---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- automatic-speech-recognition
- whisper
- urdu
datasets:
- mozilla-foundation/common_voice_17_0
- HowMannyMore/urdu-audiodataset
metrics:
- wer
- cer
- bleu
- chrf
model-index:
- name: whisper-tiny-urdu
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: Common Voice 17.0 (Urdu)
      type: mozilla-foundation/common_voice_17_0
      config: ur
      split: test
      args: ur
    metrics:
    - name: WER on Common Voice 17.0
      type: wer
      value: 46.908
    - name: CER on Common Voice 17.0
      type: cer
      value: 18.543
    - name: BLEU on Common Voice 17.0
      type: bleu
      value: 32.631
    - name: ChrF on Common Voice 17.0
      type: chrf
      value: 63.988
language:
- ur
pipeline_tag: automatic-speech-recognition
---

<!-- 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-tiny-urdu

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_17_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7225
- Wer: 47.8529


## Quick Usage

```python
from transformers import pipeline

transcriber = pipeline(
  "automatic-speech-recognition", 
  model="kingabzpro/whisper-tiny-urdu"
)

transcriber.model.generation_config.forced_decoder_ids = None
transcriber.model.generation_config.language = "ur"

transcription = transcriber("audio2.mp3")
print(transcription)
```

```sh
{'text': 'دیکھیے پانی کب تک بہتا اور مچھلی کب تک تیرتی ہے'}
```

## Evaluation


| **Dataset**                    | **WER (%)** | **CER (%)** | **BLEU** | **ChrF** |
| ------------------------------ | ----------- | ----------- | -------- | -------- |
| Common Voice 17.0 (Urdu)       | 46.908      | 18.543      | 32.631   | 63.988   |
| HowMannyMore/urdu-audiodataset | 51.405      | 21.830      | 31.475   | 64.204   |



## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- training_steps: 2500
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.6808        | 1.6949 | 500  | 0.7403          | 52.6699 |
| 0.3948        | 3.3898 | 1000 | 0.6850          | 47.1247 |
| 0.2873        | 5.0847 | 1500 | 0.6994          | 48.1516 |
| 0.2024        | 6.7797 | 2000 | 0.7169          | 46.7326 |
| 0.183         | 8.4746 | 2500 | 0.7225          | 47.8529 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1