anuragshas
/

whisper-small-bn

Automatic Speech Recognition Transformers PyTorch TensorBoard

Bengali whisper whisper-event generated_from_trainer Eval Results Inference Endpoints

Model card Files Files and versions 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: 109

Dataset used to train anuragshas/whisper-small-bn

Spaces using anuragshas/whisper-small-bn 2

Evaluation results

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

18.220

View on Papers With Code