anuragshas
/

whisper-small-bn

Automatic Speech Recognition

Transformers

PyTorch

Generated from Trainer

Eval Results (legacy)

Model card Files Files and versions

xet

Metrics Training metrics Community

Whisper Small Bengali

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 bn dataset. It achieves the following results on the evaluation set:

Loss: 0.1638
Wer: 18.22

Downloads last month: 92

Spaces using anuragshas/whisper-small-bn 2

Evaluation results

Wer on mozilla-foundation/common_voice_11_0 bn
test set self-reported

18.220