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
9f0b263
·
verified ·
1 Parent(s): e7d61fb

Training finished

Browse files
Files changed (3) hide show
  1. README.md +30 -30
  2. model.safetensors +1 -1
  3. runs/Jan21_06-14-46_7381c3269a42/events.out.tfevents.1737479091.7381c3269a42.23.1 +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: 0.0047
24
- - Wer: 0.0624
25
- - Cer: 0.0256
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
- | 0.0038 | 0.9986 | 356 | 0.0050 | 0.0657 | 0.0251 |
61
- | 0.0045 | 2.0 | 713 | 0.0064 | 0.0737 | 0.0274 |
62
- | 0.0015 | 2.9986 | 1069 | 0.0075 | 0.0814 | 0.0315 |
63
- | 0.0012 | 4.0 | 1426 | 0.0077 | 0.0795 | 0.0311 |
64
- | 0.0008 | 4.9986 | 1782 | 0.0075 | 0.0748 | 0.0263 |
65
- | 0.0005 | 6.0 | 2139 | 0.0095 | 0.0878 | 0.0325 |
66
- | 0.0009 | 6.9986 | 2495 | 0.0080 | 0.0818 | 0.0330 |
67
- | 0.0003 | 8.0 | 2852 | 0.0084 | 0.0771 | 0.0277 |
68
- | 0.0002 | 8.9986 | 3208 | 0.0091 | 0.0737 | 0.0262 |
69
- | 0.0003 | 10.0 | 3565 | 0.0087 | 0.0784 | 0.0289 |
70
- | 0.0002 | 10.9986 | 3921 | 0.0086 | 0.0854 | 0.0338 |
71
- | 0.0002 | 12.0 | 4278 | 0.0091 | 0.0829 | 0.0329 |
72
- | 0.0002 | 12.9986 | 4634 | 0.0090 | 0.0749 | 0.0283 |
73
- | 0.0002 | 14.0 | 4991 | 0.0089 | 0.0767 | 0.0285 |
74
- | 0.0001 | 14.9986 | 5347 | 0.0094 | 0.0742 | 0.0288 |
75
- | 0.0001 | 16.0 | 5704 | 0.0092 | 0.0661 | 0.0250 |
76
- | 0.0001 | 16.9986 | 6060 | 0.0096 | 0.0699 | 0.0271 |
77
- | 0.0 | 18.0 | 6417 | 0.0095 | 0.0713 | 0.0277 |
78
- | 0.0 | 18.9986 | 6773 | 0.0095 | 0.0708 | 0.0282 |
79
- | 0.0 | 20.0 | 7130 | 0.0096 | 0.0710 | 0.0293 |
80
- | 0.0 | 20.9986 | 7486 | 0.0098 | 0.0708 | 0.0289 |
81
- | 0.0 | 22.0 | 7843 | 0.0099 | 0.0700 | 0.0278 |
82
- | 0.0 | 22.9986 | 8199 | 0.0100 | 0.0699 | 0.0279 |
83
- | 0.0 | 24.0 | 8556 | 0.0096 | 0.0720 | 0.0288 |
84
- | 0.0 | 24.9649 | 8900 | 0.0100 | 0.0704 | 0.0281 |
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: 0.0077
24
+ - Wer: 0.0682
25
+ - Cer: 0.0271
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.0059 | 0.9991 | 562 | 0.0050 | 0.0695 | 0.0253 |
61
+ | 0.0017 | 2.0 | 1125 | 0.0060 | 0.0719 | 0.0263 |
62
+ | 0.0014 | 2.9991 | 1687 | 0.0070 | 0.0813 | 0.0302 |
63
+ | 0.0009 | 4.0 | 2250 | 0.0073 | 0.0715 | 0.0263 |
64
+ | 0.0009 | 4.9991 | 2812 | 0.0074 | 0.0706 | 0.0250 |
65
+ | 0.001 | 6.0 | 3375 | 0.0073 | 0.0722 | 0.0290 |
66
+ | 0.0008 | 6.9991 | 3937 | 0.0082 | 0.0753 | 0.0260 |
67
+ | 0.0004 | 8.0 | 4500 | 0.0081 | 0.0740 | 0.0257 |
68
+ | 0.0003 | 8.9991 | 5062 | 0.0083 | 0.0753 | 0.0299 |
69
+ | 0.0002 | 10.0 | 5625 | 0.0080 | 0.0637 | 0.0240 |
70
+ | 0.0004 | 10.9991 | 6187 | 0.0086 | 0.0758 | 0.0276 |
71
+ | 0.0003 | 12.0 | 6750 | 0.0083 | 0.0760 | 0.0279 |
72
+ | 0.0002 | 12.9991 | 7312 | 0.0079 | 0.0699 | 0.0267 |
73
+ | 0.0002 | 14.0 | 7875 | 0.0084 | 0.0655 | 0.0243 |
74
+ | 0.0001 | 14.9991 | 8437 | 0.0082 | 0.0671 | 0.0246 |
75
+ | 0.0001 | 16.0 | 9000 | 0.0084 | 0.0641 | 0.0237 |
76
+ | 0.0 | 16.9991 | 9562 | 0.0092 | 0.0673 | 0.0249 |
77
+ | 0.0001 | 18.0 | 10125 | 0.0083 | 0.0749 | 0.0276 |
78
+ | 0.0 | 18.9991 | 10687 | 0.0087 | 0.0670 | 0.0239 |
79
+ | 0.0 | 20.0 | 11250 | 0.0084 | 0.0661 | 0.0248 |
80
+ | 0.0 | 20.9991 | 11812 | 0.0085 | 0.0668 | 0.0251 |
81
+ | 0.0 | 22.0 | 12375 | 0.0087 | 0.0666 | 0.0248 |
82
+ | 0.0 | 22.9991 | 12937 | 0.0088 | 0.0661 | 0.0246 |
83
+ | 0.0 | 24.0 | 13500 | 0.0088 | 0.0658 | 0.0271 |
84
+ | 0.0 | 24.9778 | 14050 | 0.0089 | 0.0653 | 0.0245 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22d2ebd0ee13ce3f2cde1e00d9fe10a4d62555480fe42a9b02d37d2b691b3437
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3388893984786f6672d42d49bfbe176463c0623d17fe9db2043c2142bab3e859
3
  size 290403936
runs/Jan21_06-14-46_7381c3269a42/events.out.tfevents.1737479091.7381c3269a42.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498967459d18705eb15afd62a77db006d1afacf37fbc9522af190646d4d387cf
3
+ size 453