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
5ee9478
·
verified ·
1 Parent(s): 2f809b3

Model save

Browse files
Files changed (4) hide show
  1. README.md +25 -27
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Jun12_21-07-13_9dde9cac7102/events.out.tfevents.1749789513.9dde9cac7102.19.1 +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: 0.0928
24
- - Wer: 0.2043
25
 
26
  ## Model description
27
 
@@ -56,26 +54,26 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Wer |
58
  |:-------------:|:-------:|:----:|:---------------:|:------:|
59
- | 1.2944 | 1.0 | 313 | 0.0886 | 0.1967 |
60
- | 1.2819 | 2.0 | 626 | 0.0902 | 0.1923 |
61
- | 1.2752 | 3.0 | 939 | 0.0902 | 0.1986 |
62
- | 1.1425 | 4.0 | 1252 | 0.0915 | 0.1989 |
63
- | 1.0812 | 5.0 | 1565 | 0.0900 | 0.1914 |
64
- | 0.9708 | 6.0 | 1878 | 0.0900 | 0.1916 |
65
- | 0.9029 | 7.0 | 2191 | 0.0891 | 0.1985 |
66
- | 0.8248 | 8.0 | 2504 | 0.0896 | 0.1916 |
67
- | 0.7778 | 9.0 | 2817 | 0.0897 | 0.1941 |
68
- | 0.7485 | 10.0 | 3130 | 0.0890 | 0.1944 |
69
- | 0.7219 | 11.0 | 3443 | 0.0883 | 0.1961 |
70
- | 0.6584 | 12.0 | 3756 | 0.0889 | 0.1948 |
71
- | 0.6516 | 13.0 | 4069 | 0.0883 | 0.1951 |
72
- | 0.6233 | 14.0 | 4382 | 0.0882 | 0.1942 |
73
- | 0.6017 | 14.9536 | 4680 | 0.0883 | 0.1957 |
74
 
75
 
76
  ### Framework versions
77
 
78
- - Transformers 4.51.1
79
- - Pytorch 2.5.1+cu124
80
- - Datasets 3.5.0
81
- - Tokenizers 0.21.0
 
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: 0.0917
22
+ - Wer: 0.1973
23
 
24
  ## Model description
25
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:-------:|:----:|:---------------:|:------:|
57
+ | 1.9509 | 1.0 | 469 | 0.0928 | 0.1966 |
58
+ | 1.9061 | 2.0 | 938 | 0.0938 | 0.1901 |
59
+ | 1.4524 | 3.0 | 1407 | 0.0919 | 0.1916 |
60
+ | 1.3809 | 4.0 | 1876 | 0.0914 | 0.1951 |
61
+ | 1.1397 | 5.0 | 2345 | 0.0906 | 0.1969 |
62
+ | 1.0984 | 6.0 | 2814 | 0.0895 | 0.1897 |
63
+ | 1.0229 | 7.0 | 3283 | 0.0892 | 0.1939 |
64
+ | 0.898 | 8.0 | 3752 | 0.0879 | 0.1969 |
65
+ | 0.8656 | 9.0 | 4221 | 0.0884 | 0.1886 |
66
+ | 0.7982 | 10.0 | 4690 | 0.0866 | 0.1929 |
67
+ | 0.7736 | 11.0 | 5159 | 0.0874 | 0.1933 |
68
+ | 0.7155 | 12.0 | 5628 | 0.0871 | 0.1967 |
69
+ | 0.6907 | 13.0 | 6097 | 0.0870 | 0.1911 |
70
+ | 0.6405 | 14.0 | 6566 | 0.0867 | 0.1894 |
71
+ | 0.6369 | 14.9685 | 7020 | 0.0868 | 0.1886 |
72
 
73
 
74
  ### Framework versions
75
 
76
+ - Transformers 4.51.3
77
+ - Pytorch 2.6.0+cu124
78
+ - Datasets 3.6.0
79
+ - Tokenizers 0.21.1
generation_config.json CHANGED
@@ -208,7 +208,7 @@
208
  "tie_word_embeddings": true,
209
  "tokenizer_class": null,
210
  "torchscript": false,
211
- "transformers_version": "4.51.1",
212
  "use_bfloat16": false,
213
  "use_weighted_layer_sum": false,
214
  "vocab_size": 51865
 
208
  "tie_word_embeddings": true,
209
  "tokenizer_class": null,
210
  "torchscript": false,
211
+ "transformers_version": "4.51.3",
212
  "use_bfloat16": false,
213
  "use_weighted_layer_sum": false,
214
  "vocab_size": 51865
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c45a80343ee7c9e98755a6270dc3590cb7aa14a33fd293650503c8806e4faf9
3
  size 223144592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f17a93fb18c373c9ee2a067db9b958cdcf51826fc0802fc09a695b5013033a9
3
  size 223144592
runs/Jun12_21-07-13_9dde9cac7102/events.out.tfevents.1749789513.9dde9cac7102.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db6f74e55a2f4383c3618542162dac8ae6d4596ad6c4a975b8b14a09aa6f6780
3
+ size 406