Kreevoz

You can try mine, I'm running on W10 64bit too. I've zipped you the folder in question: https://www.dropbox.com/s/4qbzqa7ba06vnaa/monotonic_align.zip?dl=1

Ah I should probably have been more specific. Also, thankyou for taking the time to respond, jik! I was specifically curious about fine-tuning. The readme mentions that mel-spectrograms need to...

Yeah, I get the rough idea of what you're saying. I don't understand Tacotron2 well enough to do that. 😌 I'm a novice looking into this stuff as a hobby,...

The phonemization+tokenization code that ships with StyleTTS2 correctly processes the original LJSpeech dataset sentence at least. Into : `sˈɔːt tuː `` ɹˈæŋk ðə pɹˈɪzənz ðeɪ bˈɪlt ɐmˌʌŋ ðə mˈoʊst splˈɛndɪd...

Was the code for the tokenization changed during the development of StarTTS2? I think the implementation you settled with in the end is pretty good though.

This is just insane. Had to revert to the previous version and will refuse to update waterfox going forward until this is fixed. Guys you cannot just delete the previous...

There aren't even _that_ many models for a given language. The ones that have multispeaker capabilities would be using a multi-speaker dataset like vctk, which is listed when you query...

@V-Conet Billziss is right, this is an upstream issue and WinFSP is not at fault. I am running a similar VM setup, let me drop you and future googlers some...

I have the same problem - the suggested workaround of removing and reinstalling waterfox-bin doesn't work for me though. Same OS and other system parameters as the OP. You can...