Skip to content

GitLab

Unverified Commit 5eefc23f authored by Soujanya Poria's avatar Soujanya Poria Committed by GitHub
Browse files

Update README.md

parent 9dc5652c
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 2 deletions
README.md
View file @ 5eefc23f
...@@ -24,8 +24,9 @@ TangoFlux consists of FluxTransformer blocks which are Diffusion Transformer (Di ...@@ -24,8 +24,9 @@ TangoFlux consists of FluxTransformer blocks which are Diffusion Transformer (Di
![cover-photo](assets/tangoflux.png) ![cover-photo](assets/tangoflux.png)
## Quickstart
TangoFlux is a Text To Audio (TTA) Model that is capable of generating stereo audio up to 30 seconds at 44.1kHz in about 3 seconds. TangoFlux can generate stereo audio for up to 30 seconds at 44.1kHz in about 3 seconds.
## Training TangoFlux ## Training TangoFlux
We use the accelerate package from Hugging Face for multi-gpu training. Run accelerate config from terminal and set up your run configuration by the answering the questions asked. We have default an accelerator config in the configs folder. We use the accelerate package from Hugging Face for multi-gpu training. Run accelerate config from terminal and set up your run configuration by the answering the questions asked. We have default an accelerator config in the configs folder.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment