Update README.md
Browse files
README.md
CHANGED
|
@@ -44,6 +44,9 @@ frequency domain. Then, a bidirectional LSTM with projection layers is connected
|
|
| 44 |
to a final DNN to obtain the final acoustic representation that is given to
|
| 45 |
the CTC and attention decoders.
|
| 46 |
|
|
|
|
|
|
|
|
|
|
| 47 |
## Install SpeechBrain
|
| 48 |
|
| 49 |
First of all, please install SpeechBrain with the following command:
|
|
|
|
| 44 |
to a final DNN to obtain the final acoustic representation that is given to
|
| 45 |
the CTC and attention decoders.
|
| 46 |
|
| 47 |
+
The system is trained with recordings sampled at 16kHz (single channel).
|
| 48 |
+
The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *transcribe_file* if needed.
|
| 49 |
+
|
| 50 |
## Install SpeechBrain
|
| 51 |
|
| 52 |
First of all, please install SpeechBrain with the following command:
|