Hugging Face's logo

Baselhany
/
Distilation_Whisper_base_CKP_256

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
96bd519
·
verified ·
1 Parent(s): 7faf65f

Model save

Browse files
Files changed (3) hide show
  1. README.md +15 -44
  2. model.safetensors +1 -1
  3. runs/Jun10_22-27-30_fe8a168c7f1c/events.out.tfevents.1749619772.fe8a168c7f1c.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: 0.0895
24
- - Wer: 0.2050
25
 
26
  ## Model description
27
 
@@ -49,46 +47,19 @@ 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: 20
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Wer |
58
- |:-------------:|:-------:|:-----:|:---------------:|:------:|
59
- | 3.2982 | 0.5928 | 1000 | 0.1013 | 0.2140 |
60
- | 2.442 | 1.1855 | 2000 | 0.1004 | 0.2026 |
61
- | 2.4875 | 1.7783 | 3000 | 0.0967 | 0.1972 |
62
- | 1.7274 | 2.3711 | 4000 | 0.0925 | 0.1963 |
63
- | 1.8653 | 2.9638 | 5000 | 0.0941 | 0.2039 |
64
- | 1.5181 | 3.5566 | 6000 | 0.0921 | 0.2011 |
65
- | 1.4064 | 4.1494 | 7000 | 0.0911 | 0.2023 |
66
- | 1.3914 | 4.7421 | 8000 | 0.0905 | 0.1998 |
67
- | 1.2463 | 5.3349 | 9000 | 0.0891 | 0.2022 |
68
- | 1.2122 | 5.9277 | 10000 | 0.0896 | 0.2093 |
69
- | 1.4104 | 6.5205 | 11000 | 0.0912 | 0.2007 |
70
- | 1.2912 | 7.1132 | 12000 | 0.0902 | 0.1958 |
71
- | 1.2074 | 7.7060 | 13000 | 0.0907 | 0.1988 |
72
- | 1.1992 | 8.2988 | 14000 | 0.0895 | 0.2016 |
73
- | 1.0971 | 8.8915 | 15000 | 0.0902 | 0.2028 |
74
- | 1.1248 | 9.4843 | 16000 | 0.0897 | 0.2019 |
75
- | 0.9882 | 10.0771 | 17000 | 0.0885 | 0.1967 |
76
- | 1.0489 | 10.6698 | 18000 | 0.0881 | 0.2009 |
77
- | 0.9598 | 11.2626 | 19000 | 0.0881 | 0.2026 |
78
- | 1.059 | 11.8554 | 20000 | 0.0881 | 0.1995 |
79
- | 1.0843 | 12.4481 | 21000 | 0.0884 | 0.1979 |
80
- | 1.0189 | 13.0409 | 22000 | 0.0878 | 0.2056 |
81
- | 1.0068 | 13.6337 | 23000 | 0.0883 | 0.2032 |
82
- | 0.9681 | 14.2264 | 24000 | 0.0875 | 0.1986 |
83
- | 1.001 | 14.8192 | 25000 | 0.0877 | 0.2051 |
84
- | 0.9266 | 15.4120 | 26000 | 0.0868 | 0.2010 |
85
- | 0.9837 | 16.0047 | 27000 | 0.0872 | 0.2103 |
86
- | 0.8382 | 16.5975 | 28000 | 0.0871 | 0.2003 |
87
- | 0.8399 | 17.1903 | 29000 | 0.0872 | 0.1989 |
88
- | 0.8303 | 17.7830 | 30000 | 0.0871 | 0.2022 |
89
- | 0.8621 | 18.3758 | 31000 | 0.0872 | 0.2022 |
90
- | 0.8784 | 18.9686 | 32000 | 0.0872 | 0.2066 |
91
- | 0.8448 | 19.5614 | 33000 | 0.0868 | 0.2076 |
92
 
93
 
94
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
+ base_model: Baselhany/Distilation_Whisper_base_CKP_256
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: Distilation_Whisper_base_CKP_256
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
+ # Distilation_Whisper_base_CKP_256
18
 
19
+ This model is a fine-tuned version of [Baselhany/Distilation_Whisper_base_CKP_256](https://huggingface.co/Baselhany/Distilation_Whisper_base_CKP_256) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0905
22
+ - Wer: 0.1969
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: 4
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:------:|:----:|:---------------:|:------:|
57
+ | 2.0599 | 0.5858 | 1000 | 0.0910 | 0.2075 |
58
+ | 1.6156 | 1.1716 | 2000 | 0.0921 | 0.1917 |
59
+ | 1.5706 | 1.7575 | 3000 | 0.0891 | 0.1953 |
60
+ | 1.3401 | 2.3433 | 4000 | 0.0880 | 0.1882 |
61
+ | 1.2238 | 2.9291 | 5000 | 0.0865 | 0.1886 |
62
+ | 1.0654 | 3.5149 | 6000 | 0.0860 | 0.1922 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22ed954debda92c12b08cad501c44cf0d59f2474db371faeac022b91e87624fb
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06fa4886aea25ab47be29a70fc8c88bda6ed83bd437094b888a20f51db970665
3
  size 223144592
runs/Jun10_22-27-30_fe8a168c7f1c/events.out.tfevents.1749619772.fe8a168c7f1c.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13bdfed66ff5d12268f6b9baebecb01458930128f66ba28e79467653d7c5a764
3
+ size 406