HackerTrans
TopNewTrendsCommentsPastAskShowJobs

divamgupta

no profile record

Submissions

Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model

github.com
1,003 points·by divamgupta·11 mesi fa·361 comments

NamiGen: Free and Local Alternative to ElevenLabs

namigen.com
10 points·by divamgupta·anno scorso·2 comments

Stable Diffusion Implemented Using TensorFlow and Keras

twitter.com
3 points·by divamgupta·4 anni fa·3 comments

Diffusion Bee: Stable Diffusion GUI App for M1 Mac

github.com
727 points·by divamgupta·4 anni fa·190 comments

comments

divamgupta
·11 mesi fa·discuss
Thanks a lot for the detailed feedback. We are working on some models which do not use a phonemizer
divamgupta
·11 mesi fa·discuss
Lol
divamgupta
·11 mesi fa·discuss
Haha interesting pivot!
divamgupta
·11 mesi fa·discuss
The thing is that the new models keep coming every day. So it’s economically not feasible to make chips for a single model
divamgupta
·11 mesi fa·discuss
This is our goal too.
divamgupta
·11 mesi fa·discuss
It was not
divamgupta
·11 mesi fa·discuss
We are still training the model. We expect the quality to go up in the next release. This is just a preview release :)
divamgupta
·11 mesi fa·discuss
Thanks for running the benchmarks. Currently the models are not optimized yet. We will optimize loading etc when we release an SDK meant for production :)
divamgupta
·11 mesi fa·discuss
This is just an early checkpoint. We hope that the quality will improve in the future.
divamgupta
·11 mesi fa·discuss
Currently we don't have chunking enabled yet. We will add it soon. That will remove the length limitations.
divamgupta
·11 mesi fa·discuss
That is our vision too!
divamgupta
·11 mesi fa·discuss
We will try to get rid of dependencies.
divamgupta
·11 mesi fa·discuss
We are working to fix that. Thanks
divamgupta
·11 mesi fa·discuss
Hmm, we will look into it.
divamgupta
·11 mesi fa·discuss
Mostly model size, and input size. Some models which use attention are O(N^2)
divamgupta
·11 mesi fa·discuss
We have released just a preview of the model. We hope to get the model much better in the future releases.
divamgupta
·11 mesi fa·discuss
Yup it runs on the web browser. https://clowerweb.github.io/kitten-tts-web-demo/
divamgupta
·11 mesi fa·discuss
We will release an STT model as well.
divamgupta
·11 mesi fa·discuss
Thanks
divamgupta
·11 mesi fa·discuss
Thanks for posting about our project in HN! I am one of the creators of KittenTTS

Here is the link to our repo: https://github.com/KittenML/KittenTTS