Welcome to the Pony Voice Preservation Project!youtu.be/730zGRwbQuEThe Pony Preservation Project is a collaborative effort by /mlp/ to build and curate pony datasets for as many applications in AI as possible.Technology has progressed such that a trained neural network can generate convincing voice clips, drawings and text for any person or character using existing audio recordings, artwork and fanfics as a reference. As you can surely imagine, AI pony voices, drawings and text have endless applications for pony content creation.AI is incredibly versatile, basically anything that can be boiled down to a simple dataset can be used for training to create more of it. AI-generated images, fanfics, wAIfu chatbots and even animation are possible, and are being worked on here.Any anon is free to join, and there are many active tasks that would suit any level of technical expertise. If you’re interested in helping out, take a look at the quick start guide linked below and ask in the thread for any further detail you need.EQG and G5 are not welcome.>Quick start guide:docs.google.com/document/d/1PDkSrKKiHzzpUTKzBldZeKngvjeBUjyTtGCOv2GWwa0/editIntroduction to the PPP, links to text-to-speech tools, and how (You) can help with active tasks.>The main Doc:docs.google.com/document/d/1y1pfS0LCrwbbvxdn3ZksH25BKaf0LaO13uYppxIQnac/editAn in-depth repository of tutorials, resources and archives.>Active tasks:Research into animation AIResearch into pony image generation>Latest developments:GDrive clone of Master File now available >>37159549SortAnon releases script to run TalkNet on Windows >>37299594TalkNet training script >>37374942GPT-J downloadable model >>37646318FiMmicroSoL model >>38027533Delta GPT-J notebook + tutorial >>38018428New FiMfic GPT model >>38308297 >>38347556 >>38301248FimFic dataset release >>38391839Offline GPT-PNY >>38821349FiMfic dataset >>38934474SD weights >>38959367SD low vram >>38959447Huggingface SD: >>38979677Colab SD >>38981735NSFW Pony Model >>39114433New DeltaVox >>39678806so-vits-svt 4.0 >>39683876so-vits-svt tutorial >>39692758Hay Say >>39920556Haysay on the web! >>40391443SFX seperator >>40786997 >>40790270Synthbot updates GDrive >>41019588Private "MareLoid" project >>40925332 >>40928583 >>40932952VoiceCraft >>40938470 >>40953388Fimfarch dataset >>410279715 years of PPP >>41029227Audio re-up >>41100938RVC Experiments >>41244976 >>41244980Ace Studio Demo >>41256049 >>41256783>The PoneAI drive, an archive for AI pony voice content:drive.google.com/drive/folders/1E21zJQWC5XVQWy2mt42bUiJ_XbqTJXCp>Clipper’s Master Files, the central location for MLP voice data:mega.nz/folder/jkwimSTa#_xk0VnR30C8Ljsy4RCGSigmega.nz/folder/gVYUEZrI#6dQHH3P2cFYWm3UkQveHxQdrive.google.com/drive/folders/1MuM9Nb_LwnVxInIPFNvzD_hv3zOZhpwx>Cool, where is the discord/forum/whatever unifying place for this project?You're looking at it.Last Thread:>>41284357
FAQs:If your question isn’t listed here, take a look in the quick start guide and main doc to see if it’s already answered there. Use the tabs on the left for easy navigation.Quick: docs.google.com/document/d/1PDkSrKKiHzzpUTKzBldZeKngvjeBUjyTtGCOv2GWwa0/editMain: docs.google.com/document/d/1y1pfS0LCrwbbvxdn3ZksH25BKaf0LaO13uYppxIQnac/edit>Where can I find the AI text-to-speech tools and how do I use them?A list of TTS tools: docs.google.com/document/d/1y1pfS0LCrwbbvxdn3ZksH25BKaf0LaO13uYppxIQnac/edit#heading=h.yuhl8zjiwmwqHow to get the best out of them: docs.google.com/document/d/1y1pfS0LCrwbbvxdn3ZksH25BKaf0LaO13uYppxIQnac/edit#heading=h.mnnpknmj1hcy>Where can I find content made with the voice AI?In the PoneAI drive: drive.google.com/drive/folders/1E21zJQWC5XVQWy2mt42bUiJ_XbqTJXCpAnd the PPP Mega Compilation: docs.google.com/spreadsheets/d/1T2TE3OBs681Vphfas7Jgi5rvugdH6wnXVtUVYiZyJF8/edit>I want to know more about the PPP, but I can’t be arsed to read the doc.See the live PPP panel shows presented on /mlp/con for a more condensed overview.2020 pony.tube/w/5fUkuT3245pL8ZoWXUnXJ42021 pony.tube/w/a5yfTV4Ynq7tRveZH7AA8f2022 pony.tube/w/mV3xgbdtrXqjoPAwEXZCw52023 pony.tube/w/fVZShksjBbu6uT51DtvWWz>How can I help with the PPP?Build datasets, train AIs, and use the AI to make more pony content. Take a look at the quick start guide for current active tasks, or start your own in the thread if you have an idea. There’s always more data to collect and more AIs to train.>Did you know that such and such voiced this other thing that could be used for voice data?It is best to keep to official audio only unless there is very little of it available. If you know of a good source of audio for characters with few (or just fewer) lines, please post it in the thread. 5.1 is generally required unless you have a source already clean of background noise. Preferably post a sample or link. The easier you make it, the more likely it will be done.>What about fan-imitations of official voices?No.>Will you guys be doing a [insert language here] version of the AI?Probably not, but you're welcome to. You can however get most of the way there by using phonetic transcriptions of other languages as input for the AI.>What about [insert OC here]'s voice?It is often quite difficult to find good quality audio data for OCs. If you happen to know any, post them in the thread and we’ll take a look.>I have an idea!Great. Post it in the thread and we'll discuss it.>Do you have a Code of Conduct?Of course: 15.ai/code>Is this project open source? Who is in charge of this?pony.tube/w/mqJyvdgrpbWgZduz2cs1CmPPP Redubs:pony.tube/w/p/aR2dpAFn5KhnqPYiRxFQ97Stream Premieres:pony.tube/w/6cKnjJEZSCi3gsvrbATXnCpony.tube/w/oNeBFMPiQKh93ePqTz1ns8
>>41354496Anchor.
How to free the ponies from the computer?
>>41353560>model_name_mapper.jsonI did not have to edit this.I still cannot reproduce this bug. Here is the procedure I followed:>Install UVR>Download SFX_separation_v2_epoch_338.th from https://huggingface.co/therealvul/demucs/tree/main and move to Ultimate Vocal Remover\models\Demucs_Models\v3_v4_repo>Create the config file sfx_sep2.yaml under Ultimate Vocal Remover\models\Demucs_Models\v3_v4_repo with the following contents:models: ['SFX_separation_v2_epoch_338']Working for both GPU and non-GPU inference.
https://files.catbox.moe/a17hdk.wavAlternatively:https://files.catbox.moe/y4cj97.wav
>multiple threads with less than dozen posts Uhoh, did the board got raided overnight?
>>41355641>>>/co/145128460
>>41355648RIght, /mlp/ isn't allowed to link to /co/. Anyway, the mods made posts on /co/ and /a/ saying they made a mistake. The /co/ thread is still up, so you can go over there to see it.
>>41354429
>>41355320There is a progress I guess. now Its throwing me this error.>https://pastebin.com/z0bgPV88KeyError: "'models'"Traceback Error: " File "UVR.py", line 6638, in process_start File "separate.py", line 834, in seperate File "demucs\pretrained.py", line 81, in get_model File "demucs\repo.py", line 148, in get_model File "demucs\repo.py", line 128, in get_modelI've tried one of their demucs model to see if maybe something is broken on my end however the light_extra 1v works just fine.
>>41355850This indicates that it cannot find the models: key in your yaml, are you sure it is written correctly?
https://files.catbox.moe/2nqbqh.mp3
>>41356774Im following the instructions 100%, so I have no idea what I could have done wrong here. Could you catbox send the yaml from your end, may e there is some weird bullshit encoding that is not being saved when im writing the file on my end?
>>41357135https://files.catbox.moe/cyp41d.yaml
>>41357278...it fucking works.https://files.catbox.moe/kmblb3.yamlThis is mine file, and for the life of me I can NOT see what is the difference between it and yours.
>>41357362There are two differences:1. Your file has a byte order mark2. Your file has one extra lineNone of these things should break parsing in a sane world but idk
>>41357408computers are silly I guess
>>https://www.udio.com/createactually pretty good at picking up pony slang like "everypony" and using the characters names
what happened to mareloid?
>>41359072
>>41354496Can I interest you in creating a tool for the purpose of color theory analysis?Step 1: collect colored quadrupedsStep 2: season sortingStep 3: ???Step 4: a model that can tell you how shit your OC is. With numbers.
>>41358533From what we last saw it remains private due to the poster's friend (the one making it) not thinking it was perfect enough to send out to the world. It sucks majorly though, was really looking forward to it.
>>41360063https://mlpvector.club/cg/ponyThere is a raw collection of colors here, you would need to come useful format for when scarping it, such as grabbing the main coat color, than create list for mane&tail and the iris.As for comparing it, and making some sensible way to process the composition of each colors, dunno, maybe there are some github project that could help with this.
>>41360063>>41360724How to rate the quality of a mare's color scheme
>>41360901Simply take poll-based rankings of the characters and pretend that those ranks are purely due to color-scheme. There are several ways to process the data from there based around color theory. Like how complimentary the colors are, or how close they are, are they all cool-tones, warm-tones, or a mix? All these qualities and more can be assigned to a mare's color scheme before you even begin to weigh-in the results of polls to decide the most pleasing traits.
>>41360724It's in json format here:https://drive.google.com/file/d/1kCEQO1jIHgMKd1zm25OQFiUfvf3WNGyM/view?usp=drive_link
Could someone explain to me, how do I install the same f0 pitch detection stuff that haysay has but into my offline rvc copy?I only have the j=harvest and pm.
>>41361661Shouldn't rvc have rmvpe by default
>>41361715dunno, mine doesn't but than again its from March this year so maybe the github did get an update after that?
>https://files.catbox.moe/qxa6vp.mp3Since we are lacking in pony ai song, here is a quick cover of "Sanity Loss- Maggie Noire and her Elder Orchestra" from this link https://www.youtube.com/watch?v=RWVnqCwCmi0 (the guy didnt stated if original song was ai made, but it sure feels like it, so dunno).I firstly wanted to do it with Trixie/Luna but for some reason they didnt really meshed well with the extracted vocal clips, however Twilight voice fit in like a glove.
What are we eating?
>>41362576Eating Ponk's flank would be counter productive.