Hugging Face's logo

YoussefAshmawy
/
Graduation_Project_Whisper_base

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
arabic
quran
Eval Results (legacy)
Model card Files
xet
 Metrics Community
YoussefAshmawy commited on
Commit
d41a5d1
·
verified ·
1 Parent(s): 0606542

Training finished

Browse files
Files changed (2) hide show
  1. README.md +30 -30
  2. runs/Jan13_00-44-05_8d936fd76c06/events.out.tfevents.1736766294.8d936fd76c06.23.1 +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: 0.0108
24
- - Wer: 0.0696
25
- - Cer: 0.0282
26
 
27
  ## Model description
28
 
@@ -55,33 +55,33 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
- |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
60
- | 0.0045 | 0.9990 | 512 | 0.0064 | 0.0766 | 0.0315 |
61
- | 0.0032 | 2.0 | 1025 | 0.0067 | 0.0798 | 0.0322 |
62
- | 0.002 | 2.9990 | 1537 | 0.0076 | 0.0786 | 0.0314 |
63
- | 0.0019 | 4.0 | 2050 | 0.0084 | 0.0849 | 0.0333 |
64
- | 0.0009 | 4.9990 | 2562 | 0.0090 | 0.0796 | 0.0283 |
65
- | 0.0009 | 6.0 | 3075 | 0.0092 | 0.0829 | 0.0328 |
66
- | 0.0007 | 6.9990 | 3587 | 0.0094 | 0.0827 | 0.0330 |
67
- | 0.0003 | 8.0 | 4100 | 0.0088 | 0.0827 | 0.0323 |
68
- | 0.0006 | 8.9990 | 4612 | 0.0094 | 0.0842 | 0.0308 |
69
- | 0.0005 | 10.0 | 5125 | 0.0094 | 0.0822 | 0.0321 |
70
- | 0.0004 | 10.9990 | 5637 | 0.0094 | 0.0713 | 0.0262 |
71
- | 0.0002 | 12.0 | 6150 | 0.0101 | 0.0782 | 0.0309 |
72
- | 0.0002 | 12.9990 | 6662 | 0.0101 | 0.0762 | 0.0292 |
73
- | 0.0002 | 14.0 | 7175 | 0.0104 | 0.0749 | 0.0304 |
74
- | 0.0003 | 14.9990 | 7687 | 0.0107 | 0.0813 | 0.0322 |
75
- | 0.0002 | 16.0 | 8200 | 0.0107 | 0.0753 | 0.0275 |
76
- | 0.0001 | 16.9990 | 8712 | 0.0099 | 0.0724 | 0.0276 |
77
- | 0.0 | 18.0 | 9225 | 0.0103 | 0.0702 | 0.0279 |
78
- | 0.0 | 18.9990 | 9737 | 0.0104 | 0.0657 | 0.0264 |
79
- | 0.0 | 20.0 | 10250 | 0.0105 | 0.0657 | 0.0264 |
80
- | 0.0 | 20.9990 | 10762 | 0.0107 | 0.0668 | 0.0259 |
81
- | 0.0 | 22.0 | 11275 | 0.0108 | 0.0659 | 0.0254 |
82
- | 0.0 | 22.9990 | 11787 | 0.0108 | 0.0648 | 0.0249 |
83
- | 0.0 | 24.0 | 12300 | 0.0108 | 0.0698 | 0.0285 |
84
- | 0.0 | 24.9756 | 12800 | 0.0109 | 0.0652 | 0.0253 |
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: 0.0101
24
+ - Wer: 0.0679
25
+ - Cer: 0.0278
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.0067 | 1.0 | 525 | 0.0056 | 0.0720 | 0.0286 |
61
+ | 0.0021 | 2.0 | 1050 | 0.0065 | 0.0789 | 0.0321 |
62
+ | 0.0016 | 3.0 | 1575 | 0.0079 | 0.0791 | 0.0283 |
63
+ | 0.0022 | 4.0 | 2100 | 0.0086 | 0.0760 | 0.0273 |
64
+ | 0.0008 | 5.0 | 2625 | 0.0086 | 0.0776 | 0.0268 |
65
+ | 0.001 | 6.0 | 3150 | 0.0090 | 0.0811 | 0.0291 |
66
+ | 0.0006 | 7.0 | 3675 | 0.0090 | 0.0775 | 0.0296 |
67
+ | 0.0005 | 8.0 | 4200 | 0.0096 | 0.0834 | 0.0342 |
68
+ | 0.0004 | 9.0 | 4725 | 0.0093 | 0.0773 | 0.0276 |
69
+ | 0.0004 | 10.0 | 5250 | 0.0088 | 0.0740 | 0.0275 |
70
+ | 0.0005 | 11.0 | 5775 | 0.0094 | 0.0842 | 0.0326 |
71
+ | 0.0009 | 12.0 | 6300 | 0.0091 | 0.0791 | 0.0311 |
72
+ | 0.0003 | 13.0 | 6825 | 0.0084 | 0.0664 | 0.0257 |
73
+ | 0.0001 | 14.0 | 7350 | 0.0090 | 0.0695 | 0.0280 |
74
+ | 0.0001 | 15.0 | 7875 | 0.0085 | 0.0702 | 0.0283 |
75
+ | 0.0003 | 16.0 | 8400 | 0.0086 | 0.0767 | 0.0342 |
76
+ | 0.0 | 17.0 | 8925 | 0.0085 | 0.0679 | 0.0260 |
77
+ | 0.0003 | 18.0 | 9450 | 0.0086 | 0.0652 | 0.0258 |
78
+ | 0.0 | 19.0 | 9975 | 0.0085 | 0.0628 | 0.0243 |
79
+ | 0.0 | 20.0 | 10500 | 0.0084 | 0.0630 | 0.0236 |
80
+ | 0.0 | 21.0 | 11025 | 0.0086 | 0.0624 | 0.0239 |
81
+ | 0.0 | 22.0 | 11550 | 0.0087 | 0.0623 | 0.0231 |
82
+ | 0.0 | 23.0 | 12075 | 0.0088 | 0.0617 | 0.0235 |
83
+ | 0.0 | 24.0 | 12600 | 0.0101 | 0.0674 | 0.0275 |
84
+ | 0.0 | 25.0 | 13125 | 0.0088 | 0.0603 | 0.0226 |
85
 
86
 
87
  ### Framework versions
runs/Jan13_00-44-05_8d936fd76c06/events.out.tfevents.1736766294.8d936fd76c06.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1db5aac18713570651bbc057b21421bc577e095ffe36ae78b7267bf8d7edb839
3
+ size 453