Instructions to use pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0 # Run inference directly in the terminal: llama cli -hf pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0 # Run inference directly in the terminal: llama cli -hf pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0
Use Docker
docker model run hf.co/pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0
- LM Studio
- Jan
- Ollama
How to use pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf with Ollama:
ollama run hf.co/pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf with Docker Model Runner:
docker model run hf.co/pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0
- Lemonade
How to use pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf:Q8_0
Run and chat with the model
lemonade run user.VieNeu-TTS-0.3B-q8-gguf-Q8_0
List all available models
lemonade list
- Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,43 +16,62 @@ tags:
|
|
| 16 |
- gguf
|
| 17 |
---
|
| 18 |
|
| 19 |
-
# VieNeu-TTS-0.3B-Q8-GGUF (High
|
| 20 |
|
| 21 |
[](https://github.com/pnnbao97/VieNeu-TTS)
|
| 22 |
[](https://huggingface.co/pnnbao-ump/VieNeu-TTS-0.3B)
|
|
|
|
| 23 |
|
| 24 |
-
**VieNeu-TTS-0.3B-Q8-GGUF**
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
```bash
|
| 31 |
# 1. Clone repository
|
| 32 |
git clone https://github.com/pnnbao97/VieNeu-TTS.git
|
| 33 |
cd VieNeu-TTS
|
| 34 |
|
| 35 |
-
# 2.
|
| 36 |
uv sync
|
| 37 |
-
uv add llama-cpp-python==0.3.16
|
| 38 |
|
| 39 |
-
# 3.
|
| 40 |
uv run gradio_app.py
|
| 41 |
```
|
| 42 |
-
|
| 43 |
|
| 44 |
-
## 📊
|
| 45 |
-
- **
|
| 46 |
-
- **
|
| 47 |
-
- **
|
| 48 |
-
- **
|
| 49 |
|
| 50 |
-
## ⚠️
|
| 51 |
-
|
| 52 |
-
- **
|
| 53 |
-
-
|
|
|
|
| 54 |
|
| 55 |
-
## Citation
|
| 56 |
```bibtex
|
| 57 |
@misc{vieneutts03bggufq82026,
|
| 58 |
title = {VieNeu-TTS-0.3B-Q8-GGUF: High-Quality CPU-Optimized Vietnamese Text-to-Speech},
|
|
@@ -61,4 +80,7 @@ Mô hình này được phát hành dưới giấy phép **CC BY-NC 4.0**.
|
|
| 61 |
publisher = {Hugging Face},
|
| 62 |
howpublished = {\url{https://huggingface.co/pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf}}
|
| 63 |
}
|
| 64 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
- gguf
|
| 17 |
---
|
| 18 |
|
| 19 |
+
# 🦜 VieNeu-TTS-0.3B-Q8-GGUF (High-Quality CPU)
|
| 20 |
|
| 21 |
[](https://github.com/pnnbao97/VieNeu-TTS)
|
| 22 |
[](https://huggingface.co/pnnbao-ump/VieNeu-TTS-0.3B)
|
| 23 |
+
[](https://discord.gg/yJt8kzjzWZ)
|
| 24 |
|
| 25 |
+
**VieNeu-TTS-0.3B-Q8-GGUF** is a **Q8_0** quantized version of [VieNeu-TTS-0.3B](https://huggingface.co/pnnbao-ump/VieNeu-TTS-0.3B). This model provides a perfect balance between CPU performance and voice quality, retaining almost all the precision of the original PyTorch model.
|
| 26 |
|
| 27 |
+
Author: **Phạm Nguyễn Ngọc Bảo**
|
| 28 |
|
| 29 |
+
## ☕ Support This Project
|
| 30 |
+
|
| 31 |
+
Training high-quality TTS models requires significant GPU resources. If you find this model useful, please consider supporting the development:
|
| 32 |
+
|
| 33 |
+
[](https://buymeacoffee.com/pnnbao)
|
| 34 |
+
|
| 35 |
+
---
|
| 36 |
+
|
| 37 |
+
## �️ Requirements (eSpeak NG)
|
| 38 |
+
eSpeak NG is **mandatory** for phonemization.
|
| 39 |
+
- **Windows:** Download `.msi` from [eSpeak NG Releases](https://github.com/espeak-ng/espeak-ng/releases).
|
| 40 |
+
- **macOS:** `brew install espeak`
|
| 41 |
+
- **Linux:** `sudo apt install espeak-ng`
|
| 42 |
+
|
| 43 |
+
---
|
| 44 |
+
|
| 45 |
+
## 🚀 How to Use
|
| 46 |
+
|
| 47 |
+
Use the source code from GitHub for the best experience with full text preprocessing support:
|
| 48 |
|
| 49 |
```bash
|
| 50 |
# 1. Clone repository
|
| 51 |
git clone https://github.com/pnnbao97/VieNeu-TTS.git
|
| 52 |
cd VieNeu-TTS
|
| 53 |
|
| 54 |
+
# 2. Sync environment (requires uv)
|
| 55 |
uv sync
|
|
|
|
| 56 |
|
| 57 |
+
# 3. Launch Web UI
|
| 58 |
uv run gradio_app.py
|
| 59 |
```
|
| 60 |
+
In the UI, select **Backbone**: `VieNeu-TTS-0.3B-q8-gguf` and **Device**: `CPU`.
|
| 61 |
|
| 62 |
+
## 📊 Technical Specifications
|
| 63 |
+
- **Format**: GGUF (Q8_0)
|
| 64 |
+
- **Size**: ~300 MB
|
| 65 |
+
- **Quality**: ⭐⭐⭐⭐ (Near original PyTorch quality)
|
| 66 |
+
- **Performance**: Runs smoothly on modern CPUs with high efficiency.
|
| 67 |
|
| 68 |
+
## ⚠️ Licensing & Copyright
|
| 69 |
+
This model is released under the **CC BY-NC 4.0** license.
|
| 70 |
+
- ✅ **Free:** For students, researchers, and non-profit purposes.
|
| 71 |
+
- ⚠️ **Commercial/Enterprise:** Use for businesses or commercial products is strictly prohibited without prior authorization.
|
| 72 |
+
- **Commercial Licensing:** Please contact the author (**Phạm Nguyễn Ngọc Bảo**) for licensing terms (Estimated: **5,000 USD/year** - negotiable).
|
| 73 |
|
| 74 |
+
## 📑 Citation
|
| 75 |
```bibtex
|
| 76 |
@misc{vieneutts03bggufq82026,
|
| 77 |
title = {VieNeu-TTS-0.3B-Q8-GGUF: High-Quality CPU-Optimized Vietnamese Text-to-Speech},
|
|
|
|
| 80 |
publisher = {Hugging Face},
|
| 81 |
howpublished = {\url{https://huggingface.co/pnnbao-ump/VieNeu-TTS-0.3B-q8-gguf}}
|
| 82 |
}
|
| 83 |
+
```
|
| 84 |
+
|
| 85 |
+
---
|
| 86 |
+
**Made with ❤️ for the Vietnamese TTS community**
|