modelscope/FunASR: A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
04-14-2025
Link:
https://github.com/modelscope/FunASR
Note:
FunASR 是一个基础的语音识别工具包，提供了广泛的功能，包括语音识别(ASR)、语音活动检测(VAD)、标点恢复、语言模型、说话人验证、说话人分离和多说话人ASR等。FunASR提供了便捷的脚本和教程,支持预训练模型的推理和微调。
← Back to articles