Instructions to use teticio/audio-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use teticio/audio-encoder with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("teticio/audio-encoder", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
I ran the code it analyzed my files for a day and nothing happened
#1
by dpe1 - opened
I ran
from audiodiffusion.audio_encoder import AudioEncoder
audio_encoder = AudioEncoder.from_pretrained("teticio/audio-encoder")
audio_encoder.encode()
What is supposed to happen after I run it? It just closed
Try running on just one file to being with like so:
audio_encoder.encode(["file.mp3"])
If you do this in a Jupyter notebook, it will output a vector of numbers for this file. So then you can try on more files and do something with the vectors (e.g., look at cosine proximity between them, cluster them, feed into a classification model, or use to do coniditional generation with audiodiffusers)
teticio changed discussion status to closed