-
when we use the model to infer,why need the .wav files?
-
I see you claimed that "achieving better voice quality and faster synthesis speed on a single CPU". Can you share a value or the speed compared to the original hifigan?
-
```
05/14 04:33:48 AM gpu available: True, used: True
| model Arch: OfflineGaussianDiffusion
....
Traceback (most recent call last):
File "tasks/run.py", line 15, in
run_task()
F…
-
I want to test opencpop preitrain model on unseen song. I don't know how to generate the wav file.
1. What data I should prepare for model?
2. How to do it? I saw `test_step` in `FastSpeech2Task…
-
Hi
I am curious if we increase the number of layers for the duration, pitch, and energy using the 'duration_predictor_layers' parameter and some other parameters in the architecture, will it improve…
-
Hey guys, I found you set `uv = f0 = 0` at line 57, what's the intension behind this?
https://github.com/NATSpeech/NATSpeech/blob/aef3aa8899c82e40a28e4f59d559b46b18ba87e8/utils/audio/pitch/utils.py#…
-
https://github.com/MoonInTheRiver/DiffSinger/blob/3d050f76aefb766d004fddcf52e9307affefd3c4/utils/pitch_utils.py#L45-L51
Hey guys I found you set `uv = f0 = 0` at line 50, what's the intension …
-
VITS is the best TTS system, I think. So VISinger is attractive.
https://github.com/jaywalnut310/vits is the path of VITS code.
https://zhangyongmao.github.io/VISinger/ is the demo of VISinger.
-
Hi, thank you very much for your valuable SVS corpus and code.
I strictly follow your instruction until step "2. Training Example" for SVS, in https://github.com/MoonInTheRiver/DiffSinger . Then I …
-
> > Hi, thank you very much for your valuable SVS corpus and code.
> > I strictly follow your instruction until step "2. Training Example" for SVS, in https://github.com/MoonInTheRiver/DiffSinger . T…