Mirrors/voice-cloning-collab
1
0
Fork 0
mirror of https://github.com/liuhaozhe6788/voice-cloning-collab.git synced 2026-05-18 05:04:51 +02:00
Code Issues Packages Projects Releases Wiki Activity

add speed adjustment file and praat script

Browse Source
This commit is contained in:
liuhaozhe6788
2022-09-26 09:16:30 +08:00
parent 51b71bb4a6
commit f0b6afc9e7
5 changed files with 735 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -6,5 +6,6 @@
**2022.07.29：** I added model validation for encoder, synthesizer and vocoder.<br>
**2022.08.02：** I added voxceleb train and dev data for encoder. I added noise reduce method for the output wav from vocoder.<br>
noisereduce reference: https://github.com/timsainb/noisereduce<br>
**2022.08.06：** I split the long text into short sentences using spacy for input of synthesizer. Make sure to install English dataset en_core_web_sm, say by python -m spacy download en_core_web_sm<br>
**2022.08.06：** I split the long text into short sentences using spacy for input of synthesizer. Make sure to install English dataset en_core_web_sm, say by ***python -m spacy download en_core_web_sm***<br>
**2022.09.02：** I set prop_decrease=0.6 for male and 0.9 for female in noisereduce function<br>
**2022.09.26：** I added speed adjustment for output audios using praat<br>