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