Instructions to use Aratako/MioTTS-2.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Aratako/MioTTS-2.6B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Aratako/MioTTS-2.6B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Aratako/MioTTS-2.6B") model = AutoModelForCausalLM.from_pretrained("Aratako/MioTTS-2.6B") - Notebooks
- Google Colab
- Kaggle
Please Add Demo of 2.6b and 1.7B with voice cloning to test.
Hello Team, this will be helpful.
Hello @krigeta , thanks for the suggestion!
I noticed on your profile that you have a Pro account. Since Pro users get free access to ZeroGPU, you can actually spin this up yourself quite easily!
You can simply duplicate the 0.1B demo space below:
https://huggingface.co/spaces/Aratako/MioTTS-0.1B-Demo
Then, just modify line 20 in app.py to specify the model size you want (2.6B or 1.7B). It should work out of the box.
Feel free to give it a try!
Hello @krigeta , thanks for the suggestion!
I noticed on your profile that you have a Pro account. Since Pro users get free access to ZeroGPU, you can actually spin this up yourself quite easily!
You can simply duplicate the 0.1B demo space below:
https://huggingface.co/spaces/Aratako/MioTTS-0.1B-DemoThen, just modify line 20 in app.py to specify the model size you want (2.6B or 1.7B). It should work out of the box.
Feel free to give it a try!
thank you so much and it is working great!
it would be great for non zero users to have a drop down to select the dfferent model.