StyleTTS2

StyleTTS2 copied to clipboard

Getting random pauses

1

Not sure why but i've been getting a bunch of pauses especially when doing longer form generation -- i tried swapping out the text splitter but it doesn't seem to...

samyoed

add speed option to inference

1

Add a speed option to the infer function https://github.com/sidharthrajaram/StyleTTS2/blob/350b8889d75a52c2c695dafa7ba4682386be0b96/src/styletts2/tts.py#L186-L195 Have tested with dividing the predicted duration by a value https://github.com/sidharthrajaram/StyleTTS2/blob/350b8889d75a52c2c695dafa7ba4682386be0b96/src/styletts2/tts.py#L267-L267 Adding `speed=1` to the function and `/ speed` to the...

mrciolino

LJSpeech Model

4

Hi, Nice package! Would you mind adding the LJSpeech model? There's a separate LJSpeech model that is single-speaker. Currently, it looks like you're using the LibriTTS model to clone the...

fakerybakery

Some text inputs throw expanded size of the tensor

3

First of all thanks a lot for providing this package! I was doing some tests for large inputs and found that when trying to send a large string (i.e. len...

Cabeda

#repeat- more so feature request- Add a loading bar for when you give it a very large chunk of text At the moment I'm testing out how it performs when...

DrewThomasson

the text cleaner appears to strip valid numbers

1

Try to transcribe something with the phrase, "In the 1950's" and the numbers are stripped. It appears that numerals are being improperly stripped from text

thetrebor

How do I use inference() method for Hindi language?

1

I am trying to use TTS for devanagari script but I'm getting an error Traceback (most recent call last): File "C:\StyleTTS2\tts.py", line 7, in other_tts.inference("कैसे हो आप", output_wav_file="another_test.wav") File "C:\StyleTTS2\virt\lib\site-packages\styletts2\tts.py",...

tanishbajaj101

New realease 0.1.7

1

Hi! is it possible to create a new release with the updates done? thank you :)

ManueleNolli

Add Speed & Enable HuggingFace model loading

3

There are many issues opened on a missing speed parameter, like this one #6 and https://github.com/yl4579/StyleTTS/issues/3 The implementation is rather simple and many dubbing projects will benefit from this minor...

Nik-Kras

As for a high-severity [CVE in NLTK 3.8.1](https://github.com/advisories/ghsa-cgvx-9447-vcch) it is highly recommended to upgrade to at least 3.8.2 (also see [this discussion](https://github.com/nltk/nltk/issues/3266#issuecomment-2284001819)). This also introduces a breaking change as users...

ncryptedV1