helloitsme
renamed repository from ai-voice-cloning-him
to helloitsme/ai-voice-cloning
helloitsme created repository helloitsme/ai-voice-cloning
helloitsme opened issue mrq/ai-voice-cloning#365
Using TPUs in Google Colab?helloitsme commented on issue mrq/ai-voice-cloning#361
American imposter> I would increase the temperature as 0.2 is a bit low for TorToiSe. I imagine that's the case, because I remember the base model will erase any non-American accents. seconded... >=0.7 will be…
helloitsme commented on issue mrq/ai-voice-cloning#152
VALL-E Integration (and In Response To TorToiSe: a Quick Retrospective)> Trying to get proper transcriptions right now for this repo. > > I just made use of the openai-whisper package and with the "tiny" model. Do you think that's sufficient? I see you're using…
helloitsme commented on issue mrq/ai-voice-cloning#253
Results, Retrospectives, and RecommendationsHaving worked with this repo ALOT at this point, it is possible to have get reliable set-it-and-forget-it settings, provided there's post remastering that moreorless evens out variations between…
helloitsme commented on issue mrq/ai-voice-cloning#253
Results, Retrospectives, and Recommendations> Would love to know how far prompt engineering can go and even the effect punctuation has in the text such as : and other ways of expressing dialogue and context. Seems to be little out there. I…
helloitsme commented on issue mrq/ai-voice-cloning#314
How to provide Dynamic Prompt Setting Editing (switch between voices)> Would love to know how far prompt engineering can go and even the effect punctuation has in the text such as : and other ways of expressing dialogue and context. Seems to be little out there. I…
helloitsme commented on issue mrq/ai-voice-cloning#152
VALL-E Integration (and In Response To TorToiSe: a Quick Retrospective)Thanks, mrq, as always! Reading your writeups are always an interesting bit of my day. I don't have as many hobbyist experts around and it's nice to read something with that level of passion...…
helloitsme commented on issue mrq/ai-voice-cloning#152
VALL-E Integration (and In Response To TorToiSe: a Quick Retrospective)> > Have you messed with Mangio's RVC fork? > > I've actually thought about running it through an RVC to see how things are cleaned up. The output (finetuned or not) is *fine*, but both the…
helloitsme closed issue mrq/ai-voice-cloning#309
Tortoise->normalize->rvchelloitsme opened issue mrq/ai-voice-cloning#309
Tortoise->normalize->rvchelloitsme commented on issue mrq/ai-voice-cloning#152
VALL-E Integration (and In Response To TorToiSe: a Quick Retrospective)Have you messed with Mangio's RVC fork? https://github.com/Mangio621/Mangio-RVC-Fork I notice if I run output from here through a model trained on a similar dataset, it improves even more the…
helloitsme commented on issue mrq/ai-voice-cloning#253
Results, Retrospectives, and Recommendations> > A smart trick I ran into is running generated audio through RVC with its own Harvest trained model, helps smooth out the audio and make it more consistent > > Have you played around with…
helloitsme commented on issue mrq/ai-voice-cloning#253
Results, Retrospectives, and RecommendationsA smart trick I ran into is running generated audio through RVC with its own Harvest trained model, helps smooth out the audio and make it more consistent
helloitsme commented on issue mrq/ai-voice-cloning#183
generating voice clip is so much slower compared to using original Tortoise TTSWell, the basic idea still stands, train a great model on tortoise, and use that to generate a corpus for a model that is less accurate, but faster inference. The thought is that by capturing the…
helloitsme commented on issue mrq/ai-voice-cloning#253
Results, Retrospectives, and RecommendationsIdk, haven't edited the whisper.json
helloitsme commented on issue mrq/ai-voice-cloning#283
Large dataset finetuningHonestly, I believe large datasets are way overkill, as past some point, the data they provide is either unnecessary or introduces errors. All that the model is trying to do is understand various…