{"id":22600976,"url":"https://github.com/vandercat/ponyaidubtool","last_synced_at":"2025-06-13T17:09:03.337Z","repository":{"id":175297184,"uuid":"653678346","full_name":"VanderCat/ponyAiDubTool","owner":"VanderCat","description":"Ai ReDubbing tool","archived":false,"fork":false,"pushed_at":"2023-06-15T09:55:52.000Z","size":4,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-28T20:23:58.648Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/VanderCat.png","metadata":{"files":{"readme":"README.MD","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-06-14T14:06:32.000Z","updated_at":"2023-06-14T14:26:59.000Z","dependencies_parsed_at":null,"dependency_job_id":"ac661d38-8035-4b66-a3ab-7c63ac177a02","html_url":"https://github.com/VanderCat/ponyAiDubTool","commit_stats":null,"previous_names":["vandercat/ponyaidubtool"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/VanderCat/ponyAiDubTool","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VanderCat%2FponyAiDubTool","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VanderCat%2FponyAiDubTool/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VanderCat%2FponyAiDubTool/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VanderCat%2FponyAiDubTool/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/VanderCat","download_url":"https://codeload.github.com/VanderCat/ponyAiDubTool/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/VanderCat%2FponyAiDubTool/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259686190,"owners_count":22896058,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-12-08T12:13:12.922Z","updated_at":"2025-06-13T17:09:03.318Z","avatar_url":"https://github.com/VanderCat.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Pony AI Dub Tool\r\nbased and depends on so-vits-svc-fork\r\n\r\nmade primarily to make an ai redubbing of russian MLP localization (make russian actors sound like original counterparts)\r\n\r\n## installation\r\n```\r\nconda create -n so-vits-svc-fork python=3.10 pip\r\nconda activate so-vits-svc-fork\r\npython -m pip install -U pip setuptools wheel\r\npip install -U torch torchaudio --index-url https://download.pytorch.org/whl/cu118\r\npip install -U so-vits-svc-fork pydub\r\n```\r\nor you can use exsisting so-vits-svc-fork installation environment and only install pydub\r\n```\r\npip install pydub\r\n```\r\n\r\n## Usage\r\n1. Get a clean voice track to map characters at.\r\n   You can use Ultimate Vocal Remover for that (great tool btw)\r\n2. Load it in Audacity. Start selecting voicelines and mark them \r\n   by pressing \u003ckbd\u003eCtrl\u003c/kbd\u003e+\u003ckbd\u003eB\u003c/kbd\u003e and naming them whatever\r\n   you want (labels can overlap)\r\n\r\n   e.g. Celestia's line labeled as `Sunbutt`\r\n\r\n   ![Audacity](https://files.catbox.moe/7cevcz.png)\r\n3. When you are done export labels as `Files` \u003e `Export` \u003e `Export Labels`\r\n4. make a copy of ponyExample.json and start modifying however you want\r\n   \r\n   `\"settingsDefault\"` - will be applied to each character model defenition in `\"characterModels\"` list\r\n\r\n   if your model has a custom checkpoints name autodetect will fail. to avoid this you will need to disable it using `\"autodetectModel\":false` and providing paths to model, config and cluster (if it exists)  \r\n   e.g.\r\n   ```json\r\n    \"characterModels\": {\r\n        \"Moonbutt\": {\r\n            \"autodetectModel\": false,\r\n            \"model\": \"D://AI//Models//Luna.pth\",\r\n            \"config\": \"D://AI/Models//Luna.json\",\r\n        }\r\n    }\r\n    ```\r\n5. Activate the environment and run\r\n   ```\r\n   python ponyairedb.py yourjsonfile.json\r\n   ```\r\n   wait for magic to happen\r\n6. you will get a separate syncronised voice tracks for each character that you will need to combine yourself. (if it is not obvious you can add effects like reverb and etc.)\r\n\r\n## Note:\r\nif there is no character in character map or there is no characterModel for character the audio track will not render. \r\n\r\nIf you do not want to render a track (e.g. for a testing purpouse) you can add a `\"skip\":\"true\"` to `\"characterModels\"`. To solo 1 track you can flip `\"skip\"` in the default settings and set `\"skip\"` to false in `\"characterModels\"`","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvandercat%2Fponyaidubtool","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvandercat%2Fponyaidubtool","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvandercat%2Fponyaidubtool/lists"}