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
642b63e
•
1 Parent(s): 9da9558

End of training

Browse files
Files changed (3) hide show
  1. README.md +21 -21
  2. model.safetensors +1 -1
  3. runs/Jun12_12-20-04_95dcb20b6505/events.out.tfevents.1718194810.95dcb20b6505.398.0 +2 -2
README.md CHANGED
@@ -2,9 +2,9 @@
2
  language:
3
  - ar
4
  license: apache-2.0
 
5
  tags:
6
  - generated_from_trainer
7
- base_model: openai/whisper-small
8
  datasets:
9
  - zolfa
10
  metrics:
@@ -13,16 +13,16 @@ model-index:
13
  - name: Zolfa-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: 8.571428571428571
25
- name: Wer
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ 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: 0.2396
36
- - Wer: 8.5714
37
 
38
  ## Model description
39
 
@@ -53,7 +53,7 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 1e-05
56
- - train_batch_size: 4
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -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
- | 0.0673 | 0.6993 | 100 | 0.2047 | 12.8571 |
70
- | 0.0239 | 1.3986 | 200 | 0.2376 | 10.4082 |
71
- | 0.0087 | 2.0979 | 300 | 0.2165 | 9.7959 |
72
- | 0.009 | 2.7972 | 400 | 0.2169 | 7.9592 |
73
- | 0.0034 | 3.4965 | 500 | 0.2277 | 8.5714 |
74
- | 0.0041 | 4.1958 | 600 | 0.2401 | 8.5714 |
75
- | 0.0032 | 4.8951 | 700 | 0.2395 | 7.9592 |
76
- | 0.0007 | 5.5944 | 800 | 0.2430 | 8.5714 |
77
- | 0.0002 | 6.2937 | 900 | 0.2380 | 8.5714 |
78
- | 0.0015 | 6.9930 | 1000 | 0.2396 | 8.5714 |
79
 
80
 
81
  ### Framework versions
 
2
  language:
3
  - ar
4
  license: apache-2.0
5
+ base_model: tarteel-ai/whisper-base-ar-quran
6
  tags:
7
  - generated_from_trainer
 
8
  datasets:
9
  - zolfa
10
  metrics:
 
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: 5.263157894736842
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # Zolfa-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: 0.0157
36
+ - Wer: 5.2632
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 1e-05
56
+ - train_batch_size: 16
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-------:|:----:|:---------------:|:------:|
69
+ | 0.0155 | 2.8571 | 100 | 0.0156 | 5.2632 |
70
+ | 0.0037 | 5.7143 | 200 | 0.0199 | 5.2632 |
71
+ | 0.0011 | 8.5714 | 300 | 0.0175 | 5.2632 |
72
+ | 0.0006 | 11.4286 | 400 | 0.0123 | 5.2632 |
73
+ | 0.0003 | 14.2857 | 500 | 0.0187 | 5.2632 |
74
+ | 0.0001 | 17.1429 | 600 | 0.0126 | 5.2632 |
75
+ | 0.0001 | 20.0 | 700 | 0.0159 | 5.2632 |
76
+ | 0.0002 | 22.8571 | 800 | 0.0137 | 5.2632 |
77
+ | 0.0001 | 25.7143 | 900 | 0.0149 | 5.2632 |
78
+ | 0.0001 | 28.5714 | 1000 | 0.0157 | 5.2632 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba6078ae819680532a3c434dccadefd8ef6d932a3c497092fa77245bb2c781c1
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0304e31e12da59387abda9999e9e64bc88dbcdbceb81548c5c7965ce1e406bfd
3
  size 966995080
runs/Jun12_12-20-04_95dcb20b6505/events.out.tfevents.1718194810.95dcb20b6505.398.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed06d506c2bef5a2a3e94bb49ee39b12a4712c1841ab05f412bf80f3ab01850f
3
- size 19450
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a25648e7d017268455c7244c63aaaa5c5a5cc1a185237ba2d26aae6b27107d
3
+ size 19804