-
Description:
I converted the decoder of a TTS model (with HiFi-GAN vocoder) from PyTorch to ONNX and then to an engine format. During inference, both input and output shapes are dynamic, changing wit…
-
Since hifi-gan is really old and outdated, i suggest you add something newer and more robust such as BIGvae gan. The results seem promising and can improve the overall performance of the model and pot…
-
We need to replace the current fishspeech with better TTS model.
WIP Shortlist of Possible candidates:
- Amphion (https://github.com/open-mmlab/Amphion)
-
현재 학부생 김나희 학생과 같은 조로 종합설계를 준비중에 있습니다. Speech Audio Synthesis 분야와 관련된 주제를 진행할 계획입니다.
이와 관련해서 GAN 기반의 여러 음성 합성 기술을 공부중에 있습니다.
- HiFi-GAN: https://arxiv.org/pdf/2010.05646v2
- MelGAN: https://arxiv.or…
-
Olá. No README.md há, na seção "NEW", um modelo chamado "GlowTTS model + HiFi-GAN-FT".
O link da demo no Google Colab não abre.
É esse o link: https://colab.research.google.com/drive/1sh96-f9J2BJcLm…
-
Hi
Thanks for this great project.
I trained a multi speaker Tacotron using [this repo](https://github.com/CorentinJ/Real-Time-Voice-Cloning) in new dataset and results was good. Then I test hifigan …
-
Hello,
I would like to ask if it's possible to train the HiFi-GAN model to upsample from 22,050 Hz directly to 48,000 Hz instead of the default 24,000 Hz.
I'm planning to make the following chan…
-
#### What is your question?
Where is the implementation of the hifi-gan adaptation discussed in "Speech resynthesis from discrete disentangled self-supervised representations" and "DIRECT SPEECH-…
-
## 論文タイトル（原文まま）
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
## 一言でいうと
HiFi-GANは、効率的かつ高忠実度な音声合成を実現するために設計された生成対向ネットワーク（GAN）であり、最新のモデルと比較して高い品質と高速な合成を…
-
Hi,
Does any know where the pretrained Hifi GAN vocoder that works at 16KHz is available.
OR
Can any one have config file (hyper parameters setting at 16K Hz) that gives the best possible quality …