How to use julien-c/mini_an4_asr_train_raw_bpe_valid with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "julien-c/mini_an4_asr_train_raw_bpe_valid" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0]
