-
Hi all. I have good news that I have succeeded to train [THCHS30](http://www.openslr.org/18) in Chinese mandarin. The code is open on my [repo](https://github.com/begeekmyfriend/tacotron) with just a …
-
Please check whether this paper is about 'Voice Conversion' or not.
## article info.
- title: **NAUTILUS: a Versatile Voice Cloning System**
- summary: We introduce a novel speech synthesis system, …
-
Hello, I find an interested paper(https://arxiv.org/pdf/2006.04558.pdf) called FastSpeech2. It is an advanced version of FastSpeech, which eliminates the teacher model and directly combines PWG trai…
-
### Common bugs:
ddp not working in conjunction with torch/nn/modules/conv.py
## 🐛 Bug
PL is cowardly refusing to serialize anything that inherits from class _ConvNd
This is probably due to th…
-
When I try ../../../utils/synth_wav.sh --vocoder_models ljspeech.wavenet.mol.v1 example.txt with other models listed in the readme I get the above error.
I know its something simple Im doing wrong …
-
would you help me to find which part of the code is about Fast inference by caching intermediate states in convolutions?
-
Hai,
Trained multi-speaker wavenet for cmu-arctic dataset but didn't get reconstructed wave file like which mentioned in "https://r9y9.github.io/wavenet_vocoder/". For LJSpeech with local condition…
-
Hi, thank you so much for this fantastic repo and I apologize if this is an ignorant question, but on my GTX 1070 Ti the pre-trained wavenet.mol.v1 models don't decode mels faster than real-time. I pr…
-
I believe there is some missing words in Section 3.2 of your paper.
>The results indicate that MelGAN is comparable to some of the best performing models to date
as a vocoder component of TTS pipe…
-
Hi, everyone.
Firstly, I'd like to thank you for your excellent Tacotron-2 code! @Rayhane-mamah
I'm a rookie in TTS, and I'm trying to run this Tacotron-2 model on my server. But I came up with a pr…