Instructions to use oddadmix/chatterbox-egyptian-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chatterbox
How to use oddadmix/chatterbox-egyptian-v0 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
fine tune script
did the finetune script worked ? did you use flow finetune_t3.py ? share the script if it worked and dataset
Can you please provide the code for fine-tuning? and the format of data that you had fine-tuned the model on.
Hi, sorry for the late reply.
here is the training script https://github.com/Oddadmix/chatterbox-multilingual-finetuning
The data was studio recorded around 75 hours of single speaker.
That script never worked in Kaggle or colab , what GPU used for training ?/
Is that an assumption or a question?
A6000 was used for training.
how to use it with comfyui noob here plz help?
https://huggingface.co/spaces/rahul7star/Chatterbox-TRAIN here is the Train code tks one can run in zeroGPU