-
### 🐛 Describe the bug
from speechbrain.pretrained import Tacotron2
from speechbrain.pretrained import HIFIGAN
tacotron2 = Tacotron2.from_hparams(source="speechbrain/tts-tacotron2-ljspeech", savedi…
-
hello @shivammehta25
looks like the hifigan checkpoint download links are gone or have changed, do you have a .ckpt file for hifigan by any chance?
-
## Describe the bug
I'm trying to train GAN-based vocoders like HiFi-GAN, APNet, on the medium sized dataset (~ half of LibriTTS clean-100 + clean-300), however training fails with CUDA out of memory…
-
Hi,
Thank you for the very great work with great result in the demo page.
I have tried to follow all of the steps given in the README, however even after I use pretrained universal [HiFi GAN](https:…
-
I notice 16khz seems to be hard programmed into the code for the downsampling phase. I think supporting more modular sample rates for inference audio would make sense. With librosa the standard for ha…
-
Is this something that is created from the database? I tried following the steps, but this file seems to be missing. Any help is appreciated!
-
## 論文タイトル（原文まま）
VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
## 一言でいうと
単一段階のテキスト音声変換モデルであるVITS2は、対向学習とアーキテクチャ設計を用いて、音声の…
-
Hi,
My request would be to update the HiFi-GAN vocoder to newer versions, such as V2.
The current version of HiFi-GAN used by coqui is the V1.
That would improve the performance in inference…
-
Hello, i tried use another vocoder - HiFi Gan with your model.
But i faced with problem which get output with noise audio or silence.
I transopted the logmel output to a regular input for HiFiGan…
2Bye updated
8 months ago
-
The Universal HiFiGAN checkpoint is very good, we could possibly just move the weights from it over to a shell EV model.