FunAudioLLM
Popular repositories Loading
-
SenseVoice
SenseVoice PublicMultilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.
-
ThinkSound
ThinkSound Public[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
-
Fun-Audio-Chat
Fun-Audio-Chat PublicFun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.
Repositories
- Fun-ASR Public
End-to-end speech recognition large model: 31 languages, dialects, accents, lyrics, hotwords, timestamps, speaker diarization. Trained on tens of millions of hours.
FunAudioLLM/Fun-ASR’s past year of commit activity - CosyVoice Public
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
FunAudioLLM/CosyVoice’s past year of commit activity - SenseVoice Public
Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.
FunAudioLLM/SenseVoice’s past year of commit activity - FunAudioLLM.github.io Public
FunAudioLLM/FunAudioLLM.github.io’s past year of commit activity - FunResearch Public
This repository is maintained by the Speech Team at Alibaba’s Tongyi Lab, serving as an open-source platform for our cutting-edge research in speech, audio, NLP technologies. We believe in accelerating scientific progress through transparent collaboration, and invite the global research community to explore, reproduce, and build upon our work.
FunAudioLLM/FunResearch’s past year of commit activity - ThinkSound Public
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
FunAudioLLM/ThinkSound’s past year of commit activity - FunCineForge Public
FunAudioLLM/FunCineForge’s past year of commit activity - Fun-Audio-Chat Public
Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.
FunAudioLLM/Fun-Audio-Chat’s past year of commit activity - MME-Emotion Public
Official repository for the paper “MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models”
FunAudioLLM/MME-Emotion’s past year of commit activity - CV3-Eval Public
FunAudioLLM/CV3-Eval’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…