Instructions to use declare-lab/tango with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use declare-lab/tango with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="declare-lab/tango")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("declare-lab/tango", dtype="auto") - Notebooks
- Google Colab
- Kaggle
VRAM requirements
#1
by makovan - opened
Hello,
First of all, amazing work!
I would like to try this out but it looks like I'm running out of memory, I have a 10GB RTX 3080, is there anyway I could make it run or is more memory required?
Thank you
Fixed it by changing this line
tango = Tango("declare-lab/tango", "cpu")
Takes a while but at least it works :)
This comment has been hidden
In our A6000 GPU, the required VRAM is around 13GB for full precision inference with a batch size of 1. I will add a script for fp16 inference of TANGO in our GitHub repository soon which should reduce the memory footprint. Stay tuned!