NbAiLab
/

whisper_small_modified

Automatic Speech Recognition Transformers PyTorch TensorFlow JAX Safetensors 99 languages whisper audio hf-asr-leaderboard Eval Results Inference Endpoints

Model card Files Files and versions Community

Edit model card

Whisper

Experiment with modified special_tokens_map.json

Downloads last month: 4

Safetensors

Model size

242M params

Tensor type

F32

·

Evaluation results

Test WER on LibriSpeech (clean)
test set self-reported

3.432
Test WER on LibriSpeech (other)
test set self-reported

7.628
Test WER on Common Voice 11.0
test set self-reported

87.300

View leaderboard (Papers With Code)