File tree 3 files changed +6
-5
lines changed
3 files changed +6
-5
lines changed Original file line number Diff line number Diff line change 1
1
"""
2
2
DiffSVC architecture with WaveNet denoiser and NSF-HiFiGAN vocoder.
3
3
4
- Comparing to v1, this version
4
+ Comparing to v1, this version
5
5
- Doesn't need spec stats anymore.
6
6
- Added dilation cycle to WaveNet denoiser.
7
7
- Used the log10 mel spectrogram.
Original file line number Diff line number Diff line change @@ -55,9 +55,11 @@ def launch_gradio(
55
55
speaker = gr .Dropdown (
56
56
label = "Speaker Name (Used for Multi-Speaker Models)" ,
57
57
choices = list (speaker_mapping .keys ()),
58
- value = speaker
59
- if speaker in speaker_mapping
60
- else list (speaker_mapping .keys ())[0 ],
58
+ value = (
59
+ speaker
60
+ if speaker in speaker_mapping
61
+ else list (speaker_mapping .keys ())[0 ]
62
+ ),
61
63
)
62
64
else :
63
65
speaker = gr .Number (
Original file line number Diff line number Diff line change 4
4
It aims to reduce errors for long utterances and detcect aspiration which is not detected by MFA.
5
5
"""
6
6
7
-
8
7
import librosa
9
8
import numpy as np
10
9
import parselmouth as pm
You can’t perform that action at this time.
0 commit comments