Hugging Face's logo

Baselhany
/
Graduation_Project_Distilation_Whisper_base3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
38eb21c
·
verified ·
1 Parent(s): c74036d

Model save

Browse files
Files changed (3) hide show
  1. README.md +27 -24
  2. model.safetensors +1 -1
  3. runs/Jun14_05-24-33_63c55713f97e/events.out.tfevents.1749903073.63c55713f97e.19.1 +3 -0
README.md CHANGED
@@ -1,27 +1,25 @@
1
  ---
2
  library_name: transformers
3
- language:
4
- - ar
5
  license: apache-2.0
6
- base_model: openai/whisper-base
7
  tags:
8
  - generated_from_trainer
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: Whisper base AR - BA
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # Whisper base AR - BA
20
 
21
- This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0867
24
- - Wer: 0.1925
25
 
26
  ## Model description
27
 
@@ -49,28 +47,33 @@ The following hyperparameters were used during training:
49
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 500
52
- - num_epochs: 15
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Wer |
58
  |:-------------:|:-------:|:----:|:---------------:|:------:|
59
- | 1.7381 | 1.0 | 469 | 0.0864 | 0.1945 |
60
- | 1.6182 | 2.0 | 938 | 0.0902 | 0.2013 |
61
- | 1.2194 | 3.0 | 1407 | 0.0893 | 0.1911 |
62
- | 1.0951 | 4.0 | 1876 | 0.0881 | 0.2001 |
63
- | 1.0233 | 5.0 | 2345 | 0.0867 | 0.1979 |
64
- | 0.9062 | 6.0 | 2814 | 0.0864 | 0.1995 |
65
- | 0.8866 | 7.0 | 3283 | 0.0852 | 0.1992 |
66
- | 0.8074 | 8.0 | 3752 | 0.0858 | 0.1922 |
67
- | 0.7585 | 9.0 | 4221 | 0.0853 | 0.1882 |
68
- | 0.6978 | 10.0 | 4690 | 0.0849 | 0.1911 |
69
- | 0.6625 | 11.0 | 5159 | 0.0845 | 0.1901 |
70
- | 0.6375 | 12.0 | 5628 | 0.0839 | 0.1861 |
71
- | 0.6057 | 13.0 | 6097 | 0.0838 | 0.1883 |
72
- | 0.5872 | 14.0 | 6566 | 0.0839 | 0.1895 |
73
- | 0.5605 | 14.9685 | 7020 | 0.0838 | 0.1891 |
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
+ base_model: Baselhany/Graduation_Project_Distilation_Whisper_base3
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: Graduation_Project_Distilation_Whisper_base3
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # Graduation_Project_Distilation_Whisper_base3
18
 
19
+ This model is a fine-tuned version of [Baselhany/Graduation_Project_Distilation_Whisper_base3](https://huggingface.co/Baselhany/Graduation_Project_Distilation_Whisper_base3) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0890
22
+ - Wer: 0.1942
23
 
24
  ## Model description
25
 
 
47
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 500
50
+ - num_epochs: 20
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:-------:|:----:|:---------------:|:------:|
57
+ | 1.7224 | 1.0 | 301 | 0.0867 | 0.1888 |
58
+ | 1.6242 | 2.0 | 602 | 0.0876 | 0.1970 |
59
+ | 1.3485 | 3.0 | 903 | 0.0880 | 0.1932 |
60
+ | 1.2337 | 4.0 | 1204 | 0.0895 | 0.1872 |
61
+ | 1.0669 | 5.0 | 1505 | 0.0861 | 0.1932 |
62
+ | 1.0507 | 6.0 | 1806 | 0.0855 | 0.1829 |
63
+ | 0.9844 | 7.0 | 2107 | 0.0861 | 0.1892 |
64
+ | 0.8618 | 8.0 | 2408 | 0.0844 | 0.1873 |
65
+ | 0.7956 | 9.0 | 2709 | 0.0849 | 0.1964 |
66
+ | 0.7654 | 10.0 | 3010 | 0.0842 | 0.1895 |
67
+ | 0.6957 | 11.0 | 3311 | 0.0843 | 0.1848 |
68
+ | 0.7042 | 12.0 | 3612 | 0.0837 | 0.1866 |
69
+ | 0.6364 | 13.0 | 3913 | 0.0831 | 0.1929 |
70
+ | 0.6357 | 14.0 | 4214 | 0.0829 | 0.1895 |
71
+ | 0.6137 | 15.0 | 4515 | 0.0827 | 0.1904 |
72
+ | 0.5909 | 16.0 | 4816 | 0.0824 | 0.1904 |
73
+ | 0.5582 | 17.0 | 5117 | 0.0823 | 0.1941 |
74
+ | 0.5409 | 18.0 | 5418 | 0.0824 | 0.1916 |
75
+ | 0.5305 | 19.0 | 5719 | 0.0823 | 0.1895 |
76
+ | 0.5137 | 19.9343 | 6000 | 0.0824 | 0.1902 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3053e9f3e01b124d5d6708a0a22e2f65b35117ca18a5928258ff45f0b3918df6
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1cdf51c8cb89a834b399b6bb17d59963d682eebc6019c89755ecb0ec40dafd4
3
  size 223144592
runs/Jun14_05-24-33_63c55713f97e/events.out.tfevents.1749903073.63c55713f97e.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a331c4853716e214e1e866922ccdbd0162709de6f7f8d6a5c86c9542310c39bf
3
+ size 406