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.

unknown charts

💎 LTS Industrial Standard: PDF/Word optimization with scientific Trellis Mimic engine. Features Turbo Parallel processing & Global Camouflage (Ricoh/Fujitsu/Canon 2025 profiles). Embedded Python 3.12, zero-install, no admin needed. Ultimate document privacy for Windows LTSC/Enterprise.

🏭 ORCHAT Enterprise CLI: Swiss Watch Precision AI Assistant. 3378x smaller than industry average (14KB). 50+ years engineering standards, 348+ models, 13-level logging, and military-grade security. Built for production-grade reliability.

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