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
fbda816
·
verified ·
1 Parent(s): 2347d04

Training finished

Browse files
Files changed (3) hide show
  1. README.md +18 -18
  2. model.safetensors +1 -1
  3. runs/Feb23_07-05-50_226a498da3f2/events.out.tfevents.1740319250.226a498da3f2.18.1 +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: 0.0288
24
- - Wer: 15.6192
25
- - Cer: 4.7452
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
- | 0.0038 | 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
 
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: 0.0240
24
+ - Wer: 16.4755
25
+ - Cer: 4.9949
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:------:|
60
+ | 0.0033 | 1.0 | 157 | 0.0241 | 16.0794 | 4.7681 |
61
+ | 0.0013 | 2.0 | 314 | 0.0199 | 18.1697 | 6.0230 |
62
+ | 0.0008 | 3.0 | 471 | 0.0252 | 19.6172 | 6.0341 |
63
+ | 0.0011 | 4.0 | 628 | 0.0253 | 19.5458 | 6.3958 |
64
+ | 0.0008 | 5.0 | 785 | 0.0257 | 18.8601 | 6.0413 |
65
+ | 0.0008 | 6.0 | 942 | 0.0265 | 19.6934 | 6.3015 |
66
+ | 0.0005 | 7.0 | 1099 | 0.0269 | 18.7506 | 6.0729 |
67
+ | 0.0003 | 8.0 | 1256 | 0.0312 | 19.6791 | 6.2471 |
68
+ | 0.0002 | 9.0 | 1413 | 0.0295 | 18.7173 | 5.8815 |
69
+ | 0.0001 | 10.0 | 1570 | 0.0315 | 18.4363 | 6.0391 |
70
+ | 0.0 | 11.0 | 1727 | 0.0312 | 18.0649 | 6.0058 |
71
+ | 0.0 | 12.0 | 1884 | 0.0322 | 16.8984 | 5.4943 |
72
+ | 0.0 | 13.0 | 2041 | 0.0326 | 16.6698 | 5.4460 |
73
+ | 0.0 | 14.0 | 2198 | 0.0329 | 16.3889 | 5.2413 |
74
+ | 0.0 | 14.9088 | 2340 | 0.0330 | 16.3175 | 5.2302 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a525fe7c7af14c1c97a92ad31c63d87322340d267a65205d8cf193d9611eb8aa
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ede774bb40d8feeda047d110c81f1312d19b57bd68837f8b1c3594c19a48a6
3
  size 151061672
runs/Feb23_07-05-50_226a498da3f2/events.out.tfevents.1740319250.226a498da3f2.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8adcd3ed85c64141aab153d28aa528ebd8ecf26cc63a79b26fbef099d03c32af
3
+ size 453