FunASR Nano

This section describes how to use models from https://github.com/FunAudioLLM/Fun-ASR.

Fun-ASR-Nano-2512

A single model from Fun-ASR-Nano-2512 supports the following languages

  • Chinese

  • English

  • Japanese

Hint

中文包括 7 种方言（吴语、粤语、闽语、客家话、赣语、湘语、晋语）和 26 种地方口音（河南、山西、湖北、四川、重庆、云南、贵州、广东、广西 及其他 20 多个地区）。

英文和日文涵盖多种地方口音。

此外还支持歌词识别和说唱语音识别。

We have converted Fun-ASR-Nano-2512 to onnx and provided APIs for the following programming languages

You can find the onnx export script at https://github.com/Wasser1462/FunASR-nano-onnx

Note that you can use Fun-ASR-Nano-2512 with sherpa-onnx on the following platforms:

  • Linux (x64, aarch64, arm, riscv64)

  • macOS (x64, arm64)

  • Windows (x64, x86, arm64)

  • Android (arm64-v8a, armv7-eabi, x86, x86_64)

  • iOS (arm64)

In the following, we describe how to download pre-trained Fun-ASR-Nano-2512 models and use them in sherpa-onnx.