How to use WhissleAI/STT-zh-mandarin-meta-ONNX with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("WhissleAI/STT-zh-mandarin-meta-ONNX") transcriptions = asr_model.transcribe(["file.wav"])
Licensed for inference only. Accept to access.
By clicking Agree, you accept the Whissle Inference-Only License.
Log in or Sign Up to review the conditions and access this model content.
Single-pass Mandarin ASR with inline entity tagging and speaker attributes. 600M params, 1044h training, WER 57.5%, Gender 94.8%.
Base model
