Instructions to use suno/bark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use suno/bark with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="suno/bark")# Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("suno/bark") model = AutoModelForTextToWaveform.from_pretrained("suno/bark") - Notebooks
- Google Colab
- Kaggle
Is it possible to train on custom dataset?
#17
by sneakybeaky - opened
Hello everyone. Is it possible to train on custom dataset? If it is, how dataset should look like and how to train it? Is there any code examples? Thanks in advance!
voices are not trained on "dataset", it is trained by sequentially prompts. You may use phrases that wake up the emotions you want in the voice. Don't use the same prompt you used before, or it will hallucinate.
Join Discord server for more help: https://discord.gg/suno-ai