How to use espnet/DCASE23.AudioCaptioning.PreTrained with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/DCASE23.AudioCaptioning.PreTrained" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0]
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/DCASE23.AudioCaptioning.PreTrained" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0]