Kaveen Kumar comments

Results 8 comments of


                                            Kaveen Kumar

Fixed ModuleNotFoundError: No module named 'numba.decorators'

thanks for correcting the numba version and ordering the requirements.txt. Approved!

xttsv2 model sometimes（almost 10%）produce extra noise.[Bug]

Most often occurs in FR language than others. You synthesize 10 samples of a "text" for a given "voice", 2-3 out of those 10 samples contain the "text" + "some...

[Bug] Fine tuned XTTS v2 produces strange sounds for short text

Same issue. Pre-trained XTTSv2 produces extra speech after the intended "text", 10-20% of the time

[Feature request] Changing the reading speed for xTTS v2

I have a similar requirement with tempo variation. Currently I use this script to achieve the same: """borrowed from - https://stackoverflow.com/a/43438143/12584995""" ``` import wave from pydub import AudioSegment def speed_change_pydub(wav,...

False positives when using dynamic graph models

Adding similar sounding words to the grammar list helps. For instance, you could add "cheek" and the next time someone says "cheek", there is a high chance that "cheek" gets...

[Bug] The voice-cloned speaker continues with garbage after to-be-spoken text was finished or mid-sentence

Anyone has a workaround to this? I tried finishing all my text with a period "." but that does not stop the synthesizer from ending. Often there are artifacts along...

[Bug] The voice-cloned speaker continues with garbage after to-be-spoken text was finished or mid-sentence

> > Anyone has a workaround to this? > > I tried finishing all my text with a period "." but that does not stop the synthesizer from ending. Often...

Feature setting for daily reset total amount of downloads

It'd make sense to have the feature extended to reset for every month. Since we all use monthly quota of our internet/broadband, this makes total sense.