Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Modelgithub.com1,003 points·by divamgupta·11 tháng trước·361 comments
NamiGen: Free and Local Alternative to ElevenLabsnamigen.com10 points·by divamgupta·năm ngoái·2 comments
Stable Diffusion Implemented Using TensorFlow and Kerastwitter.com3 points·by divamgupta·4 năm trước·3 comments
Diffusion Bee: Stable Diffusion GUI App for M1 Macgithub.com727 points·by divamgupta·4 năm trước·190 comments
divamgupta·11 tháng trước·discussThanks a lot for the detailed feedback. We are working on some models which do not use a phonemizer
divamgupta·11 tháng trước·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·11 tháng trước·discussWe are still training the model. We expect the quality to go up in the next release. This is just a preview release :)
divamgupta·11 tháng trước·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·11 tháng trước·discussThis is just an early checkpoint. We hope that the quality will improve in the future.
divamgupta·11 tháng trước·discussCurrently we don't have chunking enabled yet. We will add it soon. That will remove the length limitations.
divamgupta·11 tháng trước·discussMostly model size, and input size. Some models which use attention are O(N^2)
divamgupta·11 tháng trước·discussWe have released just a preview of the model. We hope to get the model much better in the future releases.
divamgupta·11 tháng trước·discussYup it runs on the web browser. https://clowerweb.github.io/kitten-tts-web-demo/
divamgupta·11 tháng trước·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