Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implement FreeVC #2451

Merged
merged 10 commits into from
Mar 25, 2023
Merged

Implement FreeVC #2451

Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
f34fc51
Update .gitignore
erogol Mar 23, 2023
ad5bdfc
Draft FreeVC implementation
erogol Mar 23, 2023
a598a23
Tests and relevant updates
erogol Mar 23, 2023
ac39119
Update API tests
erogol Mar 23, 2023
fa24171
Add missings
erogol Mar 24, 2023
4e4523a
Update requirements
erogol Mar 24, 2023
d78e75f
:(
erogol Mar 24, 2023
a45fbed
Lazy handle for vc
erogol Mar 25, 2023
03d8d9d
Update docs for voice conversion
erogol Mar 25, 2023
52ef042
Make style
erogol Mar 25, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Lazy handle for vc
  • Loading branch information
@erogol
erogol committed Mar 25, 2023
commit a45fbed4d008680b4dc2ca11989dc8cbcceefcb3
7 changes: 5 additions & 2 deletions TTS/api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
from pathlib import Path
import tempfile

from TTS.utils.audio.numpy_transforms import save_wav
from TTS.utils.manage import ModelManager
Expand Down Expand Up @@ -268,10 +269,12 @@ def tts_with_vc(self, text: str, language: str = None, speaker_wav: str = None):
Path to a reference wav file to use for voice cloning with supporting models like YourTTS.
Defaults to None.
"""
wav = self.tts(text=text, speaker=None, language=language)
with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as fp:
# Lazy code... save it to a temp file to resample it while reading it for VC
self.tts_to_file(text=text, speaker=None, language=language, file_path=fp.name)
if self.voice_converter is None:
self.load_vc_model_by_name("voice_conversion_models/multilingual/vctk/freevc24")
wav = self.voice_converter.voice_conversion(source_wav=wav, target_wav=speaker_wav)
wav = self.voice_converter.voice_conversion(source_wav=fp.name, target_wav=speaker_wav)
return wav

def tts_with_vc_to_file(
Expand Down