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
d50f355
·
verified ·
1 Parent(s): ef24758

Training finished

Browse files
Files changed (3) hide show
  1. README.md +19 -19
  2. model.safetensors +1 -1
  3. runs/Feb01_12-44-16_5236a4d7f575/events.out.tfevents.1738448302.5236a4d7f575.18.1 +3 -0
README.md CHANGED
@@ -21,8 +21,8 @@ should probably proofread and complete it, then remove this comment. -->
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
 
@@ -55,23 +55,23 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
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
 
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: 0.0763
25
+ - Cer: 0.0310
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.0046 | 1.0 | 701 | 0.0052 | 0.0782 | 0.0297 |
61
+ | 0.0035 | 2.0 | 1402 | 0.0049 | 0.0717 | 0.0281 |
62
+ | 0.0036 | 3.0 | 2103 | 0.0052 | 0.0719 | 0.0290 |
63
+ | 0.0026 | 4.0 | 2804 | 0.0055 | 0.0671 | 0.0267 |
64
+ | 0.0012 | 5.0 | 3505 | 0.0058 | 0.0699 | 0.0275 |
65
+ | 0.0017 | 6.0 | 4206 | 0.0062 | 0.0691 | 0.0283 |
66
+ | 0.0012 | 7.0 | 4907 | 0.0067 | 0.0710 | 0.0285 |
67
+ | 0.0007 | 8.0 | 5608 | 0.0071 | 0.0681 | 0.0273 |
68
+ | 0.0005 | 9.0 | 6309 | 0.0075 | 0.0704 | 0.0287 |
69
+ | 0.0005 | 10.0 | 7010 | 0.0077 | 0.0695 | 0.0278 |
70
+ | 0.0003 | 11.0 | 7711 | 0.0079 | 0.0693 | 0.0270 |
71
+ | 0.0001 | 12.0 | 8412 | 0.0080 | 0.0728 | 0.0285 |
72
+ | 0.0002 | 13.0 | 9113 | 0.0081 | 0.0738 | 0.0289 |
73
+ | 0.0002 | 14.0 | 9814 | 0.0093 | 0.0770 | 0.0318 |
74
+ | 0.0001 | 14.9793 | 10500 | 0.0083 | 0.0717 | 0.0284 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eef5e4079d96e1cf29a419ea54cd053c877fd30d8a8907aef133498e118e1070
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b284a0d46cd7eff216d7a6c31e7143c55695bb4a62e28c832e514cb39808fc4f
3
  size 151061672
runs/Feb01_12-44-16_5236a4d7f575/events.out.tfevents.1738448302.5236a4d7f575.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db01f55193bebac335adbf4185ae680bb25927f56f39aad6886b1309e9856405
3
+ size 453