How to use espnet/roshansh_how2_asr_raw_ft_sum_valid.acc with ESPnet:
import soundfile from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/roshansh_how2_asr_raw_ft_sum_valid.acc" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0]
