How to use OpenVoiceOS/stt_zh_citrinet_512_onnx with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("OpenVoiceOS/stt_zh_citrinet_512_onnx") transcriptions = asr_model.transcribe(["file.wav"])
