Edresson Casanova
Edresson Casanova
do you intend to train a universal model?
This issue was solved with PR #1946 where we replaced the Pyworld with Librosa Pyin.
> Is there any diff between emotion and speaker managers? Maybe we should call them attribute_manager and use it for all. Yeah agreed, as we discussed, let's keep it this...
Nice catch. Indeed it is an issue. I will submit a PR to fix it.
> Thank you @Edresson > > Are you also planning to retrain the models and update the YourTTS paper at least on arxiv? innocent I think it is not worth...
@Tomiinek Thanks so much for finding the bug and reporting it. I talked with all authors and the final decision was added a Erratum on [YourTTS Github repository](https://github.com/Edresson/YourTTS#erratum) and on...
XTTS already can do streaming. You can find an example of how to use it [here](https://github.com/coqui-ai/xtts-streaming-server) . It consists of a server and it also has an example that shows...
Hi @gjin10969, Looks like the formatter only divided your WAV file into two files: ``` Found 2 files in /tmp/xtts_ft/dataset ``` It is not right, make sure that your audio...
Hi @treya-lin @maociao, I could not replicate this error on my side. How much RAM do you guys have available on the computer that you are trying to use XTTS?...
Hi @nicemanis, Thanks for flagging this. Feel free to send a PR fixing these comments. Given that you found the issue and it is really easy to fix I think...