Update README.md for whisper-ppg
This commit is contained in:
parent
105c1c4197
commit
668f9ef57f
|
@ -177,7 +177,7 @@ python resample.py
|
||||||
### 2. Automatically split the dataset into training and validation sets, and generate configuration files.
|
### 2. Automatically split the dataset into training and validation sets, and generate configuration files.
|
||||||
|
|
||||||
```shell
|
```shell
|
||||||
python preprocess_flist_config.py --speech_encoder vec768l12
|
python preprocess_flist_config.py --speech_encoder whisper-ppg
|
||||||
```
|
```
|
||||||
|
|
||||||
speech_encoder has three choices
|
speech_encoder has three choices
|
||||||
|
@ -186,6 +186,7 @@ speech_encoder has three choices
|
||||||
vec768l12
|
vec768l12
|
||||||
vec256l9
|
vec256l9
|
||||||
hubertsoft
|
hubertsoft
|
||||||
|
whisper-ppg
|
||||||
```
|
```
|
||||||
|
|
||||||
If the speech_encoder argument is omitted, the default value is vec768l12
|
If the speech_encoder argument is omitted, the default value is vec768l12
|
||||||
|
|
Loading…
Reference in New Issue