Add C++ and Python API for FireRedASR AED models

[csukuangfj]

Usage

1. Build sherpa-onnx from source
2. Download a model

wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16.tar.bz2
tar xvf sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16.tar.bz2
rm sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16.tar.bz2

3. Run it with a binary compiled from C++

./build/bin/sherpa-onnx-offline \
  --fire-red-asr-encoder=./sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16/encoder.int8.onnx \
  --fire-red-asr-decoder=./sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16/decoder.int8.onnx \
  --tokens=./sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16/tokens.txt \
  ./sherpa-onnx-fire-red-asr-large-zh_en-2025-02-16/test_wavs/0.wav

4. Run it with Python API

 python3 ./python-api-examples/offline-fire-red-asr-decode-files.py

Huggingface spaces

You can try the model by visiting
https://huggingface.co/spaces/k2-fsa/automatic-speech-recognition

---

国内用户，可以访问下面的huggingface space 镜像
https://hf.qhduan.com/spaces/k2-fsa/automatic-speech-recognition

---

CC @FireRedTeam @kaituoxu