Hugging Face's logo

Baselhany
/
Quran_Whisper_base_fine_tune

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
26c2c09
·
verified ·
1 Parent(s): 6fba087

Training finished

Browse files
Files changed (2) hide show
  1. README.md +33 -30
  2. runs/Feb16_10-42-42_e07caf301fc1/events.out.tfevents.1739735119.e07caf301fc1.18.1 +3 -0
README.md CHANGED
@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.0150
24
- - Wer: 17.8382
25
- - Cer: 5.3725
26
 
27
  ## Model description
28
 
@@ -50,37 +50,40 @@ The following hyperparameters were used during training:
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: cosine
52
  - lr_scheduler_warmup_steps: 500
53
- - num_epochs: 6
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
59
- |:-------------:|:------:|:----:|:-------:|:---------------:|:-------:|
60
- | 0.0425 | 0.3011 | 400 | 11.2952 | 0.0330 | 37.6901 |
61
- | 0.0258 | 0.6023 | 800 | 7.9539 | 0.0218 | 25.4742 |
62
- | 0.0197 | 0.9034 | 1200 | 7.0188 | 0.0194 | 22.3362 |
63
- | 0.0083 | 1.2637 | 1600 | 6.1604 | 0.0183 | 20.2225 |
64
- | 0.0066 | 1.5794 | 2000 | 5.9469 | 0.0176 | 19.4205 |
65
- | 0.0065 | 1.8952 | 2400 | 5.8609 | 0.0174 | 19.0958 |
66
- | 0.0161 | 2.1084 | 2800 | 5.8786 | 0.0167 | 18.8094 |
67
- | 0.0157 | 2.4096 | 3200 | 5.6719 | 0.0162 | 18.4526 |
68
- | 0.0157 | 2.7107 | 3600 | 5.6150 | 0.0160 | 18.3772 |
69
- | 0.0063 | 3.1595 | 4000 | 5.4820 | 0.0160 | 18.0877 |
70
- | 0.0052 | 3.4752 | 4400 | 5.4747 | 0.0161 | 18.2023 |
71
- | 0.0049 | 3.7910 | 4800 | 5.5285 | 0.0161 | 17.9922 |
72
- | 0.0154 | 3.9155 | 5200 | 5.5457 | 0.0159 | 18.1641 |
73
- | 0.0142 | 4.2168 | 5600 | 5.4871 | 0.0158 | 17.9721 |
74
- | 0.0143 | 4.5180 | 6000 | 5.5382 | 0.0157 | 18.0495 |
75
- | 0.0155 | 4.8191 | 6400 | 5.4620 | 0.0156 | 17.9460 |
76
- | 0.005 | 5.3710 | 6800 | 5.4875 | 0.0157 | 17.7691 |
77
- | 0.0052 | 5.6868 | 7200 | 5.4416 | 0.0157 | 17.8646 |
78
- | 0.0085 | 4.8653 | 7600 | 5.5002 | 0.0157 | 17.8817 |
79
- | 0.0096 | 5.1216 | 8000 | 5.5124 | 0.0156 | 17.8264 |
80
- | 0.0094 | 5.3776 | 8400 | 5.6387 | 0.0155 | 17.7500 |
81
- | 0.0093 | 5.6336 | 8800 | 5.4429 | 0.0154 | 17.6736 |
82
- | 0.01 | 5.8896 | 9200 | 5.3128 | 0.0153 | 17.2856 |
83
- | 0.0091 | 6.1453 | 9600 | 5.2836 | 0.0153 | 17.2424 |
 
 
 
84
 
85
 
86
  ### Framework versions
 
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: 0.0151
24
+ - Wer: 17.8284
25
+ - Cer: 5.3577
26
 
27
  ## Model description
28
 
 
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: cosine
52
  - lr_scheduler_warmup_steps: 500
53
+ - num_epochs: 7
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
59
+ |:-------------:|:------:|:-----:|:-------:|:---------------:|:-------:|
60
+ | 0.0425 | 0.3011 | 400 | 11.2952 | 0.0330 | 37.6901 |
61
+ | 0.0258 | 0.6023 | 800 | 7.9539 | 0.0218 | 25.4742 |
62
+ | 0.0197 | 0.9034 | 1200 | 7.0188 | 0.0194 | 22.3362 |
63
+ | 0.0083 | 1.2637 | 1600 | 6.1604 | 0.0183 | 20.2225 |
64
+ | 0.0066 | 1.5794 | 2000 | 5.9469 | 0.0176 | 19.4205 |
65
+ | 0.0065 | 1.8952 | 2400 | 5.8609 | 0.0174 | 19.0958 |
66
+ | 0.0161 | 2.1084 | 2800 | 5.8786 | 0.0167 | 18.8094 |
67
+ | 0.0157 | 2.4096 | 3200 | 5.6719 | 0.0162 | 18.4526 |
68
+ | 0.0157 | 2.7107 | 3600 | 5.6150 | 0.0160 | 18.3772 |
69
+ | 0.0063 | 3.1595 | 4000 | 5.4820 | 0.0160 | 18.0877 |
70
+ | 0.0052 | 3.4752 | 4400 | 5.4747 | 0.0161 | 18.2023 |
71
+ | 0.0049 | 3.7910 | 4800 | 5.5285 | 0.0161 | 17.9922 |
72
+ | 0.0154 | 3.9155 | 5200 | 5.5457 | 0.0159 | 18.1641 |
73
+ | 0.0142 | 4.2168 | 5600 | 5.4871 | 0.0158 | 17.9721 |
74
+ | 0.0143 | 4.5180 | 6000 | 5.5382 | 0.0157 | 18.0495 |
75
+ | 0.0155 | 4.8191 | 6400 | 5.4620 | 0.0156 | 17.9460 |
76
+ | 0.005 | 5.3710 | 6800 | 5.4875 | 0.0157 | 17.7691 |
77
+ | 0.0052 | 5.6868 | 7200 | 5.4416 | 0.0157 | 17.8646 |
78
+ | 0.0085 | 4.8653 | 7600 | 5.5002 | 0.0157 | 17.8817 |
79
+ | 0.0096 | 5.1216 | 8000 | 5.5124 | 0.0156 | 17.8264 |
80
+ | 0.0094 | 5.3776 | 8400 | 5.6387 | 0.0155 | 17.7500 |
81
+ | 0.0093 | 5.6336 | 8800 | 5.4429 | 0.0154 | 17.6736 |
82
+ | 0.01 | 5.8896 | 9200 | 5.3128 | 0.0153 | 17.2856 |
83
+ | 0.0091 | 6.1453 | 9600 | 5.2836 | 0.0153 | 17.2424 |
84
+ | 0.0088 | 6.4019 | 10000 | 0.0153 | 17.2434 | 5.2826 |
85
+ | 0.008 | 6.6579 | 10400 | 0.0153 | 17.1288 | 5.2957 |
86
+ | 0.007 | 6.9139 | 10800 | 0.0153 | 17.1680 | 5.2889 |
87
 
88
 
89
  ### Framework versions
runs/Feb16_10-42-42_e07caf301fc1/events.out.tfevents.1739735119.e07caf301fc1.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c82d7e340aa6f033aab976a2bf637092ae1c25f681db48c85b3e719fca89a61d
3
+ size 453