Update README.md
Browse files
README.md
CHANGED
@@ -48,6 +48,9 @@ For a better experience, we encourage you to learn more about
|
|
48 |
## Pipeline description
|
49 |
This system is composed of a TDNN model coupled with statistical pooling. A classifier, trained with Categorical Cross-Entropy Loss, is applied on top of that.
|
50 |
|
|
|
|
|
|
|
51 |
## Install SpeechBrain
|
52 |
|
53 |
First of all, please install SpeechBrain with the following command:
|
|
|
48 |
## Pipeline description
|
49 |
This system is composed of a TDNN model coupled with statistical pooling. A classifier, trained with Categorical Cross-Entropy Loss, is applied on top of that.
|
50 |
|
51 |
+
The system is trained with recordings sampled at 16kHz (single channel).
|
52 |
+
The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *classify_file* if needed.
|
53 |
+
|
54 |
## Install SpeechBrain
|
55 |
|
56 |
First of all, please install SpeechBrain with the following command:
|