speechllm

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.

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

The Interspeech 2025 Multilingual Conversational Speech LLM (MLC-SLM) Challenge

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

SHALLOW, the first hallucination benchmark for ASR models