Nikita Kononov
Nikita Kononov
> @NikitaKononov , hi! > > I trained the model 2 times. > > 1. I downloaded [this](https://www.kaggle.com/datasets/showmik50/vctk-dataset) dataset, lowered the frequency of wav files to 22050 Hz, then deleted...
In your samples I can clearly hear data-hunger typical for VITS or it can be a syndrome of poor data markup quality or both LR of course matters too
> About 5 min/epoch. > > dataset size: 10k batchsize: 20 gpu: A4000 model is the same as that in vctk_basse.json. > > Here is the log: 2023-01-25 19:52:04,390 paimon...
> At the interval, the GPU does not seem to be working. Maybe you have bottleneck in CPU / num_workers / disk speed / RAM speed
> Hi I have a n00b question. I am using the inference script provided with the pretrained model "pretrained_ljs.pth" and result has a noticeable noise and not close to the...
> Thanks a lot for the response. Is there an ideal example of text/ inference parameters that should produce results similar to the demo ? Can't suggest parameters values, coz...
But LJSpeech is veeeery boring voice. It's very sad that current SOTA models are tested with LJS... It has no emotions. Even tacotron sounds well with it
> https://github.com/NaruseMioShirakana 你这拿别人代码來先引流 证据:https://boards.4channel.org/g/thread/92107895/vsg-ai-voice-synthesis-general-29 养出一堆后再利用“牠”们来控評的“人”~在那删评也没用~凡“爬”过必留痕迹~ Мала Полк Азов Supporter, dO yoU Really tHINK THAT YoU caN gEt AWaY wiTH TheSe "μOP Codes"? https://web.archive.org/web/20230317071754/https://t.bilibili.com/773675325630447632 Write your thoughts in English please Your...
+1 RTX 4090 + Ryzen 5900X +64GB RAM Gpu utilization is
> recently, sagemaker have updated the default pytorch kernel to py3.10 with cuda 11.8; so now pyannote is not working properly there so what should we do