Text-to-Speech
Chatterbox
Vietnamese
English
viterbox
viterbox-tts
tts
vietnamese
voice-cloning
audio
speech-synthesis
Instructions to use dolly-vn/viterbox with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chatterbox
How to use dolly-vn/viterbox with Chatterbox:
# pip install chatterbox-tts import torchaudio as ta from chatterbox.tts import ChatterboxTTS model = ChatterboxTTS.from_pretrained(device="cuda") text = "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill." wav = model.generate(text) ta.save("test-1.wav", wav, model.sr) # If you want to synthesize with a different voice, specify the audio prompt AUDIO_PROMPT_PATH="YOUR_FILE.wav" wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH) ta.save("test-2.wav", wav, model.sr) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -48,29 +48,6 @@ inference: false
|
|
| 48 |
|
| 49 |
---
|
| 50 |
|
| 51 |
-
## 📊 Model Details
|
| 52 |
-
|
| 53 |
-
### Kiến trúc
|
| 54 |
-
|
| 55 |
-
| Component | Mô tả | Parameters |
|
| 56 |
-
|-----------|-------|------------|
|
| 57 |
-
| **T3** | Text-to-Token Transformer | 520M |
|
| 58 |
-
| **S3Gen** | Flow-matching Vocoder | ~150M |
|
| 59 |
-
| **Voice Encoder** | Speaker Embedding | ~5M |
|
| 60 |
-
| **Total** | | ~675M |
|
| 61 |
-
|
| 62 |
-
### Thông số kỹ thuật
|
| 63 |
-
|
| 64 |
-
| Thuộc tính | Giá trị |
|
| 65 |
-
|------------|---------|
|
| 66 |
-
| Sample Rate | 24,000 Hz |
|
| 67 |
-
| Audio Format | Mono, 16-bit |
|
| 68 |
-
| Vocabulary Size | 2,549 tokens |
|
| 69 |
-
| Max Text Length | 2,048 tokens |
|
| 70 |
-
| Max Audio Length | ~40 giây |
|
| 71 |
-
|
| 72 |
-
---
|
| 73 |
-
|
| 74 |
## 📚 Training Data
|
| 75 |
|
| 76 |
Model được fine-tune trên **3,000+ giờ** dữ liệu tiếng Việt chất lượng cao:
|
|
|
|
| 48 |
|
| 49 |
---
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
## 📚 Training Data
|
| 52 |
|
| 53 |
Model được fine-tune trên **3,000+ giờ** dữ liệu tiếng Việt chất lượng cao:
|