Skip to content

GitLab

Unverified Commit 18ee767d authored by Chia-Yu Hung's avatar Chia-Yu Hung Committed by GitHub
Browse files

Update README.md

parent e6f81486
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
README.md
View file @ 18ee767d
...@@ -30,7 +30,7 @@ TangoFlux consists of FluxTransformer blocks which are Diffusion Transformer (Di ...@@ -30,7 +30,7 @@ TangoFlux consists of FluxTransformer blocks which are Diffusion Transformer (Di
## Inference with TangoFlux ## Inference with TangoFlux
Download the TangoFlux model and generate audio from a text prompt: Download the TangoFlux model and generate audio from a text prompt:
TangoFlux can generate audio up to 30seconds through passing in a duration variable in model.generate function.
```python ```python
import torchaudio import torchaudio
from tangoflux import TangoFluxInference from tangoflux import TangoFluxInference
...@@ -41,7 +41,7 @@ audio = model.generate('Hammer slowly hitting the wooden table', steps=50, durat ...@@ -41,7 +41,7 @@ audio = model.generate('Hammer slowly hitting the wooden table', steps=50, durat
Audio(data=audio, rate=44100) Audio(data=audio, rate=44100)
``` ```
Our evaluation shows that inferencing with 50 steps yield the best results, which takes about 3seconds. For faster inference, consider setting steps to 25 that yield similar audio quality.
## Evaluation Scripts ## Evaluation Scripts
......
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