Text-to-Speech
Transformers
Safetensors
arktts
feature-extraction
audio
tts
voice-cloning
zero-shot
multilingual
custom_code
Instructions to use Audio8/Audio8-TTS-Preview-0.1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Audio8/Audio8-TTS-Preview-0.1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Audio8/Audio8-TTS-Preview-0.1b", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Audio8/Audio8-TTS-Preview-0.1b", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training Code
#1
by yukiarimo - opened
Hello!
Can you please release the full training code for both the model and codec?
Thanks!
Hi @yukiarimo ,
Thank you for your interest and suggestion!
At the moment, we have not scheduled the release of the training code, as preparing it for public release would require substantial additional work and careful validation to avoid reproducibility issues that could waste the computational resources.
We are considering consolidating the training details into a technical report, and may release the training code together with the report in the future. We will share an update if this becomes available.