{"id":13793910,"url":"https://github.com/quickvc/QuickVC-VoiceConversion","last_synced_at":"2025-05-12T20:31:23.483Z","repository":{"id":82797666,"uuid":"601493326","full_name":"quickvc/QuickVC-VoiceConversion","owner":"quickvc","description":"QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion","archived":false,"fork":false,"pushed_at":"2023-07-13T07:43:54.000Z","size":9673,"stargazers_count":227,"open_issues_count":8,"forks_count":26,"subscribers_count":21,"default_branch":"main","last_synced_at":"2024-11-18T08:55:49.561Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/quickvc.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-02-14T07:20:29.000Z","updated_at":"2024-11-13T02:53:45.000Z","dependencies_parsed_at":"2024-01-07T05:58:30.508Z","dependency_job_id":null,"html_url":"https://github.com/quickvc/QuickVC-VoiceConversion","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/quickvc%2FQuickVC-VoiceConversion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/quickvc%2FQuickVC-VoiceConversion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/quickvc%2FQuickVC-VoiceConversion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/quickvc%2FQuickVC-VoiceConversion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/quickvc","download_url":"https://codeload.github.com/quickvc/QuickVC-VoiceConversion/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253816734,"owners_count":21968875,"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":"2024-08-03T23:00:33.102Z","updated_at":"2025-05-12T20:31:18.456Z","avatar_url":"https://github.com/quickvc.png","language":"Python","readme":"# QuickVC\nThis repository contains the open source code, audio samples and pretrained models of my paper: QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion\n## [Demo Page](https://quickvc.github.io/quickvc-demo)\n\u003cimg src=\"qvcfinalwhite.png\" width=\"100%\"\u003e\n\n## [Pretrained Model](https://drive.google.com/drive/folders/1DF6RgIHHkn2aoyyUMt4_hPitKSc2YR9d?usp=share_link)\nPut pretrained model into logs/quickvc\n\n## Inference with pretrained model\n```python\npython convert.py\n```\nYou can change convert.txt to select the target and source\n## Preprocess\n1. Hubert-Soft\n```python\ncd dataset\npython encode.py soft dataset/VCTK-16K dataset/VCTK-16K\n```\n2. Spectrogram resize data augumentation, please refer to [FreeVC](https://github.com/OlaWod/FreeVC).\n\n## Train\n\n```python\npython train.py\n```\n\nIf you want to change the config and model name, change:\n```python\nparser.add_argument('-c', '--config', type=str, default=\"./configs/quickvc.json\",help='JSON file for configuration')\nparser.add_argument('-m', '--model', type=str,default=\"quickvc\",help='Model name')\n```                   \nin utils.py\n\nIn order to use the sr during training, change [this part](https://github.com/quickvc/QuickVC-VoiceConversion/blob/277118de9c81d1689e16be8a43408eda4223553d/data_utils_new_new.py#L70) to\n```python\ni = random.randint(68,92)\nc_filename = filename.replace(\".wav\", f\"_{i}.npy\")\n```    \n## References\nIf you have any question about the decoder, refer to [MS-ISTFT-VITS](https://github.com/MasayaKawamura/MB-iSTFT-VITS).\n\nIf you have any question about the Hubert-soft, refer to [Soft-VC](https://github.com/bshall/hubert).\n\nIf you have any question about the data augumentation, refer to [FreeVC](https://github.com/OlaWod/FreeVC).\n## If you meet any problem, welcome to contact with me.\n","funding_links":[],"categories":["Modified"],"sub_categories":["iSTFT (inverse short-time Fourier transform)"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fquickvc%2FQuickVC-VoiceConversion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fquickvc%2FQuickVC-VoiceConversion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fquickvc%2FQuickVC-VoiceConversion/lists"}