{"ID":2825737,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20156","arxiv_id":"2512.20156","title":"Fun-Audio-Chat Technical Report","abstract":"Recent advancements in joint speech-text models show great potential for seamless voice interactions. However, existing models face critical challenges: temporal resolution mismatch between speech tokens (25Hz) and text tokens (~3Hz) dilutes semantic information, incurs high computational costs, and causes catastrophic forgetting of text LLM knowledge. We introduce Fun-Audio-Chat, a Large Audio Language Model addressing these limitations via two innovations from our previous work DrVoice. First, Dual-Resolution Speech Representations (DRSR): the Shared LLM processes audio at efficient 5Hz (via token grouping), while the Speech Refined Head generates high-quality tokens at 25Hz, balancing efficiency (~50% GPU reduction) and quality. Second, Core-Cocktail Training, a two-stage fine-tuning with intermediate merging that mitigates catastrophic forgetting. We then apply Multi-Task DPO Training to enhance robustness, audio understanding, instruction-following and voice empathy. This multi-stage post-training enables Fun-Audio-Chat to retain text LLM knowledge while gaining powerful audio understanding, reasoning, and generation. Unlike recent LALMs requiring large-scale audio-text pre-training, Fun-Audio-Chat leverages pre-trained models and extensive post-training. Fun-Audio-Chat 8B and MoE 30B-A3B achieve competitive performance on Speech-to-Text and Speech-to-Speech tasks, ranking top among similar-scale models on Spoken QA benchmarks. They also achieve competitive to superior performance on Audio Understanding, Speech Function Calling, Instruction-Following and Voice Empathy. We develop Fun-Audio-Chat-Duplex, a full-duplex variant with strong performance on Spoken QA and full-duplex interactions. We open-source Fun-Audio-Chat-8B with training and inference code, and provide an interactive demo, at https://github.com/FunAudioLLM/Fun-Audio-Chat .","short_abstract":"Recent advancements in joint speech-text models show great potential for seamless voice interactions. However, existing models face critical challenges: temporal resolution mismatch between speech tokens (25Hz) and text tokens (~3Hz) dilutes semantic information, incurs high computational costs, and causes catastrophic...","url_abs":"https://arxiv.org/abs/2512.20156","url_pdf":"https://arxiv.org/pdf/2512.20156v4","authors":"[\"Tongyi Fun Team\",\"Qian Chen\",\"Luyao Cheng\",\"Chong Deng\",\"Xiangang Li\",\"Jiaqing Liu\",\"Chao-Hong Tan\",\"Wen Wang\",\"Junhao Xu\",\"Jieping Ye\",\"Qinglin Zhang\",\"Qiquan Zhang\",\"Jingren Zhou\"]","published":"2025-12-23T08:35:27Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.SD\",\"eess.AS\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":605693,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2825737,"paper_url":"https://arxiv.org/abs/2512.20156","paper_title":"Fun-Audio-Chat Technical Report","repo_url":"https://github.com/FunAudioLLM/Fun-Audio-Chat","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}