---
library_name: transformers
language:
- ta
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- deepdml/iisc-mile-tamil-asr
- deepdml/openslr65-tamil
- google/fleurs
- fixie-ai/common_voice_17_0
- ai4bharat/Kathbath
- deepdml/microsoft-speech-corpus-indian
metrics:
- wer
model-index:
- name: Whisper Medium ta
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 17.0
      type: deepdml/iisc-mile-tamil-asr
    metrics:
    - name: Wer
      type: wer
      value: 28.496348108358777
---
<!-- 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 Medium ta

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1192
- Wer: 28.4963
- Cer: 4.8178

## 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: 16
- 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: 18000

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Wer     | Cer    |
|:-------------:|:------:|:-----:|:---------------:|:-------:|:------:|
| 0.1425        | 0.0556 | 1000  | 0.2033          | 42.3465 | 8.2575 |
| 0.0992        | 0.1111 | 2000  | 0.1824          | 38.1999 | 7.0789 |
| 0.0969        | 0.1667 | 3000  | 0.1749          | 36.7353 | 6.9087 |
| 0.0724        | 0.2222 | 4000  | 0.1716          | 36.3682 | 6.8174 |
| 0.0605        | 0.2778 | 5000  | 0.1591          | 34.1861 | 6.2048 |
| 0.0544        | 0.3333 | 6000  | 0.1556          | 33.2663 | 5.9622 |
| 0.0544        | 0.3889 | 7000  | 0.1504          | 32.3505 | 5.7064 |
| 0.0459        | 0.4444 | 8000  | 0.1410          | 32.2191 | 5.5940 |
| 0.0533        | 0.5    | 9000  | 0.1434          | 31.6562 | 5.5619 |
| 0.0529        | 0.5556 | 10000 | 0.1386          | 30.9747 | 5.4560 |
| 0.0377        | 0.6111 | 11000 | 0.1435          | 31.1190 | 5.5364 |
| 0.0367        | 0.6667 | 12000 | 0.1457          | 30.4170 | 5.2740 |
| 0.0414        | 0.7222 | 13000 | 0.1375          | 30.3294 | 5.2244 |
| 0.0479        | 0.7778 | 14000 | 0.1338          | 29.7381 | 5.0581 |
| 0.031         | 0.8333 | 15000 | 0.1362          | 29.5707 | 4.9853 |
| 0.026         | 0.8889 | 16000 | 0.1341          | 29.1894 | 4.9600 |
| 0.0399        | 0.9444 | 17000 | 0.1217          | 28.9021 | 4.8740 |
| 0.0454        | 1.0    | 18000 | 0.1192          | 28.4963 | 4.8178 |


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