217 stars | 8 forks | Python
FireRedASR2S is a SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and singing lyrics recognition. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects.
What it does
FireRedASR2S is a cutting-edge ASR system that integrates speech recognition, voice activity detection, language identification, and punctuation prediction. Its high accuracy across multiple languages and dialects makes it a valuable tool for developers and researchers in the speech technology domain.
Why it matters: Unlock the power of speech technology with FireRedASR2S - the all-in-one solution for accurate and efficient speech processing!
Want to create content about this repo? Use Nemati AI tools to generate articles, tutorials, and social posts.





