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

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

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 both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.

TASU: A New Style of Alignment of Speech LLM with only Text Training Data, zero-shot on ASR and Other SU tasks

FunASR实时语音识别版，识别麦克风和电脑内播放的声音，电脑语音打字软件

[ICLR 2026] StableToken: A state-of-the-art noise-robust semantic speech tokenizer featuring Voting-LFQ for resilient SpeechLLMs.

SHALLOW, the first hallucination benchmark for ASR models

🎤 Enable voice recognition for the Doubao input method using Python; ideal for learning and research with a focus on audio processing.

Provide accurate voice activity and audio event detection in 100+ languages with high-performance streaming and non-streaming capabilities.

🎨 Explore clip-path techniques in HTML and CSS to create interactive menus and dynamic shapes without JavaScript for responsive design.