metadata
language:
- en
library_name: transformers
pipeline_tag: automatic-speech-recognition
Model trained in 8-bit with LoRA
Usage:
prepare pipeline:
asr_model=prepare_pipeline(
model_dir='.', # wherever you save the model
generate_opts={'max_new_tokens':112,
'num_beams':1,
'repetition_penalty':r1,
'do_sample':False
}
)
run ASR:
asr_model(audio_path)