InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909517784023040 |
|---|---|
| author | Zhang, Chong Ma, Yukun Chen, Qian Wang, Wen Zhao, Shengkui Pan, Zexu Wang, Hao Ni, Chongjia Nguyen, Trung Hieu Zhou, Kun Jiang, Yidi Tan, Chaohong Gao, Zhifu Du, Zhihao Ma, Bin |
| author_facet | Zhang, Chong Ma, Yukun Chen, Qian Wang, Wen Zhao, Shengkui Pan, Zexu Wang, Hao Ni, Chongjia Nguyen, Trung Hieu Zhou, Kun Jiang, Yidi Tan, Chaohong Gao, Zhifu Du, Zhihao Ma, Bin |
| contents | We introduce InspireMusic, a framework integrated super resolution and large language model for high-fidelity long-form music generation. A unified framework generates high-fidelity music, songs, and audio, which incorporates an autoregressive transformer with a super-resolution flow-matching model. This framework enables the controllable generation of high-fidelity long-form music at a higher sampling rate from both text and audio prompts. Our model differs from previous approaches, as we utilize an audio tokenizer with one codebook that contains richer semantic information, thereby reducing training costs and enhancing efficiency. This combination enables us to achieve high-quality audio generation with long-form coherence of up to $8$ minutes. Then, an autoregressive transformer model based on Qwen 2.5 predicts audio tokens. Next, we employ a super-resolution flow-matching model to generate high-sampling rate audio with fine-grained details learned from an acoustic codec model. Comprehensive experiments show that the InspireMusic-1.5B-Long model has a comparable performance to recent top-tier open-source systems, including MusicGen and Stable Audio 2.0, on subjective and objective evaluations. The code and pre-trained models are released at https://github.com/FunAudioLLM/InspireMusic. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00084 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation Zhang, Chong Ma, Yukun Chen, Qian Wang, Wen Zhao, Shengkui Pan, Zexu Wang, Hao Ni, Chongjia Nguyen, Trung Hieu Zhou, Kun Jiang, Yidi Tan, Chaohong Gao, Zhifu Du, Zhihao Ma, Bin Sound Artificial Intelligence Computation and Language Audio and Speech Processing We introduce InspireMusic, a framework integrated super resolution and large language model for high-fidelity long-form music generation. A unified framework generates high-fidelity music, songs, and audio, which incorporates an autoregressive transformer with a super-resolution flow-matching model. This framework enables the controllable generation of high-fidelity long-form music at a higher sampling rate from both text and audio prompts. Our model differs from previous approaches, as we utilize an audio tokenizer with one codebook that contains richer semantic information, thereby reducing training costs and enhancing efficiency. This combination enables us to achieve high-quality audio generation with long-form coherence of up to $8$ minutes. Then, an autoregressive transformer model based on Qwen 2.5 predicts audio tokens. Next, we employ a super-resolution flow-matching model to generate high-sampling rate audio with fine-grained details learned from an acoustic codec model. Comprehensive experiments show that the InspireMusic-1.5B-Long model has a comparable performance to recent top-tier open-source systems, including MusicGen and Stable Audio 2.0, on subjective and objective evaluations. The code and pre-trained models are released at https://github.com/FunAudioLLM/InspireMusic. |
| title | InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation |
| topic | Sound Artificial Intelligence Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2503.00084 |