How to use espnet/owsm_v2_ebranchformer with ESPnet:
import soundfile from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/owsm_v2_ebranchformer" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0]
sw005320 commited on 
