Text-to-Speech
Transformers
ONNX
teratts_onnx
feature-extraction
onnxruntime
russian
english
custom-code
custom_code
Instructions to use vlapky/TeraTTSv2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vlapky/TeraTTSv2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="vlapky/TeraTTSv2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vlapky/TeraTTSv2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": ["TeraTTSModel"], | |
| "automatic_russian_stress": true, | |
| "auto_map": { | |
| "AutoConfig": "configuration_teratts.TeraTTSConfig", | |
| "AutoModel": "modeling_teratts.TeraTTSModel" | |
| }, | |
| "default_diffusion_model": "distilled", | |
| "default_voice": "ru_f1", | |
| "cross_language_prompt_note": "For an English reference voice speaking Russian, try duration_scale below 1.0.", | |
| "model_type": "teratts_onnx", | |
| "sample_rate": 44100, | |
| "voices": ["eng_f3", "eng_f4_whisper", "eng_f5", "eng_m2_whisper", "eng_m3", "eng_m4", "ru_f1", "ru_f2", "ru_m1", "ru_m5"] | |
| } | |