A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc. - modelscope/FunASR

Dickson A.

Community Picks is a section on daily.dev where our community members share the most interesting and valuable content they've discovered online. From insightful articles to handy tools, every post is a gem curated by our dedicated coomunity. To contribute to Community Picks, you need to have at least 250 reputation points, ensuring that only active and trusted members can share their finds.

Community Picks

FunASR is a comprehensive speech recognition toolkit that supports various functionalities such as speech recognition, voice activity detection, punctuation restoration, and more. It features a range of pre-trained models, including the highly accurate Paraformer-large model and the multitasking Whisper-large-v3-turbo model. The toolkit provides scripts and tutorials for easy inference and fine-tuning, and multiple models are accessible via ModelScope and Huggingface. The latest supported models and features include real-time transcription services, keyword spotting, and emotion recognition.

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.