deepdml/whisper-base-ta-mix-norm

Whisper Base ta

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

• Loss: 0.2545
• Wer: 47.8288
• Cer: 10.4653

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
0.0965	0.2	1000	0.2826	53.0729	11.8395
0.0547	0.4	2000	0.2570	49.0732	10.5462
0.0789	1.1734	3000	0.2472	48.2230	10.3181
0.0476	1.3734	4000	0.2619	47.5171	10.1930
0.0579	2.1468	5000	0.2545	47.8288	10.4653

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