Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Modelgithub.com1,003 ポイント·投稿者 divamgupta·11 か月前·361 コメント
divamgupta·11 か月前·議論Thanks a lot for the detailed feedback. We are working on some models which do not use a phonemizer
divamgupta·11 か月前·議論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 か月前·議論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 か月前·議論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 か月前·議論This is just an early checkpoint. We hope that the quality will improve in the future.
divamgupta·11 か月前·議論Currently we don't have chunking enabled yet. We will add it soon. That will remove the length limitations.
divamgupta·11 か月前·議論We have released just a preview of the model. We hope to get the model much better in the future releases.
divamgupta·11 か月前·議論Thanks 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