search

GrandaddyShmax / audiocraft_plus

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
MIT License
561 stars 63 forks source link

Question: Generate multiple files at once? #29

Open tob-har opened 1 year ago

tob-har commented 1 year ago

Using the API and a simple python script to use model.generate, I can create multiple files in one run, simply by adding several prompts in a row. Is this possible with your app?

GrandaddyShmax commented 1 year ago

as of right now it does not exist in the current build

jasalt commented 11 months ago

@tob-har do you have example scripts you could share? I tried to use the Gradio API but it doesn't have any working examples and didn't dig deeper how it is set up. Doing batches would be very useful via scripting, or via UI (like in Stable Diffusion web ui).

jasalt commented 11 months ago

Quick Selenium automation script that inputs given parameters to the audiocraft_plus Web UI and keeps hitting the Generate button while generation is not in progress. Not most elegant solution but works https://gist.github.com/jasalt/8174773ffc8abc8c98b328155c4dfc83.

tob-har commented 11 months ago

@jasalt yes, you can take a look at my repo: https://github.com/tob-har/audiocraft-cablesGUI The file createaudio.py together with serverCables.py handle the audio generation. This is quite a custom approach… but maybe still helpful.