Downloads · 30 days
13
3% of all-time downloads
whisper-small
AsemBadr/whisper-small
whisper-small is a automatic speech recognition model from AsemBadr. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
385
Public
Parameters
242M
7.7 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Feb 16, 2024
- Updated
- Mar 22, 2024
- SHA
- 199e716f
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
Whisper Small for Quran Recognition
This model is a fine-tuned version of openai/whisper-small on the Quran_Reciters dataset. It achieves the following results on the evaluation set:
- Loss: 0.0193
- Wer: 3.7476
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0264 | 1.62 | 500 | 0.0319 | 8.0110 |
| 0.0012 | 3.24 | 1000 | 0.0228 | 5.5011 |
| 0.0009 | 4.85 | 1500 | 0.0209 | 4.1258 |
| 0.0003 | 6.47 | 2000 | 0.0185 | 3.7992 |
| 0.0002 | 8.09 | 2500 | 0.0188 | 3.7820 |
| 0.0001 | 9.71 | 3000 | 0.0191 | 3.7476 |
| 0.0001 | 11.33 | 3500 | 0.0193 | 3.7133 |
| 0.0 | 12.94 | 4000 | 0.0193 | 3.7476 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.1.2
- Datasets 2.17.1
- Tokenizers 0.15.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ara
- Created
- Feb 16, 2024
- Updated
- Mar 22, 2024