Hugging Face's logo

Baselhany
/
Distilation_Whisper_base_CKP

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
fcff4ae
·
verified ·
1 Parent(s): 4f2a98c

Model save

Browse files
Files changed (3) hide show
  1. README.md +36 -28
  2. model.safetensors +1 -1
  3. runs/Jun02_04-39-50_09e2856230c8/events.out.tfevents.1748877140.09e2856230c8.19.1 +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: 0.0870
24
- - Wer: 0.1935
25
 
26
  ## Model description
27
 
@@ -49,30 +47,40 @@ 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: 10
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Wer |
58
- |:-------------:|:------:|:-----:|:---------------:|:------:|
59
- | 2.1291 | 0.5858 | 1000 | 0.0912 | 0.1978 |
60
- | 1.7057 | 1.1716 | 2000 | 0.0912 | 0.2003 |
61
- | 1.7162 | 1.7575 | 3000 | 0.0912 | 0.2060 |
62
- | 1.4996 | 2.3433 | 4000 | 0.0901 | 0.2047 |
63
- | 1.3942 | 2.9291 | 5000 | 0.0883 | 0.1951 |
64
- | 1.2285 | 3.5149 | 6000 | 0.0876 | 0.1957 |
65
- | 1.0637 | 4.1008 | 7000 | 0.0873 | 0.1920 |
66
- | 1.1144 | 4.6866 | 8000 | 0.0865 | 0.1927 |
67
- | 1.0164 | 5.2724 | 9000 | 0.0858 | 0.1923 |
68
- | 0.9812 | 5.8582 | 10000 | 0.0856 | 0.1941 |
69
- | 0.8927 | 6.4441 | 11000 | 0.0849 | 0.2017 |
70
- | 0.8936 | 7.0299 | 12000 | 0.0844 | 0.1961 |
71
- | 0.8718 | 7.6157 | 13000 | 0.0854 | 0.1979 |
72
- | 0.9019 | 8.2015 | 14000 | 0.0847 | 0.1854 |
73
- | 0.8293 | 8.7873 | 15000 | 0.0847 | 0.1983 |
74
- | 0.8363 | 9.3732 | 16000 | 0.0842 | 0.1982 |
75
- | 0.8034 | 9.9590 | 17000 | 0.0840 | 0.1975 |
 
 
 
 
 
 
 
 
 
 
76
 
77
 
78
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
+ base_model: Baselhany/Distilation_Whisper_base_CKP
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: Distilation_Whisper_base_CKP
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
18
 
19
+ This model is a fine-tuned version of [Baselhany/Distilation_Whisper_base_CKP](https://huggingface.co/Baselhany/Distilation_Whisper_base_CKP) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0858
22
+ - Wer: 0.1940
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: 16
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
57
+ | 2.1291 | 0.5858 | 1000 | 0.0912 | 0.1978 |
58
+ | 1.7057 | 1.1716 | 2000 | 0.0912 | 0.2003 |
59
+ | 1.7162 | 1.7575 | 3000 | 0.0912 | 0.2060 |
60
+ | 1.4996 | 2.3433 | 4000 | 0.0901 | 0.2047 |
61
+ | 1.3942 | 2.9291 | 5000 | 0.0883 | 0.1951 |
62
+ | 1.2285 | 3.5149 | 6000 | 0.0876 | 0.1957 |
63
+ | 1.0637 | 4.1008 | 7000 | 0.0873 | 0.1920 |
64
+ | 1.1144 | 4.6866 | 8000 | 0.0865 | 0.1927 |
65
+ | 1.0164 | 5.2724 | 9000 | 0.0858 | 0.1923 |
66
+ | 0.9812 | 5.8582 | 10000 | 0.0856 | 0.1941 |
67
+ | 0.8927 | 6.4441 | 11000 | 0.0849 | 0.2017 |
68
+ | 0.8936 | 7.0299 | 12000 | 0.0844 | 0.1961 |
69
+ | 0.8718 | 7.6157 | 13000 | 0.0854 | 0.1979 |
70
+ | 0.9019 | 8.2015 | 14000 | 0.0847 | 0.1854 |
71
+ | 0.8293 | 8.7873 | 15000 | 0.0847 | 0.1983 |
72
+ | 0.8363 | 9.3732 | 16000 | 0.0842 | 0.1982 |
73
+ | 0.8034 | 9.9590 | 17000 | 0.0840 | 0.1975 |
74
+ | 0.8462 | 10.5448 | 18000 | 0.0855 | 0.1953 |
75
+ | 0.8824 | 11.1306 | 19000 | 0.0848 | 0.1930 |
76
+ | 0.8591 | 11.7165 | 20000 | 0.0849 | 0.1838 |
77
+ | 0.8339 | 12.3023 | 21000 | 0.0842 | 0.1863 |
78
+ | 0.8573 | 12.8881 | 22000 | 0.0836 | 0.1926 |
79
+ | 0.7445 | 13.4739 | 23000 | 0.0839 | 0.1842 |
80
+ | 0.783 | 14.0598 | 24000 | 0.0836 | 0.1842 |
81
+ | 0.7263 | 14.6456 | 25000 | 0.0839 | 0.1824 |
82
+ | 0.7634 | 15.2314 | 26000 | 0.0835 | 0.1826 |
83
+ | 0.7379 | 15.8172 | 27000 | 0.0834 | 0.1829 |
84
 
85
 
86
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8697dd2e30554939f3fdca476e8f8c14ef00252787d6ed337c4f9c24c9f4e2e
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b547caa72cf268ef3220b2e4b72f19c8fd48492a4c17a145c1528e1131fd251c
3
  size 223144592
runs/Jun02_04-39-50_09e2856230c8/events.out.tfevents.1748877140.09e2856230c8.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b47203d276069da117cfcf2c8aa00715bdfa7953cdd681dcae3d635a8a8a30e
3
+ size 412