MuPT: A Generative Symbolic Music Pretrained Transformer
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909377405911040 |
|---|---|
| author | Qu, Xingwei Bai, Yuelin Ma, Yinghao Zhou, Ziya Lo, Ka Man Liu, Jiaheng Yuan, Ruibin Min, Lejun Liu, Xueling Zhang, Tianyu Du, Xinrun Guo, Shuyue Liang, Yiming Li, Yizhi Wu, Shangda Zhou, Junting Zheng, Tianyu Ma, Ziyang Han, Fengze Xue, Wei Xia, Gus Benetos, Emmanouil Yue, Xiang Lin, Chenghua Tan, Xu Huang, Stephen W. Fu, Jie Zhang, Ge |
| author_facet | Qu, Xingwei Bai, Yuelin Ma, Yinghao Zhou, Ziya Lo, Ka Man Liu, Jiaheng Yuan, Ruibin Min, Lejun Liu, Xueling Zhang, Tianyu Du, Xinrun Guo, Shuyue Liang, Yiming Li, Yizhi Wu, Shangda Zhou, Junting Zheng, Tianyu Ma, Ziyang Han, Fengze Xue, Wei Xia, Gus Benetos, Emmanouil Yue, Xiang Lin, Chenghua Tan, Xu Huang, Stephen W. Fu, Jie Zhang, Ge |
| contents | In this paper, we explore the application of Large Language Models (LLMs) to the pre-training of music. While the prevalent use of MIDI in music modeling is well-established, our findings suggest that LLMs are inherently more compatible with ABC Notation, which aligns more closely with their design and strengths, thereby enhancing the model's performance in musical composition. To address the challenges associated with misaligned measures from different tracks during generation, we propose the development of a Synchronized Multi-Track ABC Notation (SMT-ABC Notation), which aims to preserve coherence across multiple musical tracks. Our contributions include a series of models capable of handling up to 8192 tokens, covering 90% of the symbolic music data in our training set. Furthermore, we explore the implications of the Symbolic Music Scaling Law (SMS Law) on model performance. The results indicate a promising direction for future research in music generation, offering extensive resources for community-led research through our open-source contributions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06393 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MuPT: A Generative Symbolic Music Pretrained Transformer Qu, Xingwei Bai, Yuelin Ma, Yinghao Zhou, Ziya Lo, Ka Man Liu, Jiaheng Yuan, Ruibin Min, Lejun Liu, Xueling Zhang, Tianyu Du, Xinrun Guo, Shuyue Liang, Yiming Li, Yizhi Wu, Shangda Zhou, Junting Zheng, Tianyu Ma, Ziyang Han, Fengze Xue, Wei Xia, Gus Benetos, Emmanouil Yue, Xiang Lin, Chenghua Tan, Xu Huang, Stephen W. Fu, Jie Zhang, Ge Sound Artificial Intelligence Audio and Speech Processing In this paper, we explore the application of Large Language Models (LLMs) to the pre-training of music. While the prevalent use of MIDI in music modeling is well-established, our findings suggest that LLMs are inherently more compatible with ABC Notation, which aligns more closely with their design and strengths, thereby enhancing the model's performance in musical composition. To address the challenges associated with misaligned measures from different tracks during generation, we propose the development of a Synchronized Multi-Track ABC Notation (SMT-ABC Notation), which aims to preserve coherence across multiple musical tracks. Our contributions include a series of models capable of handling up to 8192 tokens, covering 90% of the symbolic music data in our training set. Furthermore, we explore the implications of the Symbolic Music Scaling Law (SMS Law) on model performance. The results indicate a promising direction for future research in music generation, offering extensive resources for community-led research through our open-source contributions. |
| title | MuPT: A Generative Symbolic Music Pretrained Transformer |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2404.06393 |