deepdml/whisper-tiny-ta-mix-norm

Whisper Tiny ta

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2986
• Wer: 54.6315
• Cer: 12.9630

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.04
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.1533	0.2	1000	0.3370	60.6394	14.6984
0.0975	0.4	2000	0.3093	56.1889	13.3764
0.123	1.1734	3000	0.2991	55.3426	13.0832
0.0846	1.3734	4000	0.3028	54.5143	12.8327
0.0963	2.1468	5000	0.2986	54.6315	12.9630

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1

Citation

Please cite the model using the following BibTeX entry:

@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}
    }