Hugging Face's logo

raghadOmar
/
whisper-base-quran

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
raghadOmar commited on
Commit
90d91bc
•
1 Parent(s): 7868a70

End of training

Browse files
Files changed (2) hide show
  1. README.md +22 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -2,38 +2,38 @@
2
  language:
3
  - ar
4
  license: apache-2.0
 
5
  tags:
6
  - generated_from_trainer
7
- base_model: tarteel-ai/whisper-base-ar-quran
8
  datasets:
9
  - zolfa
10
  metrics:
11
  - wer
12
  model-index:
13
- - name: Whisper-raghadomar
14
  results:
15
  - task:
16
- type: automatic-speech-recognition
17
  name: Automatic Speech Recognition
 
18
  dataset:
19
  name: Zolfa Dataset
20
  type: zolfa
21
  args: 'config: ar, split: test'
22
  metrics:
23
- - type: wer
24
- value: 6.896551724137931
25
- name: Wer
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
- # Whisper-raghadomar
32
 
33
- This model is a fine-tuned version of [tarteel-ai/whisper-base-ar-quran](https://huggingface.co/tarteel-ai/whisper-base-ar-quran) on the Zolfa Dataset dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.0208
36
- - Wer: 6.8966
37
 
38
  ## Model description
39
 
@@ -64,18 +64,18 @@ The following hyperparameters were used during training:
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Wer |
68
- |:-------------:|:------:|:----:|:---------------:|:------:|
69
- | 0.0191 | 0.7143 | 100 | 0.0403 | 6.8966 |
70
- | 0.0065 | 1.4286 | 200 | 0.0149 | 6.8966 |
71
- | 0.009 | 2.1429 | 300 | 0.0263 | 6.8966 |
72
- | 0.0106 | 2.8571 | 400 | 0.0417 | 6.8966 |
73
- | 0.0011 | 3.5714 | 500 | 0.0195 | 6.8966 |
74
- | 0.0028 | 4.2857 | 600 | 0.0223 | 6.8966 |
75
- | 0.0001 | 5.0 | 700 | 0.0188 | 6.8966 |
76
- | 0.0017 | 5.7143 | 800 | 0.0212 | 6.8966 |
77
- | 0.0001 | 6.4286 | 900 | 0.0199 | 6.8966 |
78
- | 0.0009 | 7.1429 | 1000 | 0.0208 | 6.8966 |
79
 
80
 
81
  ### Framework versions
 
2
  language:
3
  - ar
4
  license: apache-2.0
5
+ base_model: openai/whisper-small
6
  tags:
7
  - generated_from_trainer
 
8
  datasets:
9
  - zolfa
10
  metrics:
11
  - wer
12
  model-index:
13
+ - name: Zolfa-raghadomar
14
  results:
15
  - task:
 
16
  name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
  dataset:
19
  name: Zolfa Dataset
20
  type: zolfa
21
  args: 'config: ar, split: test'
22
  metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 8.571428571428571
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
+ # Zolfa-raghadomar
32
 
33
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Zolfa Dataset dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.2371
36
+ - Wer: 8.5714
37
 
38
  ## Model description
39
 
 
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
69
+ | 0.0671 | 0.6993 | 100 | 0.2041 | 12.8571 |
70
+ | 0.0247 | 1.3986 | 200 | 0.2290 | 10.4082 |
71
+ | 0.0071 | 2.0979 | 300 | 0.2219 | 9.7959 |
72
+ | 0.0102 | 2.7972 | 400 | 0.2215 | 26.9388 |
73
+ | 0.0046 | 3.4965 | 500 | 0.2192 | 8.5714 |
74
+ | 0.005 | 4.1958 | 600 | 0.2401 | 9.1837 |
75
+ | 0.0074 | 4.8951 | 700 | 0.2296 | 7.9592 |
76
+ | 0.0006 | 5.5944 | 800 | 0.2363 | 9.1837 |
77
+ | 0.0002 | 6.2937 | 900 | 0.2366 | 8.5714 |
78
+ | 0.0013 | 6.9930 | 1000 | 0.2371 | 8.5714 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf0e2d97399502442ac679edf810b5fd2366b3b4f77e7cdede3215b04a13b5f5
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c2f59d43ef1a593d2dfce80b8bdb1153d81bb7931705228f3af4aec17b778c
3
  size 966995080