acestep 5Hz lm 4B

提供商ACE-Step
分类text-to-audio
许可证mit
下载量3.1K
星标2

简介

acestep 5Hz lm 4B 是一款由 ACE-Step 推出的轻量级文本转音频（Text-to-Audio）模型。与传统的 TTS 语音合成不同，它更侧重于从文本描述直接生成丰富的音频片段或环境音效。4B 的参数规模使其在保证生成质量的同时，对硬件显存要求较低，适合开发者将其集成到游戏开发、短视频配音或 AI 助手等需要快速生成音效的本地化场景中。由于采用了 MIT 许可，开发者可以非常灵活地进行商业部署或二次开发。

核心亮点

  • 轻量级 4B 参数，低门槛部署且推理速度快
  • 支持文本直接生成音频，覆盖多种音效场景
  • 采用 MIT 协议，对商业化应用极其友好
  • 适合游戏开发与短视频创作者快速补全音效

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("ACE-Step/acestep-5Hz-lm-4B")
tokenizer = AutoTokenizer.from_pretrained("ACE-Step/acestep-5Hz-lm-4B")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download ACE-Step/acestep-5Hz-lm-4B

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download ACE-Step/acestep-5Hz-lm-4B config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('ACE-Step/acestep-5Hz-lm-4B')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/ACE-Step/acestep-5Hz-lm-4B

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/ACE-Step/acestep-5Hz-lm-4B

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('ACE-Step/acestep-5Hz-lm-4B')
tokenizer = AutoTokenizer.from_pretrained('ACE-Step/acestep-5Hz-lm-4B')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model ACE-Step/acestep-5Hz-lm-4B

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model ACE-Step/acestep-5Hz-lm-4B README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('ACE-Step/acestep-5Hz-lm-4B')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/ACE-Step/acestep-5Hz-lm-4B.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/ACE-Step/acestep-5Hz-lm-4B.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook 快速开发

下载并安装 ModelScope library

下载并安装 ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'ACE-Step/acestep-5Hz-lm-4B')

完整文档

来源: HuggingFace

---
library_name: transformers
license: mit
pipeline_tag: text-to-audio
tags:

  • audio

  • music

  • text2music

---

<h1 align="center">ACE-Step 1.5</h1>
<h1 align="center">Pushing the Boundaries of Open-Source Music Generation</h1>
<p align="center">
<a href="https://ace-step.github.io/ace-step-v1.5.github.io/">Project</a> |
<a href="https://huggingface.co/collections/ACE-Step/ace-step-15">Hugging Face</a> |
<a href="https://modelscope.cn/models/ACE-Step/ACE-Step-v1-5">ModelScope</a> |
<a href="https://huggingface.co/spaces/ACE-Step/Ace-Step-v1.5">Space Demo</a> |
<a href="https://discord.gg/PeWDxrkdj7">Discord</a>
<a href="https://arxiv.org/abs/2602.00744">Tech Report</a>
</p>

!image

Model Details

🚀 ACE-Step v1.5 is a highly efficient open-source music foundation model designed to bring commercial-grade music generation to consumer hardware.

Key Features

  • 💰 Commercial-Ready: Unlike many models trained on ambiguous datasets, ACE-Step v1.5 is designed for creators. You can strictly use the generated music for commercial purposes.
  • 📚 Safe & Robust Training Data: The model is trained on a massive, legally compliant dataset consisting of:
* Licensed Data: Professionally licensed music tracks. * Royalty-Free / No-Copyright Data: A vast collection of public domain and royalty-free music. * Synthetic Data: High-quality audio generated via advanced MIDI-to-Audio conversion.
  • ⚡ Extreme Speed: Generates a full song in under 2 seconds on an A100 and under 10 seconds on an RTX 3090.
  • 🖥️ Consumer Hardware Friendly: Runs locally with less than 4GB of VRAM.

Technical Capabilities

🌉 At its core lies a novel hybrid architecture where the Language Model (LM) functions as an omni-capable planner: it transforms simple user queries into comprehensive song blueprints—scaling from short loops to 10-minute compositions—while synthesizing metadata, lyrics, and captions via Chain-of-Thought to guide the Diffusion Transformer (DiT). ⚡ Uniquely, this alignment is achieved through intrinsic reinforcement learning relying solely on the model's internal mechanisms, thereby eliminating the biases inherent in external reward models or human preferences. 🎚️

🔮 Beyond standard synthesis, ACE-Step v1.5 unifies precise stylistic control with versatile editing capabilities—such as cover generation, repainting, and vocal-to-BGM conversion—while maintaining strict adherence to prompts across 50+ languages. This paves the way for powerful tools that seamlessly integrate into the creative workflows of music artists, producers, and content creators. 🎸

  • Developed by: [ACE-STEP]
  • Model type: [Text2Music]
  • Language(s): [50+ languages]
  • License: [MIT]

Evaluation

!image

🏗️ Architecture

!image

🦁 Model Zoo

!image

DiT Models

| DiT Model | Pre-Training | SFT | RL | CFG | Step | Refer audio | Text2Music | Cover | Repaint | Extract | Lego | Complete | Quality | Diversity | Fine-Tunability | Hugging Face |
|-----------|:------------:|:---:|:--:|:---:|:----:|:-----------:|:----------:|:-----:|:-------:|:-------:|:----:|:--------:|:-------:|:---------:|:---------------:|--------------|
| acestep-v15-base | ✅ | ❌ | ❌ | ✅ | 50 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | Medium | High | Easy | Link |
| acestep-v15-sft | ✅ | ✅ | ❌ | ✅ | 50 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | High | Medium | Easy | Link |
| acestep-v15-turbo | ✅ | ✅ | ❌ | ❌ | 8 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | Very High | Medium | Medium | Link |
| acestep-v15-turbo-rl | ✅ | ✅ | ✅ | ❌ | 8 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | Very High | Medium | Medium | To be released |

LM Models

| LM Model | Pretrain from | Pre-Training | SFT | RL | CoT metas | Query rewrite | Audio Understanding | Composition Capability | Copy Melody | Hugging Face |
|----------|---------------|:------------:|:---:|:--:|:---------:|:-------------:|:-------------------:|:----------------------:|:-----------:|--------------|
| acestep-5Hz-lm-0.6B | Qwen3-0.6B | ✅ | ✅ | ✅ | ✅ | ✅ | Medium | Medium | Weak | ✅ |
| acestep-5Hz-lm-1.7B | Qwen3-1.7B | ✅ | ✅ | ✅ | ✅ | ✅ | Medium | Medium | Medium | ✅ |
| acestep-5Hz-lm-4B | Qwen3-4B | ✅ | ✅ | ✅ | ✅ | ✅ | Strong | Strong | Strong | ✅ |

🙏 Acknowledgements

This project is co-led by ACE Studio and StepFun.

📖 Citation

If you find this project useful for your research, please consider citing:

```BibTeX
@misc{gong2026acestep,
title={ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation},
author={Junmin Gong, Yulin Song, Wenxiao Zhao, Sen Wang, Shengyuan Xu, Jing Guo},
howpublished={\url{https://github.com/ace-step/ACE-Step-1.5}},
year={2026},
note={GitHub repository}
}

查看官方来源