---
title: ZipVoice-Vietnamese-150h
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/ZipVoice-Vietnamese-150h"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/ZipVoice-Vietnamese-150h.md"
repository: AI-ModelScope/ZipVoice-Vietnamese-150h
last_updated: 2026-01-30
license: cc-by-nc-sa-4.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - vi
downloads: 55
stars: 0
tags:
  - text-to-speech
  - vietnamese
  - ai-model
  - deep-learning
---

# ZipVoice-Vietnamese-150h

> ZipVoice-Vietnamese-150h - AI-ModelScope 在 ModelScope 开源的模型。🛑 Important Note ⚠️ This model is only intended for research purposes. Access requests must be made using an institutional, academic, or corporate email. Requests from public email providers will…

AI-ModelScope/ZipVoice-Vietnamese-150h 是 ModelScope 魔搭社区上的text-to-speech模型，采用 cc-by-nc-sa-4.0 许可。

- **Repository**: AI-ModelScope/ZipVoice-Vietnamese-150h
- **License**: cc-by-nc-sa-4.0
- **Tasks**: text-to-speech
- **Tags**: text-to-speech, vietnamese, ai-model, deep-learning
- **Downloads**: 55
- **Stars**: 0
- **Last updated**: 2026-01-30

Source: https://www.modelscope.cn/models/AI-ModelScope/ZipVoice-Vietnamese-150h

---

# 🛑 Important Note ⚠️  
This model is only intended for **research purposes**.  
**Access requests must be made using an institutional, academic, or corporate email**. Requests from public email providers will be denied. We appreciate your understanding.  

# 🎙️ ZipVoice-Vietnamese-150h
ZipVoice is a series of fast and high-quality zero-shot TTS models based on flow matching.

Key features:
1. Small and fast: only 123M parameters.

2. High-quality voice cloning: state-of-the-art performance in speaker similarity, intelligibility, and naturalness.

3. Multi-lingual: support Chinese and English.

4. Multi-mode: support both single-speaker and dialogue speech generation.

This checkpoint is a compact fine-tuned version of ZipVoice trained on 150 hours of Vietnamese speech.  

🔗 For more fine-tuning and inference experiments, visit: https://github.com/k2-fsa/ZipVoice.  

📜 **License:** [CC-BY-NC-SA-4.0](https://spdx.org/licenses/CC-BY-NC-SA-4.0) — Non-commercial research use only.  

---

## 📌 Model Details

- **Dataset:** VLSP 2021, VLSP 2022, VLSP 2023, VietTTS, TeacherDinh-UEH and some speech sources from YouTube channels.
- **Total dataset durations:** 150 hours
- **Data processing Technique:**
  - Remove all music background from audios, using facebook demucs model: https://github.com/facebookresearch/demucs
  - Do not use audio files shorter than 1 second or longer than 30 seconds.
  - Keep the default punctuation marks unchanged.
  - Normalize to lowercase format.
- **Training Configuration:**  
  - **Base Model:** ZipVoice with espeak-ng vi for tokenizer  
  - **GPU:** RTX 3090  
  - **Batch Siz:** Max duration 200  
- **Training Progress:** Stopped at **96,000 steps at epoch 30**  

---

## 🛑 Update Note
Thank you, Teacher Định from the University of Economics Ho Chi Minh City (UEH), for providing me with an additional 50-hours high-quality labeled dataset.