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
1ad4e6c
·
verified ·
1 Parent(s): a8dca0b

Training finished

Browse files
Files changed (3) hide show
  1. README.md +30 -30
  2. model.safetensors +1 -1
  3. runs/Dec29_18-07-46_32265823a9c3/events.out.tfevents.1735532064.32265823a9c3.23.1 +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: 0.0134
24
- - Wer: 0.0795
25
- - Cer: 0.0327
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
- | 0.0109 | 1.0 | 469 | 0.0075 | 0.0851 | 0.0324 |
61
- | 0.0038 | 2.0 | 938 | 0.0082 | 0.0927 | 0.0332 |
62
- | 0.0028 | 3.0 | 1407 | 0.0104 | 0.0981 | 0.0364 |
63
- | 0.0028 | 4.0 | 1876 | 0.0106 | 0.0936 | 0.0359 |
64
- | 0.0015 | 5.0 | 2345 | 0.0112 | 0.0963 | 0.0361 |
65
- | 0.0013 | 6.0 | 2814 | 0.0108 | 0.0957 | 0.0359 |
66
- | 0.0009 | 7.0 | 3283 | 0.0126 | 0.0959 | 0.0366 |
67
- | 0.0007 | 8.0 | 3752 | 0.0115 | 0.1024 | 0.0391 |
68
- | 0.0005 | 9.0 | 4221 | 0.0121 | 0.0985 | 0.0371 |
69
- | 0.0009 | 10.0 | 4690 | 0.0125 | 0.1024 | 0.0383 |
70
- | 0.0004 | 11.0 | 5159 | 0.0123 | 0.0954 | 0.0361 |
71
- | 0.0003 | 12.0 | 5628 | 0.0124 | 0.0889 | 0.0347 |
72
- | 0.0002 | 13.0 | 6097 | 0.0129 | 0.0948 | 0.0368 |
73
- | 0.0002 | 14.0 | 6566 | 0.0124 | 0.0903 | 0.0346 |
74
- | 0.0001 | 15.0 | 7035 | 0.0127 | 0.0907 | 0.0353 |
75
- | 0.0001 | 16.0 | 7504 | 0.0128 | 0.0918 | 0.0354 |
76
- | 0.0002 | 17.0 | 7973 | 0.0131 | 0.0916 | 0.0362 |
77
- | 0.0002 | 18.0 | 8442 | 0.0126 | 0.0883 | 0.0356 |
78
- | 0.0002 | 19.0 | 8911 | 0.0122 | 0.0885 | 0.0365 |
79
- | 0.0 | 20.0 | 9380 | 0.0124 | 0.0778 | 0.0323 |
80
- | 0.0 | 21.0 | 9849 | 0.0126 | 0.0784 | 0.0322 |
81
- | 0.0 | 22.0 | 10318 | 0.0126 | 0.0775 | 0.0326 |
82
- | 0.0 | 23.0 | 10787 | 0.0126 | 0.0758 | 0.0315 |
83
- | 0.0 | 24.0 | 11256 | 0.0133 | 0.0795 | 0.0328 |
84
- | 0.0 | 25.0 | 11725 | 0.0127 | 0.0749 | 0.0313 |
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: 0.0131
24
+ - Wer: 0.0768
25
+ - Cer: 0.0318
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.0074 | 0.9990 | 512 | 0.0070 | 0.0780 | 0.0313 |
61
+ | 0.0054 | 2.0 | 1025 | 0.0080 | 0.0834 | 0.0334 |
62
+ | 0.0022 | 2.9990 | 1537 | 0.0097 | 0.0914 | 0.0351 |
63
+ | 0.0016 | 4.0 | 2050 | 0.0100 | 0.0907 | 0.0329 |
64
+ | 0.0012 | 4.9990 | 2562 | 0.0099 | 0.0871 | 0.0331 |
65
+ | 0.0013 | 6.0 | 3075 | 0.0104 | 0.0907 | 0.0379 |
66
+ | 0.0008 | 6.9990 | 3587 | 0.0111 | 0.0948 | 0.0339 |
67
+ | 0.0008 | 8.0 | 4100 | 0.0104 | 0.0896 | 0.0341 |
68
+ | 0.0005 | 8.9990 | 4612 | 0.0118 | 0.0885 | 0.0353 |
69
+ | 0.0005 | 10.0 | 5125 | 0.0105 | 0.0822 | 0.0290 |
70
+ | 0.0006 | 10.9990 | 5637 | 0.0108 | 0.0901 | 0.0328 |
71
+ | 0.0005 | 12.0 | 6150 | 0.0109 | 0.0825 | 0.0316 |
72
+ | 0.0001 | 12.9990 | 6662 | 0.0119 | 0.0858 | 0.0331 |
73
+ | 0.0003 | 14.0 | 7175 | 0.0116 | 0.0900 | 0.0336 |
74
+ | 0.0002 | 14.9990 | 7687 | 0.0118 | 0.0921 | 0.0346 |
75
+ | 0.0002 | 16.0 | 8200 | 0.0117 | 0.0867 | 0.0344 |
76
+ | 0.0002 | 16.9990 | 8712 | 0.0123 | 0.0849 | 0.0324 |
77
+ | 0.0001 | 18.0 | 9225 | 0.0120 | 0.0767 | 0.0290 |
78
+ | 0.0 | 18.9990 | 9737 | 0.0117 | 0.0773 | 0.0297 |
79
+ | 0.0 | 20.0 | 10250 | 0.0118 | 0.0767 | 0.0300 |
80
+ | 0.0 | 20.9990 | 10762 | 0.0120 | 0.0766 | 0.0309 |
81
+ | 0.0 | 22.0 | 11275 | 0.0122 | 0.0753 | 0.0305 |
82
+ | 0.0 | 22.9990 | 11787 | 0.0123 | 0.0751 | 0.0301 |
83
+ | 0.0 | 24.0 | 12300 | 0.0132 | 0.0763 | 0.0316 |
84
+ | 0.0 | 24.9756 | 12800 | 0.0124 | 0.0751 | 0.0303 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b84ab5a9a4781a1524adf0dbed32264261247e3fb0261eb166e36f024ef8b95a
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78674d64cbdfc0b434ce126d52663b5d0d5fdf239953cb1cdf3ee977167c3021
3
  size 290403936
runs/Dec29_18-07-46_32265823a9c3/events.out.tfevents.1735532064.32265823a9c3.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2019beda90996d348a30c738745383ef9798c2c24ba0241f44c14952f6ff739e
3
+ size 453