Move resource badges above titles and simplify the model card
Browse files
README.md
CHANGED
|
@@ -11,13 +11,9 @@ library_name: pytorch
|
|
| 11 |
pipeline_tag: audio-to-audio
|
| 12 |
---
|
| 13 |
|
| 14 |
-
# SteerSound
|
| 15 |
-
|
| 16 |
-
<div align="center">
|
| 17 |
-
|
| 18 |
[](https://gewu-lab.github.io/SteerSound/) [](https://github.com/GeWu-Lab/SteerSound) [](https://huggingface.co/GeWu-Lab/SteerSound) [](https://huggingface.co/datasets/GeWu-Lab/SteerSound)
|
| 19 |
|
| 20 |
-
|
| 21 |
|
| 22 |
SteerSound is an instruction-guided audio editing model supporting sound generation, addition, removal, replacement, pitch modification and volume modification. This repository provides the final SteerSound weights and the components needed for inference.
|
| 23 |
|
|
@@ -104,8 +100,6 @@ Input files are downmixed to mono, resampled to 16 kHz, and truncated or right-p
|
|
| 104 |
|
| 105 |
**GPU memory for inference: approximately 8 GB** (BF16, batch size 1, 10-second audio).
|
| 106 |
|
| 107 |
-
##
|
| 108 |
|
| 109 |
The DiT and VAE weights are stored in BF16. The T5 encoder and vocoder files are stored in FP32 and cast to the runtime dtype when loaded. Architecture and audio settings are in `config.json`.
|
| 110 |
-
|
| 111 |
-
The [SteerSound dataset](https://huggingface.co/datasets/GeWu-Lab/SteerSound) contains plain instructions and input audio. Only the training split provides paired target audio; all validation/test splits, including Complex, provide input audio only. Evaluation protocols and training code are documented in the [code repository](https://github.com/GeWu-Lab/SteerSound).
|
|
|
|
| 11 |
pipeline_tag: audio-to-audio
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
[](https://gewu-lab.github.io/SteerSound/) [](https://github.com/GeWu-Lab/SteerSound) [](https://huggingface.co/GeWu-Lab/SteerSound) [](https://huggingface.co/datasets/GeWu-Lab/SteerSound)
|
| 15 |
|
| 16 |
+
# SteerSound
|
| 17 |
|
| 18 |
SteerSound is an instruction-guided audio editing model supporting sound generation, addition, removal, replacement, pitch modification and volume modification. This repository provides the final SteerSound weights and the components needed for inference.
|
| 19 |
|
|
|
|
| 100 |
|
| 101 |
**GPU memory for inference: approximately 8 GB** (BF16, batch size 1, 10-second audio).
|
| 102 |
|
| 103 |
+
## Model files
|
| 104 |
|
| 105 |
The DiT and VAE weights are stored in BF16. The T5 encoder and vocoder files are stored in FP32 and cast to the runtime dtype when loaded. Architecture and audio settings are in `config.json`.
|
|
|
|
|
|