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
dd32689
·
verified ·
1 Parent(s): cf131b5

Training finished

Browse files
Files changed (2) hide show
  1. README.md +18 -18
  2. runs/Feb22_18-49-25_89fa7aa30e2c/events.out.tfevents.1740281301.89fa7aa30e2c.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: 0.0306
24
- - Wer: 16.3270
25
- - Cer: 5.0521
26
 
27
  ## Model description
28
 
@@ -57,21 +57,21 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:------:|
60
- | 0.0052 | 1.0 | 235 | 0.0172 | 17.0984 | 5.3883 |
61
- | 0.0032 | 2.0 | 470 | 0.0215 | 18.7839 | 6.1922 |
62
- | 0.0022 | 3.0 | 705 | 0.0228 | 19.5838 | 6.0518 |
63
- | 0.0017 | 4.0 | 940 | 0.0254 | 21.2884 | 7.6318 |
64
- | 0.0013 | 5.0 | 1175 | 0.0256 | 19.8695 | 6.7863 |
65
- | 0.0009 | 6.0 | 1410 | 0.0280 | 20.1838 | 7.0021 |
66
- | 0.0006 | 7.0 | 1645 | 0.0273 | 19.4077 | 6.6620 |
67
- | 0.0004 | 8.0 | 1880 | 0.0275 | 20.0695 | 6.7136 |
68
- | 0.0003 | 9.0 | 2115 | 0.0277 | 18.5792 | 6.2177 |
69
- | 0.0001 | 10.0 | 2350 | 0.0297 | 18.5839 | 6.0440 |
70
- | 0.0 | 11.0 | 2585 | 0.0300 | 17.3364 | 5.6424 |
71
- | 0.0 | 12.0 | 2820 | 0.0297 | 16.7841 | 5.3456 |
72
- | 0.0 | 13.0 | 3055 | 0.0301 | 16.5746 | 5.2125 |
73
- | 0.0 | 14.0 | 3290 | 0.0305 | 16.2937 | 5.0699 |
74
- | 0.0 | 14.9382 | 3510 | 0.0306 | 16.3270 | 5.0521 |
75
 
76
 
77
  ### Framework versions
 
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: 15.6192
25
+ - Cer: 4.7452
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:------:|
60
+ | 0.0038 | 1.0 | 235 | 0.0190 | 18.0459 | 5.7195 |
61
+ | 0.0023 | 2.0 | 470 | 0.0224 | 19.7981 | 6.3220 |
62
+ | 0.0017 | 3.0 | 705 | 0.0240 | 20.3362 | 6.9178 |
63
+ | 0.0012 | 4.0 | 940 | 0.0257 | 19.6838 | 6.1855 |
64
+ | 0.001 | 5.0 | 1175 | 0.0271 | 19.7791 | 6.2892 |
65
+ | 0.0007 | 6.0 | 1410 | 0.0286 | 19.8886 | 6.5894 |
66
+ | 0.0005 | 7.0 | 1645 | 0.0283 | 19.7362 | 6.5228 |
67
+ | 0.0003 | 8.0 | 1880 | 0.0295 | 19.9029 | 6.3603 |
68
+ | 0.0002 | 9.0 | 2115 | 0.0284 | 18.7077 | 5.8826 |
69
+ | 0.0001 | 10.0 | 2350 | 0.0277 | 17.8174 | 5.7073 |
70
+ | 0.0 | 11.0 | 2585 | 0.0286 | 17.0746 | 5.2252 |
71
+ | 0.0 | 12.0 | 2820 | 0.0287 | 16.1366 | 4.9994 |
72
+ | 0.0 | 13.0 | 3055 | 0.0293 | 16.0985 | 4.8513 |
73
+ | 0.0 | 14.0 | 3290 | 0.0300 | 15.9985 | 4.8436 |
74
+ | 0.0 | 14.9382 | 3510 | 0.0301 | 15.8985 | 4.8325 |
75
 
76
 
77
  ### Framework versions
runs/Feb22_18-49-25_89fa7aa30e2c/events.out.tfevents.1740281301.89fa7aa30e2c.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfa0f02278913900d3e4ac9108aefa073b7c7fb12b413c17bb6ac917a12cd7f
3
+ size 453