Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- onnx
|
| 5 |
+
- audio
|
| 6 |
+
- sam-audio
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# SAM-Audio-Small ONNX
|
| 10 |
+
|
| 11 |
+
This repository contains the ONNX version of the SAM-Audio-Small model.
|
| 12 |
+
|
| 13 |
+
## Contents
|
| 14 |
+
|
| 15 |
+
- `dacvae_encoder.onnx`: DAC-VAE Encoder
|
| 16 |
+
- `dacvae_decoder.onnx`: DAC-VAE Decoder
|
| 17 |
+
- `dit_single_step.onnx`: DiT Single Step model
|
| 18 |
+
- `t5_encoder.onnx`: T5 Text Encoder
|
| 19 |
+
- `tokenizer/`: T5 Tokenizer files
|
| 20 |
+
|
| 21 |
+
## Usage
|
| 22 |
+
|
| 23 |
+
These models are intended to be used with the `sam-audio` inference pipeline.
|