Modelpublic

chaitnya26/SongGeneration-fork

sourceHugging Faceupdated 11mo agoView on Hugging Face

0likes11downloads

Model Card

SongGeneration

<p align="center"><img src="img/logo.jpg" width="40%"></p> <p align="center"> <a href="https://levo-demo.github.io/">Demo</a>  |  <a href="https://arxiv.org/abs/2506.07520">Paper</a>  |  <a href="https://github.com/tencent-ailab/songgeneration">Code</a>  |  <a href="https://huggingface.co/spaces/tencent/SongGeneration">Space Demo</a> </p>

This repository is the official weight repository for LeVo: High-Quality Song Generation with Multi-Preference Alignment. In this repository, we provide the SongGeneration model, inference scripts, and the checkpoint that has been trained on the Million Song Dataset.

Model Versions

Model	Max Length	Language	GPU Menmory	RFT(A100)	Download Link
SongGeneration-base	2m30s	zh	10G/16G	1.26	You were here
SongGeneration-base-new	2m30s	zh, en	10G/16G	1.26	Huggingface
SongGeneration-base-full	4m30s	zh, en	12G/18G	1.30	Huggingface
SongGeneration-large	4m30s	zh, en	22G/28G	1.51	Huggingface
SongGeneration-v1.5-small	2m	zh, en, es, ja, etc.	-	-	Coming soon
SongGeneration-v1.5-base	4m30s	zh, en, es, ja, etc.	-	-	Coming soon
SongGeneration-v1.5-large	4m30s	zh, en, es, ja, etc.	-	-	Coming soon

Overview

We develop the SongGeneration model. It is an LM-based framework consisting of LeLM and a music codec. LeLM is capable of parallelly modeling two types of tokens: mixed tokens, which represent the combined audio of vocals and accompaniment to achieve vocal-instrument harmony, and dual-track tokens, which separately encode vocals and accompaniment for high-quality song generation. The music codec reconstructs the dual-track tokens into highfidelity music audio. SongGeneration significantly improves over the open-source music generation models and performs competitively with current state-of-the-art industry systems. For more details, please refer to our paper.

License

The code and weights in this repository is released in the LICENSE file.