mei/SoulX-Singer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
jlqian98
2026-03-12 16:50:00 +08:00
parent ca3b600c07
commit 05dda87e4b
1 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+10 -6
View File
@@ -21,13 +21,15 @@
## 🎵 Overview
**SoulX-Singer** is a high-fidelity, zero-shot singing voice synthesis model that enables users to generate realistic singing voices for unseen singers.
It supports **melody-conditioned (F0 contour)** and **score-conditioned (MIDI notes)** control for precise pitch, rhythm, and expression.
**SoulX-Singer** is a high-fidelity, zero-shot singing voice synthesis model that enables users to generate realistic singing voices for unseen singers. It supports **melody-conditioned (F0 contour)** and **score-conditioned (MIDI notes)** control for precise pitch, rhythm, and expression.
**SoulX-Singer-SVC** is a singing voice conversion model finetuned from **SoulX-Singer**, enabling users to perform singing voice conversion without lyric and MIDI transcriptions.
---
## ✨ Key Features
#### SoulX-Singer
- **🎤 Zero-Shot Singing** – Generate high-fidelity voices for unseen singers, no fine-tuning needed.
- **🎵 Flexible Control Modes** – Melody (F0) and Score (MIDI) conditioning.
- **📚 Large-Scale Dataset** – 42,000+ hours of aligned vocals, lyrics, notes across Mandarin, English, Cantonese.
@@ -35,6 +37,11 @@ It supports **melody-conditioned (F0 contour)** and **score-conditioned (MIDI no
- **✏️ Singing Voice Editing** – Modify lyrics while keeping natural prosody.
- **🌐 Cross-Lingual Synthesis** – High-fidelity synthesis by disentangling timbre from content.
#### SoulX-Singer-SVC
- **🎙️ Zero-Shot Timbre and Style Transfer** – Transfer singer identity and style to unseen voices without per-speaker fine-tuning.
- **🌍 Language-Agnostic Conversion** – Works across multilingual singing content.
- **🔄 Transcription-Free Audio-to-Audio Conversion** – Convert target singing directly without lyrics transcription or MIDI inputs.
---
<p align="center">
@@ -109,12 +116,9 @@ Download the SVS, SVC model and preprocessing models:
```sh
pip install -U huggingface_hub
# Download the SoulX-Singer SVS model
# Download the SoulX-Singer SVS and SVC model
hf download Soul-AILab/SoulX-Singer --local-dir pretrained_models/SoulX-Singer
# Download the SoulX-Singer SVC model
hf download Soul-AILab/SoulX-Singer-SVC --local-dir pretrained_models/SoulX-Singer-SVC
# Download models required for preprocessing
hf download Soul-AILab/SoulX-Singer-Preprocess --local-dir pretrained_models/SoulX-Singer-Preprocess
```