Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- zh
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- CAM++
|
| 7 |
+
- 3D-Speaker
|
| 8 |
+
- Speaker Recognition & Verification
|
| 9 |
+
- Chinese & English
|
| 10 |
license: apache-2.0
|
| 11 |
+
datasets:
|
| 12 |
+
- 3D-Speaker
|
| 13 |
+
- voxceleb
|
| 14 |
+
- cnceleb
|
| 15 |
+
metrics:
|
| 16 |
+
- EER
|
| 17 |
+
- minDCF
|
| 18 |
---
|
| 19 |
+
|
| 20 |
+
# CAM++: A Fast and Efficient Speaker Recognition Network
|
| 21 |
+
CAM++ is a fast and efficient network based on a densely-connected time delay neural network (D-TDNN). This repository provides tools for extracting speaker embeddings and performing speaker verification tasks with a pretrained CAM++ model. It has been trained on a large-scale training dataset, which includes Chinese and English corpora.
|
| 22 |
+
|
| 23 |
+
|