Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Modelgithub.com1,003 points·by divamgupta·il y a 11 mois·361 comments
NamiGen: Free and Local Alternative to ElevenLabsnamigen.com10 points·by divamgupta·l’année dernière·2 comments
Stable Diffusion Implemented Using TensorFlow and Kerastwitter.com3 points·by divamgupta·il y a 4 ans·3 comments
Diffusion Bee: Stable Diffusion GUI App for M1 Macgithub.com727 points·by divamgupta·il y a 4 ans·190 comments
divamgupta·il y a 11 mois·discussThanks a lot for the detailed feedback. We are working on some models which do not use a phonemizer
divamgupta·il y a 11 mois·discussThe thing is that the new models keep coming every day. So it’s economically not feasible to make chips for a single model
divamgupta·il y a 11 mois·discussWe are still training the model. We expect the quality to go up in the next release. This is just a preview release :)
divamgupta·il y a 11 mois·discussThanks 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·il y a 11 mois·discussThis is just an early checkpoint. We hope that the quality will improve in the future.
divamgupta·il y a 11 mois·discussCurrently we don't have chunking enabled yet. We will add it soon. That will remove the length limitations.
divamgupta·il y a 11 mois·discussMostly model size, and input size. Some models which use attention are O(N^2)
divamgupta·il y a 11 mois·discussWe have released just a preview of the model. We hope to get the model much better in the future releases.
divamgupta·il y a 11 mois·discussYup it runs on the web browser. https://clowerweb.github.io/kitten-tts-web-demo/
divamgupta·il y a 11 mois·discussThanks for posting about our project in HN! I am one of the creators of KittenTTSHere is the link to our repo: https://github.com/KittenML/KittenTTS