---
library_name: transformers
language:
- ta
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- fixie-ai/common_voice_17_0
- google/fleurs
- ai4bharat/Kathbath
- deepdml/iisc-mile-tamil-asr
- deepdml/microsoft-speech-corpus-indian
- deepdml/openslr65-tamil
metrics:
- wer
model-index:
- name: Whisper Tiny ta
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 17.0
      type: fixie-ai/common_voice_17_0
    metrics:
    - name: Wer
      type: wer
      value: 51.66621581584676
---
<!-- 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 ta

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: 0.2641
- Wer: 51.6662
- Cer: 11.8757

## 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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.04
- training_steps: 8000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     | Cer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
| 0.2508        | 0.125 | 1000 | 0.3392          | 62.4235 | 15.5864 |
| 0.1747        | 0.25  | 2000 | 0.3003          | 57.3701 | 13.4963 |
| 0.1586        | 0.375 | 3000 | 0.2905          | 55.5023 | 13.1754 |
| 0.1244        | 0.5   | 4000 | 0.2812          | 53.6500 | 12.6062 |
| 0.1361        | 0.625 | 5000 | 0.2687          | 52.9080 | 12.3268 |
| 0.1093        | 0.75  | 6000 | 0.2685          | 52.2523 | 12.0787 |
| 0.1141        | 0.875 | 7000 | 0.2647          | 51.9844 | 11.9065 |
| 0.1274        | 1.0   | 8000 | 0.2641          | 51.6662 | 11.8757 |


### Framework versions

- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.21.0

## Citation

Please cite the model using the following BibTeX entry:

```bibtex
@misc{deepdml/whisper-tiny-ta-mix-norm,
      title={Fine-tuned Whisper tiny ASR model for speech recognition in Tamil},
      author={Jimenez, David},
      howpublished={\url{https://huggingface.co/deepdml/whisper-tiny-ta-mix-norm}},
      year={2026}
    }
```