Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_tiny

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
486b63a
·
verified ·
1 Parent(s): 6a24cc0

Training finished

Browse files
Files changed (3) hide show
  1. README.md +18 -18
  2. model.safetensors +1 -1
  3. runs/Feb01_04-43-14_b0d1bca5a632/events.out.tfevents.1738409065.b0d1bca5a632.18.1 +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: 0.0064
24
- - Wer: 0.0813
25
- - Cer: 0.0322
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
- | 0.0056 | 1.0 | 469 | 0.0061 | 0.0813 | 0.0325 |
61
- | 0.0054 | 2.0 | 938 | 0.0057 | 0.0748 | 0.0289 |
62
- | 0.0038 | 3.0 | 1407 | 0.0058 | 0.0720 | 0.0274 |
63
- | 0.0018 | 4.0 | 1876 | 0.0061 | 0.0735 | 0.0285 |
64
- | 0.0034 | 5.0 | 2345 | 0.0064 | 0.0737 | 0.0283 |
65
- | 0.0011 | 6.0 | 2814 | 0.0069 | 0.1537 | 0.0660 |
66
- | 0.0006 | 7.0 | 3283 | 0.0071 | 0.1546 | 0.0663 |
67
- | 0.0007 | 8.0 | 3752 | 0.0076 | 0.1535 | 0.0654 |
68
- | 0.0006 | 9.0 | 4221 | 0.0078 | 0.0764 | 0.0301 |
69
- | 0.0002 | 10.0 | 4690 | 0.0081 | 0.0757 | 0.0287 |
70
- | 0.0003 | 11.0 | 5159 | 0.0084 | 0.0786 | 0.0313 |
71
- | 0.0003 | 12.0 | 5628 | 0.0085 | 0.0737 | 0.0287 |
72
- | 0.0003 | 13.0 | 6097 | 0.0087 | 0.0755 | 0.0297 |
73
- | 0.0001 | 14.0 | 6566 | 0.0104 | 0.0799 | 0.0323 |
74
- | 0.0001 | 15.0 | 7035 | 0.0088 | 0.0738 | 0.0293 |
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: 0.0061
24
+ - Wer: 0.0788
25
+ - Cer: 0.0318
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.008 | 1.0 | 469 | 0.0055 | 0.0719 | 0.0275 |
61
+ | 0.0064 | 2.0 | 938 | 0.0054 | 0.0776 | 0.0285 |
62
+ | 0.0047 | 3.0 | 1407 | 0.0056 | 0.0711 | 0.0268 |
63
+ | 0.0046 | 4.0 | 1876 | 0.0059 | 0.0740 | 0.0275 |
64
+ | 0.0026 | 5.0 | 2345 | 0.0062 | 0.0726 | 0.0262 |
65
+ | 0.0018 | 6.0 | 2814 | 0.0066 | 0.0749 | 0.0299 |
66
+ | 0.001 | 7.0 | 3283 | 0.0070 | 0.0762 | 0.0293 |
67
+ | 0.001 | 8.0 | 3752 | 0.0074 | 0.0776 | 0.0306 |
68
+ | 0.0005 | 9.0 | 4221 | 0.0077 | 0.0766 | 0.0299 |
69
+ | 0.0007 | 10.0 | 4690 | 0.0079 | 0.0760 | 0.0305 |
70
+ | 0.0004 | 11.0 | 5159 | 0.0082 | 0.0766 | 0.0300 |
71
+ | 0.0002 | 12.0 | 5628 | 0.0084 | 0.0775 | 0.0310 |
72
+ | 0.0001 | 13.0 | 6097 | 0.0085 | 0.0755 | 0.0295 |
73
+ | 0.0001 | 14.0 | 6566 | 0.0100 | 0.0935 | 0.0394 |
74
+ | 0.0002 | 15.0 | 7035 | 0.0086 | 0.0758 | 0.0300 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ef057ff168643e0c0759aaca7d8d9bd4800f32082c4f5912c76deaed5f318cc
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b12223d1fdf68abb27abfa96c7c63fe4bdc2d29e62823d7ac0f60b84d14728
3
  size 151061672
runs/Feb01_04-43-14_b0d1bca5a632/events.out.tfevents.1738409065.b0d1bca5a632.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b86e51d3c8819294ba6854c2d4d9beaa44a65fddb0c9085c7b14ccf6758afa8
3
+ size 453