Julian Weber comments

Results 34 comments of


                                            Julian Weber

Languages other than PT, FR, EN

Hi, yeah as soon our PR will be merged on https://github.com/coqui-ai/TTS. We'll provide recipes and we'll train a massively multilingual version of the model. One with phonemes, and one without...

train.py

It's a zero-shot voice cloning model, so you don't need to train on either target or driving speakers (but that helps).

add web demo

Great work! Thanks for doing that. Would you mind adding a language selector as well? (Like here for exemple https://huggingface.co/spaces/mbarnig/lb_de_fr_en_pt_COQUI_VITS_TTS)

AttributeError: 'KerasTensor' object has no attribute 'graph'

Thank you @yan12125, that worked for me!

[feature request] Warning when unexpected key is loaded but not present in class

I'll add that tonight

[feature request] Warning when unexpected key is loaded but not present in class

I added the description @erogol

[feature request] Warning when unexpected key is loaded but not present in class

> maybe not allowing a new attributes would be safer Agreed

[Bug] Error in training Capacitron

Training capacitron is hard since it's pretty unstable. Try using the latest recipe since it improved stability (at least for alignments), you can find it on the latest TTS version.

[Feature request] Tutorial should mention when to use Espeak (or Espeak-ng) and when to use Gruut phonemizer

Yeah, you can also finetune from gruut to espeak. By default you should use espeak.

train our own voice model

Hey, speaker adaptation is to add speakers to existing supported languages. If you want to add langages, you'll have to add it in languages_ids.json and manually add one embedding to...