Instructions to use TeraSpace/TeraTTSv2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TeraSpace/TeraTTSv2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="TeraSpace/TeraTTSv2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TeraSpace/TeraTTSv2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Лицензия
Здравствуйте! Хотим использовать TeraTTSv2 в десктопном приложении с локальным ONNX-инференсом. Код TeraTTS на GitHub у вас под MIT, но у карточек моделей на HuggingFace поле license не заполнено - ни у TeraTTSv2, ни у моделей организации TeraTTS. Не могли бы вы проставить лицензию на веса (MIT или Apache-2.0)? Без явного указания мы вынуждены считать их «все права сохранены» и не можем включить в сборку. Спасибо за v2 — русский там заметно лучше того, что мы используем сейчас.
Hello!
We'd like to use TeraTTSv2 in a desktop application with local ONNX inference.
Your TeraTTS code on GitHub is MIT-licensed, but the license field is not filled in on the Hugging Face model cards - neither for TeraTTSv2 nor for the models under the TeraTTS organization.
Could you please set a license for the weights (MIT or Apache-2.0)? Without an explicit grant we have to treat them as "all rights reserved", which means we can't include them in our build.
Thank you for v2 — the Russian is noticeably better than what we're currently using.