-
Have you tried changing the vocoder from Waveglow to HiFi-GAN? HiFi-GAN is faster and requires less VRAM. Alternatively, you could try adding a different vocoder.
-
Hi. This is an incredible great idea. I was looking through the code and was a bit confused by the diffusion vocoder models.
https://github.com/nkandpa2/music_enhancement/blob/b6ce281c35dd22441f9e5…
-
Hi, @haoheliu. Thank you for your awesome work.
1. After read code on the vocoder part, I found that there is only a pre-trained model and no training steps. Why is there no implementation of this …
-
I went through the trouble of writing a SST to TTS system that does not work very well. I was hoping if there was interest in this, I would like this in pulse effects which I use as a fixture in my OS…
-
I replicated the results of VITS and Matcha-TTS on a single speaker Chinese dataset and found that the timbre similarity of Matcha-TTS is lower than that of VITS, especially in the high-frequency deta…
-
```python
[DDSP Model] Minimum-Phase harmonic Source Combtooth Subtractive Synthesiser
Traceback (most recent call last):
File "C:\Users\cross\Downloads\MNP-SVC\train.py", line 48, in
mode…
-
hello,
the provided vocoder checkpoint using mHubert does not support multi-speaker. Do you have a multi-speaker checkpoint?
`mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj`
-
### Single speaker
We stopped the training at 680K step.
You can find some results at https://twidddj.github.io/docs/vocoder.
We tested the vocoder on the set of two group: 1) samples from the d…
-
hi,
i train the firefly vocoder in 24k and it will end up NAN loss in the end, how to fix this error.
![image](https://github.com/fishaudio/vocoder/assets/13691793/95464896-5def-4ff2-95e8-b8a6a1…
-
Hi,
I am trying to setup Fastspeech2 with LPCNet based on this LPCTron repo. I am able to synthesise audio but audio gets clipped at the end. For LPCNet usage, custom 20dim features are required to…