Tim von Känel
Tim von Känel
You may need to install poetry https://python-poetry.org/docs/ but as I said, it's a work in progress and you will run into other bugs.
@DrAnime-byte I am currently working on removing docker as a dependency, so if you come back in a few weeks the issue should be resolved.
I wrote you an email :)
If you want to use your model with the pretrained HiFiGAN as Vocoder you need to mimic its short-time fourier transform window and hop length. The window length for pretrained...
No, you dont need to train a new hifigan, the output of hifigan will be 22050 hz even though you trained fastspeech on 16khz mel spectrograms
Thanks for opening the issue! Pre-training the model will take me roughly one more week. Afterward, I will refactor the code, and get the project into a usable state, then...
I fine-tuned the model on the voices of Twilight Sparkle (~6000 samples, My Little Pony) and Demoman (~500 samples, Team Fortress 2) now. There is definitely still a lot of...
I also noticed the multilingual G2P stuff and unusual phone set (phone set from [Montreal Forced Aligner](https://montreal-forced-aligner.readthedocs.io/en/latest/)) will probably make it a pain to implement this into coqui. It's probably...
Just noticed coqui already has support for multiple languages, that is nice. It doesn't really matter which G2P model we use, we just need a way to extract the phoneme...
@snufas Hey thanks! I work full-time in text-to-speech now and developing this repository is way out of scope at the moment, unfortunately. Maybe one day I will update and finish...