Hugging Face's logo

YoussefAshmawy
/
Graduation_Project_Whisper_base

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
arabic
quran
Eval Results
Model card Files
xet
Metrics Community
YoussefAshmawy commited on
Commit
5239da2
·
verified ·
1 Parent(s): 29728d2

Training finished

Browse files
Files changed (3) hide show
  1. README.md +28 -28
  2. model.safetensors +1 -1
  3. runs/Jan15_01-25-24_a423d15cfe31/events.out.tfevents.1736942271.a423d15cfe31.23.1 +3 -0
README.md CHANGED
@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0050
24
- - Wer: 0.0655
25
- - Cer: 0.0258
26
 
27
  ## Model description
28
 
@@ -57,31 +57,31 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
60
- | 0.006 | 1.0 | 419 | 0.0050 | 0.0643 | 0.0237 |
61
- | 0.004 | 2.0 | 838 | 0.0065 | 0.0793 | 0.0306 |
62
- | 0.0015 | 3.0 | 1257 | 0.0074 | 0.0744 | 0.0273 |
63
- | 0.0008 | 4.0 | 1676 | 0.0079 | 0.0814 | 0.0309 |
64
- | 0.0008 | 5.0 | 2095 | 0.0081 | 0.0833 | 0.0314 |
65
- | 0.0008 | 6.0 | 2514 | 0.0087 | 0.0807 | 0.0293 |
66
- | 0.0007 | 7.0 | 2933 | 0.0094 | 0.0851 | 0.0326 |
67
- | 0.0007 | 8.0 | 3352 | 0.0094 | 0.0802 | 0.0280 |
68
- | 0.0008 | 9.0 | 3771 | 0.0089 | 0.0771 | 0.0293 |
69
- | 0.0003 | 10.0 | 4190 | 0.0087 | 0.0748 | 0.0282 |
70
- | 0.0003 | 11.0 | 4609 | 0.0088 | 0.0720 | 0.0271 |
71
- | 0.0001 | 12.0 | 5028 | 0.0087 | 0.0702 | 0.0261 |
72
- | 0.0002 | 13.0 | 5447 | 0.0096 | 0.0789 | 0.0284 |
73
- | 0.0001 | 14.0 | 5866 | 0.0092 | 0.0757 | 0.0267 |
74
- | 0.0002 | 15.0 | 6285 | 0.0093 | 0.0767 | 0.0284 |
75
- | 0.0001 | 16.0 | 6704 | 0.0098 | 0.0760 | 0.0285 |
76
- | 0.0 | 17.0 | 7123 | 0.0098 | 0.0791 | 0.0304 |
77
- | 0.0001 | 18.0 | 7542 | 0.0103 | 0.0757 | 0.0282 |
78
- | 0.0 | 19.0 | 7961 | 0.0094 | 0.0737 | 0.0276 |
79
- | 0.0 | 20.0 | 8380 | 0.0097 | 0.0735 | 0.0282 |
80
- | 0.0 | 21.0 | 8799 | 0.0099 | 0.0728 | 0.0277 |
81
- | 0.0 | 22.0 | 9218 | 0.0100 | 0.0724 | 0.0277 |
82
- | 0.0 | 23.0 | 9637 | 0.0101 | 0.0724 | 0.0273 |
83
- | 0.0 | 24.0 | 10056 | 0.0105 | 0.0745 | 0.0307 |
84
- | 0.0 | 25.0 | 10475 | 0.0101 | 0.0728 | 0.0276 |
85
 
86
 
87
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0096
24
+ - Wer: 0.0668
25
+ - Cer: 0.0274
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.0084 | 1.0 | 544 | 0.0057 | 0.0749 | 0.0296 |
61
+ | 0.0024 | 2.0 | 1088 | 0.0064 | 0.0755 | 0.0302 |
62
+ | 0.0016 | 3.0 | 1632 | 0.0069 | 0.0749 | 0.0289 |
63
+ | 0.0008 | 4.0 | 2176 | 0.0074 | 0.0751 | 0.0288 |
64
+ | 0.0008 | 5.0 | 2720 | 0.0079 | 0.0760 | 0.0304 |
65
+ | 0.0008 | 6.0 | 3264 | 0.0086 | 0.0789 | 0.0304 |
66
+ | 0.0004 | 7.0 | 3808 | 0.0086 | 0.0816 | 0.0320 |
67
+ | 0.0008 | 8.0 | 4352 | 0.0093 | 0.0757 | 0.0290 |
68
+ | 0.0005 | 9.0 | 4896 | 0.0085 | 0.0762 | 0.0284 |
69
+ | 0.0003 | 10.0 | 5440 | 0.0090 | 0.0776 | 0.0294 |
70
+ | 0.0004 | 11.0 | 5984 | 0.0094 | 0.0757 | 0.0276 |
71
+ | 0.0003 | 12.0 | 6528 | 0.0089 | 0.0764 | 0.0267 |
72
+ | 0.0002 | 13.0 | 7072 | 0.0088 | 0.0802 | 0.0314 |
73
+ | 0.0002 | 14.0 | 7616 | 0.0090 | 0.0773 | 0.0283 |
74
+ | 0.0001 | 15.0 | 8160 | 0.0094 | 0.0729 | 0.0297 |
75
+ | 0.0 | 16.0 | 8704 | 0.0094 | 0.0671 | 0.0262 |
76
+ | 0.0002 | 17.0 | 9248 | 0.0090 | 0.0731 | 0.0288 |
77
+ | 0.0001 | 18.0 | 9792 | 0.0094 | 0.0749 | 0.0281 |
78
+ | 0.0 | 19.0 | 10336 | 0.0095 | 0.0675 | 0.0272 |
79
+ | 0.0 | 20.0 | 10880 | 0.0096 | 0.0706 | 0.0277 |
80
+ | 0.0 | 21.0 | 11424 | 0.0097 | 0.0684 | 0.0275 |
81
+ | 0.0 | 22.0 | 11968 | 0.0096 | 0.0670 | 0.0262 |
82
+ | 0.0 | 23.0 | 12512 | 0.0097 | 0.0664 | 0.0254 |
83
+ | 0.0 | 24.0 | 13056 | 0.0097 | 0.0666 | 0.0273 |
84
+ | 0.0 | 25.0 | 13600 | 0.0098 | 0.0666 | 0.0252 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a597c41a19804bcf8cea96ed7e714a0204c2b8b99f39a4032d0eb9b975bcada
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ec751c759fea3d43df2383299ba92ba8c12d778471c65242f0f74e03de5af97
3
  size 290403936
runs/Jan15_01-25-24_a423d15cfe31/events.out.tfevents.1736942271.a423d15cfe31.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87569c9a247881e6e56032de1cddc2f5486818dc71f04fc6f752b578f1af2ea1
3
+ size 453