.out.tfevents.1711248906.Software-AI.917997.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a49a0eee53ac30d4eced714ebb1802fea37c04d2fca0396bdabe5873f50b0570
3
- size 51503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c55bde6219361f578d65ab944a6027e2f8d4c398348d3e003d97627c70f9c87d
3
+ size 52803