Downloads · 30 days
11
10% of all-time downloads
whisper-small-urdu
gradio-ci/whisper-small-urdu
whisper-small-urdu is a automatic speech recognition model from gradio-ci. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
<a href="https://huggingface.co/spaces/gradio-ci/whisper-urdu-asr-static-3105a7" target="blank"<img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in…
All-time downloads
105
Public
Parameters
242M
2.9 GB on disk
Likes
0
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
- Apr 26, 2026
- Updated
- Apr 26, 2026
- SHA
- 144ff810
Base models
Model card
From the Hugging Face model README
<a href="https://huggingface.co/spaces/gradio-ci/whisper-urdu-asr-static-3105a7" target="_blank"><img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in Trackio" title="Visualize in Trackio" style="height: 40px;"/></a>
<!-- 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-urdu
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7483
- Wer: 44.5016
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- training_steps: 300
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1845 | 1.0638 | 100 | 0.7734 | 46.4309 |
| 0.6925 | 2.1277 | 200 | 0.7494 | 45.5949 |
| 0.6574 | 3.1915 | 300 | 0.7483 | 44.5016 |
Framework versions
- Transformers 5.6.2
- Pytorch 2.11.0+cu130
- Datasets 4.8.4
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Apr 26, 2026
- Updated
- Apr 26, 2026