-
Observing that there is no mature data preprocessing in this project, which directly uses raw data for training, we propose to add data preprocessing
-
Hi,
I am training the V1 version of HiFi-GAN. I downsampled wavs to 16kHz and used a hopsize of 200 frames to make Mel-spectrums. Accordingly, I configed the upsampling scales as [5, 5, 4, 2].
A…
-
I use this shape of Mel to train the hifi gan, it has no any error when training. however, when I use the model to inference from tacotron file ,is reminds me it must be 80 channels
![图像2023-2-26 0…
-
Hello!
I have trained GradTTS on quite a few datasets and observed that it produces excellent results on most of the voices, but the generated results on heavy voices sound very robotic! Can anyone…
-
Hi, I want to know what config does you use when you train the hifigan model of DataBaker to get the samples in the webset https://light1726.github.io/vaenar-tts/.
With these parameters clearifie…
-
Hi! How this work compares with UnivNet for which one you already implemented code: https://github.com/rishikksh20/UnivNet-pytorch
This paper is a little bit newer but afaik they're more concerned ab…
-
do we have to put hifigan's check point at --path_ckpt argument of inference.py? for testing the samples
-
Dear Paveel,
Thanks a lot for releasing the supplementary material at https://arxiv.org/pdf/2203.13086v4.pdf and releasing the architecture code at this repo.
However, I don't find in the Githu…
-
Your work is really impressive. In your code, I could not find the SpeechAutoEncoder class. Could you please provide the code for this part and the weights? Many thanks.
HLSUD updated
3 months ago
-
Hello!
We are interested in using the HuBERT model trained / fine-tuned on the Fisher corpus as well as the HiFi-GAN Vocoder that generates audio directly from the units for academic research. Is …