Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
#!/usr/bin/env python3
# -*- encoding: utf-8 -*-
# Copyright FunASR (https://github.com/QwenAudio/SenseVoice). All Rights Reserved.
# MIT License (https://opensource.org/licenses/MIT)
from funasr import AutoModel
model_dir = "iic/SenseVoiceSmall"
model = AutoModel(
model=model_dir,
device="cuda:0",
)
res = model.export(type="onnx", quantize=False)