How to use nvidia/stt_en_fastconformer_transducer_large with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/stt_en_fastconformer_transducer_large") transcriptions = asr_model.transcribe(["file.wav"])
SaylorTwift