projecte-aina
/

tts-ca-coqui-vits-multispeaker

Model card Files Files and versions Community

Gerard Muniesa commited on Dec 5, 2022

Commit

681919a

·

1 Parent(s): a5fbdd4

[FIX] Minor Issues

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -47,7 +47,7 @@ wavs = synthesizer.tts(text, speaker_idx)
 ## Training
 ### Training Procedure
 ### Data preparation
-The data has been processed using the script process_data.py, which reduces the sampling frequency of the audios, eliminates silences, adds padding and structures the data in the format accepted by the framework. You can find more information here.
 ### Hyperparameter

 ## Training
 ### Training Procedure
 ### Data preparation
+The data has been processed using the script [process_data.sh](https://huggingface.co/projecte-aina/tts-multispeaker-ca-aina/blob/main/data_processing/process_data.sh), which reduces the sampling frequency of the audios, eliminates silences, adds padding and structures the data in the format accepted by the framework. You can find more information [here](https://huggingface.co/projecte-aina/tts-multispeaker-ca-aina/blob/main/data_processing/README.md).
 ### Hyperparameter