Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_tiny2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
ae802b4
·
verified ·
1 Parent(s): 57f6997

Training finished

Browse files
Files changed (3) hide show
  1. README.md +14 -9
  2. model.safetensors +1 -1
  3. runs/Jan03_09-48-51_1418d86e4f8f/events.out.tfevents.1735907053.1418d86e4f8f.40.1 +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: 0.0145
24
- - Wer: 0.0963
25
- - Cer: 0.0363
26
 
27
  ## Model description
28
 
@@ -50,18 +50,23 @@ The following hyperparameters were used during training:
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 500
53
- - num_epochs: 5
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0011 | 1.0 | 219 | 0.0134 | 0.1178 | 0.0421 |
61
- | 0.0004 | 2.0 | 438 | 0.0136 | 0.1097 | 0.0399 |
62
- | 0.0001 | 3.0 | 657 | 0.0141 | 0.1062 | 0.0390 |
63
- | 0.0 | 4.0 | 876 | 0.0145 | 0.0963 | 0.0363 |
64
- | 0.0 | 5.0 | 1095 | 0.0146 | 0.0976 | 0.0346 |
 
 
 
 
 
65
 
66
 
67
  ### 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: 0.0131
24
+ - Wer: 0.0884
25
+ - Cer: 0.0343
26
 
27
  ## Model description
28
 
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - lr_scheduler_warmup_steps: 500
53
+ - num_epochs: 10
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0061 | 1.0 | 219 | 0.0133 | 0.0986 | 0.0357 |
61
+ | 0.0054 | 2.0 | 438 | 0.0099 | 0.0959 | 0.0354 |
62
+ | 0.0054 | 3.0 | 657 | 0.0093 | 0.1008 | 0.0372 |
63
+ | 0.0019 | 4.0 | 876 | 0.0106 | 0.0945 | 0.0341 |
64
+ | 0.0014 | 5.0 | 1095 | 0.0115 | 0.0936 | 0.0350 |
65
+ | 0.0011 | 6.0 | 1314 | 0.0120 | 0.0918 | 0.0323 |
66
+ | 0.0002 | 7.0 | 1533 | 0.0125 | 0.0950 | 0.0340 |
67
+ | 0.0001 | 8.0 | 1752 | 0.0129 | 0.0914 | 0.0316 |
68
+ | 0.0001 | 9.0 | 1971 | 0.0131 | 0.0884 | 0.0343 |
69
+ | 0.0001 | 10.0 | 2190 | 0.0132 | 0.0909 | 0.0317 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1f8d74dc50e9f8635cd33117e493df751cff46e534f198be95108c7c884c9a9
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42cfdaf8af10c5996972719a78ea991704e95235d931617db996d6c54e12c56
3
  size 151061672
runs/Jan03_09-48-51_1418d86e4f8f/events.out.tfevents.1735907053.1418d86e4f8f.40.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f077938493d2fa91ee4010471ad7971af14394d869faf37f42b1aabaf30c4567
3
+ size 453