deepdml/whisper-small-ta-mix-norm

Whisper Small ta

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

• Loss: 0.2021
• Wer: 37.7349
• Cer: 7.1808

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: 32
• eval_batch_size: 32
• 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
0.107	0.2	1000	0.2099	42.9558	8.5389
0.0274	0.4	2000	0.2070	41.0841	8.0743
0.0688	0.6	3000	0.1824	38.7564	7.6139
0.0194	0.8	4000	0.1950	37.8032	7.2174
0.0148	1.147	5000	0.2021	37.7349	7.1808

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