Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
-
title: Audio Diffusion
|
| 3 |
emoji: 🎵
|
| 4 |
colorFrom: pink
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 3.1.4
|
| 8 |
app_file: app.py
|
|
@@ -125,6 +125,7 @@ accelerate launch --config_file config/accelerate_sagemaker.yaml \
|
|
| 125 |
```bash
|
| 126 |
--scheduler ddim
|
| 127 |
```
|
|
|
|
| 128 |
|
| 129 |
Inference can the be run with far fewer steps than the number used for training (e.g., ~50), allowing for much faster generation. Without retraining, the parameter `eta` can be used to replicate a DDPM if it is set to 1 or a DDIM if it is set to 0, with all values in between being valid. When `eta` is 0 (the default value), the de-noising procedure is deterministic, which means that it can be run in reverse as a kind of encoder that recovers the original noise used in generation. A function `encode` has been added to `AudioDiffusionPipeline` for this purpose. It is then possible to interpolate between audios in the latent "noise" space using the function `slerp` (Spherical Linear intERPolation).
|
| 130 |
|
|
|
|
| 1 |
---
|
| 2 |
+
title: Audio Diffusion Style Transfer
|
| 3 |
emoji: 🎵
|
| 4 |
colorFrom: pink
|
| 5 |
+
colorTo: purple
|
| 6 |
sdk: gradio
|
| 7 |
sdk_version: 3.1.4
|
| 8 |
app_file: app.py
|
|
|
|
| 125 |
```bash
|
| 126 |
--scheduler ddim
|
| 127 |
```
|
| 128 |
+
forked from https://huggingface.co/spaces/teticio/audio-diffusion lets get the style transfer in the app and possibly in painting eventually
|
| 129 |
|
| 130 |
Inference can the be run with far fewer steps than the number used for training (e.g., ~50), allowing for much faster generation. Without retraining, the parameter `eta` can be used to replicate a DDPM if it is set to 1 or a DDIM if it is set to 0, with all values in between being valid. When `eta` is 0 (the default value), the de-noising procedure is deterministic, which means that it can be run in reverse as a kind of encoder that recovers the original noise used in generation. A function `encode` has been added to `AudioDiffusionPipeline` for this purpose. It is then possible to interpolate between audios in the latent "noise" space using the function `slerp` (Spherical Linear intERPolation).
|
| 131 |
|