Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

Which TTS software should I use? [P] (alien.top)

submitted 1 year ago by buffering_humor@alien.top to c/machinelearning@academy.garden

8 comments fedilink hide all child comments

This post is to ask for help regarding a personal project of mine.

So as a heads up, I'm very new to Machine Learning. I mostly a engaged in development stuff. But recently I took on a project where I have to convert text to lip-synced video file.

I need to first generate a WAV file from text. For that, Im looking for a TTS software. I just want a somewhat human-like voice for my project so I am not looking for a very high-quality voice.

I tried to use Tortoise TTS but I failed during the installation process and I can't find a good enough tutorial I can follow. Also, it seems Tortoise and many other AI tools work with a NVIDIA GPU which I don't have (I got a system with AMD integrated graphics). So does anyone have a tutorial or suggestion how to install tortoise?

Or do you have any suggestion for any other TTS to use?

top 8 comments

sorted by: hot top controversial new old

[–] KingsmanVince@alien.top 1 points 1 year ago (2 children)

A quick Google search on "tortoise-tts amd gpu",

[–] buffering_humor@alien.top 1 points 1 year ago

I've already tried those. But PyTorch site says that ROCm doesn't work with Windows anymore.

[–] zokkmon@alien.top 1 points 1 year ago

Do u know any model which can train voice data ??

[–] m98789@alien.top 1 points 1 year ago (1 children)

ElevenLabs

[–] buffering_humor@alien.top 1 points 1 year ago (1 children)

Thanks. But I am looking for an open source alternative.

[–] mr_birrd@alien.top 1 points 1 year ago

You can use the VITS TTS model

[–] Slackerrrrr@alien.top 1 points 1 year ago

This should be fairly easy to get running: https://github.com/coqui-ai/TTS

Iirc the Judy voice is pretty decent

[–] radarsat1@alien.top 1 points 1 year ago

If you just need a basic voice and aren't hung up on it being an ML model then you can try espeak