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
461b415
·
verified ·
1 Parent(s): de37f59

Training finished

Browse files
Files changed (3) hide show
  1. README.md +28 -28
  2. model.safetensors +1 -1
  3. runs/Mar08_00-59-59_4192d658394d/events.out.tfevents.1741434566.4192d658394d.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: 0.0079
24
- - Wer: 0.0667
25
- - Cer: 0.0266
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
- | 0.0023 | 0.9989 | 437 | 0.0055 | 0.0646 | 0.0232 |
61
- | 0.0014 | 2.0 | 875 | 0.0067 | 0.0671 | 0.0253 |
62
- | 0.001 | 2.9989 | 1312 | 0.0073 | 0.0717 | 0.0265 |
63
- | 0.0007 | 4.0 | 1750 | 0.0082 | 0.0704 | 0.0272 |
64
- | 0.0004 | 4.9989 | 2187 | 0.0083 | 0.0744 | 0.0283 |
65
- | 0.0005 | 6.0 | 2625 | 0.0085 | 0.0767 | 0.0291 |
66
- | 0.0004 | 6.9989 | 3062 | 0.0080 | 0.0722 | 0.0259 |
67
- | 0.0003 | 8.0 | 3500 | 0.0078 | 0.0762 | 0.0299 |
68
- | 0.0002 | 8.9989 | 3937 | 0.0083 | 0.0695 | 0.0264 |
69
- | 0.0001 | 10.0 | 4375 | 0.0080 | 0.0668 | 0.0247 |
70
- | 0.0001 | 10.9989 | 4812 | 0.0083 | 0.0637 | 0.0248 |
71
- | 0.0002 | 12.0 | 5250 | 0.0085 | 0.0715 | 0.0283 |
72
- | 0.0002 | 12.9989 | 5687 | 0.0092 | 0.0724 | 0.0264 |
73
- | 0.0004 | 14.0 | 6125 | 0.0088 | 0.0710 | 0.0260 |
74
- | 0.0 | 14.9989 | 6562 | 0.0084 | 0.0679 | 0.0266 |
75
- | 0.0 | 16.0 | 7000 | 0.0090 | 0.0684 | 0.0270 |
76
- | 0.0 | 16.9989 | 7437 | 0.0085 | 0.0655 | 0.0245 |
77
- | 0.0 | 18.0 | 7875 | 0.0089 | 0.0728 | 0.0272 |
78
- | 0.0 | 18.9989 | 8312 | 0.0085 | 0.0693 | 0.0256 |
79
- | 0.0 | 20.0 | 8750 | 0.0088 | 0.0711 | 0.0269 |
80
- | 0.0 | 20.9989 | 9187 | 0.0090 | 0.0708 | 0.0288 |
81
- | 0.0 | 22.0 | 9625 | 0.0092 | 0.0690 | 0.0272 |
82
- | 0.0 | 22.9989 | 10062 | 0.0092 | 0.0686 | 0.0277 |
83
- | 0.0 | 24.0 | 10500 | 0.0087 | 0.0656 | 0.0255 |
84
- | 0.0 | 24.9714 | 10925 | 0.0093 | 0.0686 | 0.0274 |
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: 0.0076
24
+ - Wer: 0.0631
25
+ - Cer: 0.0261
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.0036 | 0.9991 | 562 | 0.0045 | 0.0608 | 0.0247 |
61
+ | 0.0021 | 2.0 | 1125 | 0.0056 | 0.0588 | 0.0229 |
62
+ | 0.0009 | 2.9991 | 1687 | 0.0059 | 0.0661 | 0.0259 |
63
+ | 0.0008 | 4.0 | 2250 | 0.0066 | 0.0662 | 0.0259 |
64
+ | 0.0011 | 4.9991 | 2812 | 0.0065 | 0.0662 | 0.0264 |
65
+ | 0.0005 | 6.0 | 3375 | 0.0075 | 0.0657 | 0.0254 |
66
+ | 0.0005 | 6.9991 | 3937 | 0.0077 | 0.0677 | 0.0256 |
67
+ | 0.0006 | 8.0 | 4500 | 0.0080 | 0.0706 | 0.0264 |
68
+ | 0.0007 | 8.9991 | 5062 | 0.0071 | 0.0691 | 0.0261 |
69
+ | 0.0002 | 10.0 | 5625 | 0.0074 | 0.0722 | 0.0305 |
70
+ | 0.0002 | 10.9991 | 6187 | 0.0076 | 0.0614 | 0.0232 |
71
+ | 0.0002 | 12.0 | 6750 | 0.0073 | 0.0610 | 0.0229 |
72
+ | 0.0001 | 12.9991 | 7312 | 0.0081 | 0.0626 | 0.0255 |
73
+ | 0.0 | 14.0 | 7875 | 0.0079 | 0.0572 | 0.0222 |
74
+ | 0.0 | 14.9991 | 8437 | 0.0083 | 0.0576 | 0.0227 |
75
+ | 0.0002 | 16.0 | 9000 | 0.0080 | 0.0668 | 0.0240 |
76
+ | 0.0001 | 16.9991 | 9562 | 0.0078 | 0.0590 | 0.0211 |
77
+ | 0.0001 | 18.0 | 10125 | 0.0081 | 0.0621 | 0.0247 |
78
+ | 0.0 | 18.9991 | 10687 | 0.0078 | 0.0597 | 0.0219 |
79
+ | 0.0 | 20.0 | 11250 | 0.0076 | 0.0599 | 0.0234 |
80
+ | 0.0 | 20.9991 | 11812 | 0.0077 | 0.0608 | 0.0230 |
81
+ | 0.0 | 22.0 | 12375 | 0.0078 | 0.0605 | 0.0233 |
82
+ | 0.0 | 22.9991 | 12937 | 0.0079 | 0.0601 | 0.0229 |
83
+ | 0.0 | 24.0 | 13500 | 0.0080 | 0.0622 | 0.0252 |
84
+ | 0.0 | 24.9778 | 14050 | 0.0080 | 0.0601 | 0.0231 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30d0b6d2138e18f968a2f83dd6ccca58219aaf2e9133fc55f3eaacb95aeeef1d
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d60cda3002c7b8fedc7ba8ec371b42f227977d74f10ac2bb8ea27f2a2789379
3
  size 290403936
runs/Mar08_00-59-59_4192d658394d/events.out.tfevents.1741434566.4192d658394d.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0475af164d12ad06ae33b7f3fab2760caf039a4a8457626ee4f9f55c5b6dd8
3
+ size 453