sherpa
1.3
  • Introduction
  • Download pdf
  • Social groups
  • Run Next-gen Kaldi in your browser
  • Pre-trained models

k2-fsa/sherpa

  • sherpa

k2-fsa/sherpa-ncnn

  • sherpa-ncnn

k2-fsa/sherpa-onnx

  • sherpa-onnx
    • Tutorials
    • Installation
    • Frequently Asked Question (FAQs)
    • Python
    • C API
    • Java API
    • Javascript API
    • Kotlin API
    • Swift API
    • Go API
    • C# API
    • Pascal API
    • Lazarus
    • WebAssembly
    • Android
    • HarmonyOS
    • iOS
    • Flutter
    • WebSocket
    • Hotwords (Contextual biasing)
    • Keyword spotting
    • Punctuation
    • Audio tagging
    • Spoken language identification
    • VAD
    • Pre-trained models
      • Online transducer models
      • Online paraformer models
      • Online CTC models
      • Offline transducer models
      • Offline paraformer models
      • Offline CTC models
      • TeleSpeech
      • Whisper
        • Export Whisper to ONNX
        • tiny.en
        • large-v3
        • colab
        • Huggingface space
      • WeNet
      • Small models
    • Moonshine
    • SenseVoice
    • FireRedAsr
    • Dolphin
    • Speaker Diarization
    • Speaker Identification
    • Speech enhancement
    • rknn
    • Text-to-speech (TTS)

Triton

  • Triton
sherpa
  • »
  • sherpa-onnx »
  • Pre-trained models »
  • Whisper
  • Edit on GitHub

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
Previous Next

© Copyright 2022-2025, sherpa development team.

Built with Sphinx using a theme provided by Read the Docs.