Whisper

This section describes how to use models from Whisper with sherpa-onnx for non-streaming speech recognition.

• Export Whisper to ONNX
  • Available models
  • Export to onnx
    • Example 1: Export tiny.en
    • Example 2: Export large-v3
• tiny.en
  • Real-time factor (RTF) on Raspberry Pi 4 Model B
• large-v3
  • Run with CPU (float32)
  • Run with CPU (int8)
  • Run with GPU (float32)
  • Run with GPU (int8)
    • Fix issues about running on GPU
  • colab
• colab
  • Non-large models
  • Large models
• Huggingface space