Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_tiny_fine_tune_Quran

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
40e08c1
·
verified ·
1 Parent(s): 6bcbf24

Training finished

Browse files
Files changed (2) hide show
  1. README.md +19 -19
  2. runs/Apr28_08-51-52_bf4b3ecc6b3d/events.out.tfevents.1745854302.bf4b3ecc6b3d.18.1 +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-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0288
24
- - Wer: 15.7981
25
- - Cer: 4.8926
26
 
27
  ## Model description
28
 
@@ -57,26 +57,26 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:------:|
60
- | 0.0015 | 1.0 | 157 | 0.0176 | 17.0508 | 5.4660 |
61
- | 0.0007 | 2.0 | 314 | 0.0205 | 17.9173 | 5.9564 |
62
- | 0.0007 | 3.0 | 471 | 0.0241 | 20.2647 | 6.7086 |
63
- | 0.0009 | 4.0 | 628 | 0.0254 | 20.3409 | 6.5112 |
64
- | 0.0007 | 5.0 | 785 | 0.0263 | 20.7123 | 6.4479 |
65
- | 0.0006 | 6.0 | 942 | 0.0279 | 19.9695 | 6.0607 |
66
- | 0.0004 | 7.0 | 1099 | 0.0269 | 20.1219 | 6.6016 |
67
- | 0.0003 | 8.0 | 1256 | 0.0280 | 18.9982 | 6.0934 |
68
- | 0.0003 | 9.0 | 1413 | 0.0294 | 20.1505 | 6.0196 |
69
- | 0.0001 | 10.0 | 1570 | 0.0286 | 19.0791 | 6.0391 |
70
- | 0.0 | 11.0 | 1727 | 0.0308 | 18.3935 | 5.9303 |
71
- | 0.0 | 12.0 | 1884 | 0.0302 | 17.2793 | 5.5675 |
72
- | 0.0 | 13.0 | 2041 | 0.0308 | 16.5556 | 5.3800 |
73
- | 0.0 | 14.0 | 2198 | 0.0311 | 16.3984 | 5.2890 |
74
- | 0.0 | 14.9088 | 2340 | 0.0312 | 16.4365 | 5.3134 |
75
 
76
 
77
  ### Framework versions
78
 
79
  - Transformers 4.47.0
80
  - Pytorch 2.5.1+cu121
81
- - Datasets 3.3.1
82
  - Tokenizers 0.21.0
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0313
24
+ - Wer: 16.1017
25
+ - Cer: 5.0675
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:------:|
60
+ | 0.0002 | 1.0 | 157 | 0.0254 | 18.5125 | 5.9309 |
61
+ | 0.0003 | 2.0 | 314 | 0.0265 | 19.3648 | 6.2149 |
62
+ | 0.0005 | 3.0 | 471 | 0.0288 | 20.4790 | 6.5827 |
63
+ | 0.0007 | 4.0 | 628 | 0.0285 | 20.8647 | 7.2739 |
64
+ | 0.0007 | 5.0 | 785 | 0.0266 | 20.3076 | 7.0016 |
65
+ | 0.0005 | 6.0 | 942 | 0.0271 | 21.2742 | 6.7797 |
66
+ | 0.0004 | 7.0 | 1099 | 0.0302 | 20.7790 | 6.9333 |
67
+ | 0.0003 | 8.0 | 1256 | 0.0290 | 20.2028 | 6.4168 |
68
+ | 0.0002 | 9.0 | 1413 | 0.0298 | 19.6791 | 6.6121 |
69
+ | 0.0001 | 10.0 | 1570 | 0.0314 | 19.1125 | 6.3358 |
70
+ | 0.0 | 11.0 | 1727 | 0.0331 | 18.4078 | 6.1239 |
71
+ | 0.0 | 12.0 | 1884 | 0.0327 | 18.2364 | 5.9958 |
72
+ | 0.0 | 13.0 | 2041 | 0.0336 | 17.3650 | 5.8316 |
73
+ | 0.0 | 14.0 | 2198 | 0.0337 | 17.1412 | 5.6635 |
74
+ | 0.0 | 14.9088 | 2340 | 0.0337 | 17.0746 | 5.6452 |
75
 
76
 
77
  ### Framework versions
78
 
79
  - Transformers 4.47.0
80
  - Pytorch 2.5.1+cu121
81
+ - Datasets 3.2.0
82
  - Tokenizers 0.21.0
runs/Apr28_08-51-52_bf4b3ecc6b3d/events.out.tfevents.1745854302.bf4b3ecc6b3d.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d71e9fdaf8d78475c05aeefbcc213a6ee8d0da4e811c1b56b21fd9c91ba56e08
3
+ size 453