Update README.md
Browse files
README.md
CHANGED
|
@@ -45,6 +45,8 @@ transformer. Hence, the decoding also incorporates the CTC probabilities.
|
|
| 45 |
|
| 46 |
To Train this system from scratch, [see our SpeechBrain recipe](https://github.com/speechbrain/speechbrain/tree/develop/recipes/AISHELL-1/ASR/transformer).
|
| 47 |
|
|
|
|
|
|
|
| 48 |
|
| 49 |
## Install SpeechBrain
|
| 50 |
|
|
|
|
| 45 |
|
| 46 |
To Train this system from scratch, [see our SpeechBrain recipe](https://github.com/speechbrain/speechbrain/tree/develop/recipes/AISHELL-1/ASR/transformer).
|
| 47 |
|
| 48 |
+
The system is trained with recordings sampled at 16kHz (single channel).
|
| 49 |
+
The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *transcribe_file* if needed.
|
| 50 |
|
| 51 |
## Install SpeechBrain
|
| 52 |
|