How to use OpenVoiceOS/inesc-id-ebranch-w2vbert2-ep-ctc-onnx with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "OpenVoiceOS/inesc-id-ebranch-w2vbert2-ep-ctc-onnx" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0]
