yangwang825
commited on
Commit
•
d25916e
1
Parent(s):
aaf6353
Update README.md
Browse files
README.md
CHANGED
@@ -28,7 +28,9 @@ This repository provides a pretrained ECAPA-TDNN model using SpeechBrain. The sy
|
|
28 |
|
29 |
# Pipeline description
|
30 |
|
31 |
-
This system is composed of an ECAPA-TDNN model. It is a combination of convolutional and residual blocks. The embeddings are extracted using attentive statistical pooling. The system is trained with Additive Margin Softmax Loss.
|
|
|
|
|
32 |
|
33 |
# Performance
|
34 |
|
|
|
28 |
|
29 |
# Pipeline description
|
30 |
|
31 |
+
This system is composed of an ECAPA-TDNN model. It is a combination of convolutional and residual blocks. The embeddings are extracted using attentive statistical pooling. The system is trained with Additive Margin Softmax Loss.
|
32 |
+
|
33 |
+
We use FBank (16kHz, 25ms frame length, 10ms hop length, 80 filter-bank channels) as the input features. It was trained using initial learning rate of 0.001 and batch size of 512 with cyclical learning rate policy (CLR) for 10 epochs on 4 A100 GPUs. We employ additive noises and reverberation from [MUSAN](http://www.openslr.org/17/) and [RIR](http://www.openslr.org/28/) datasets to enrich the supervised information. The pre-training progress takes approximately seven days for the ECAPA-TDNN model.
|
34 |
|
35 |
# Performance
|
36 |
|