holm/Thorsten-Voice
1
0
Fork 0
forked from extern/Thorsten-Voice
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Added download link to v03 dataset.

Browse Source
This commit is contained in:
Thorsten Müller 2021-02-10 19:46:21 +01:00 committed by GitHub
parent 09705597b8
commit cca10c215e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -84,7 +84,8 @@ If you wanna use just a dataset subset (phase1 and/or phase2 and/or phase3) you
Version | Description | Date | Link
------------ | ------------- | ------------- | -------------
thorsten-de-v01 | Initial version | 2020-06-28 | [Google Drive Download v01](https://drive.google.com/file/d/1yKJM1LAOQpRVojKunD9r8WN_p5KzBxjc/view?usp=sharing)
thorsten-de-v02 | normalized to -24dB and split metadata.csv into shuffeled metadata_train.csv and metadata_val.csv | 2020-08-22 | [Google Drive Download v02](https://drive.google.com/file/d/1mGWfG0s2V2TEg-AI2m85tze1m4pyeM7b/view?usp=sharing)
thorsten-de-v02 | Normalized to -24dB and split metadata.csv into shuffeled metadata_train.csv and metadata_val.csv | 2020-08-22 | [Google Drive Download v02](https://drive.google.com/file/d/1mGWfG0s2V2TEg-AI2m85tze1m4pyeM7b/view?usp=sharing)
thorsten-de-v03 | Based on v02 dataset, but with increased speed by 10% (using ffmpeg atempo=1.1). | 2021-02-10 | [Google Drive Download v03](https://drive.google.com/file/d/134_UramfCRoAxRrOnhbPJ2YHHTwxRtr-/view?usp=sharing)
# Trained tacotron2 model "thorsten"