Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,43 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
tags:
|
| 4 |
+
- audio
|
| 5 |
+
- speech
|
| 6 |
+
- target-speaker-extraction
|
| 7 |
+
- source-separation
|
| 8 |
+
- speakerbeam
|
| 9 |
+
- dprnn
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
datasets:
|
| 12 |
+
- wsj0-2mix
|
| 13 |
+
- librimix
|
| 14 |
+
- wham
|
| 15 |
+
- whamr
|
| 16 |
+
library_name: pytorch
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# TSExcalibur
|
| 20 |
+
|
| 21 |
+
🎯 **TSExcalibur** is a modular and extensible toolkit for **Target Speaker Extraction (TSE)**.
|
| 22 |
+
|
| 23 |
+
> **GitHub Repository**: [youzhenghai/TSExcalibur](https://github.com/youzhenghai/TSExcalibur)
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
## 🧠 Features
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
- Implementations of leading TSE models
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
## 🚀 Usage
|
| 37 |
+
|
| 38 |
+
Coming soon! In the meantime, you can clone the repo and run:
|
| 39 |
+
|
| 40 |
+
```bash
|
| 41 |
+
git clone https://github.com/youzhenghai/TSExcalibur.git
|
| 42 |
+
cd TSExcalibur
|
| 43 |
+
# Set up your environment and run training or inference scripts
|