ModelScope Model

How to infer using a pretrained Paraformer-large Model

Inference

You can use the pretrain model for inference directly.

• Setting parameters in infer.py

  • audio_in: # Support wav, url, bytes, and parsed audio format.
  • output_dir: # If the input format is wav.scp, it needs to be set.
  • batch_size: # Set batch size in inference.
  • param_dict: # Set the hotword list in inference.

• Then you can run the pipeline to infer with:
  python python infer.py