{"id":13656154,"url":"https://github.com/TheTempAccount/Co-Speech-Motion-Generation","last_synced_at":"2025-04-23T17:31:24.026Z","repository":{"id":45394214,"uuid":"418147751","full_name":"TheTempAccount/Co-Speech-Motion-Generation","owner":"TheTempAccount","description":"Freeform Body Motion Generation from Speech","archived":false,"fork":false,"pushed_at":"2022-11-12T03:56:58.000Z","size":86361,"stargazers_count":197,"open_issues_count":22,"forks_count":25,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-11-10T08:37:25.308Z","etag":null,"topics":["co-speech-gesture","generation-algorithms","gesture-controller","talking-head"],"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/TheTempAccount.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}},"created_at":"2021-10-17T13:55:13.000Z","updated_at":"2024-10-18T09:06:14.000Z","dependencies_parsed_at":"2023-01-22T00:19:33.945Z","dependency_job_id":null,"html_url":"https://github.com/TheTempAccount/Co-Speech-Motion-Generation","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/TheTempAccount%2FCo-Speech-Motion-Generation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheTempAccount%2FCo-Speech-Motion-Generation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheTempAccount%2FCo-Speech-Motion-Generation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheTempAccount%2FCo-Speech-Motion-Generation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TheTempAccount","download_url":"https://codeload.github.com/TheTempAccount/Co-Speech-Motion-Generation/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250480425,"owners_count":21437543,"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":["co-speech-gesture","generation-algorithms","gesture-controller","talking-head"],"created_at":"2024-08-02T04:00:52.170Z","updated_at":"2025-04-23T17:31:19.459Z","avatar_url":"https://github.com/TheTempAccount.png","language":"Python","funding_links":[],"categories":["Papers","GitHub projects"],"sub_categories":["Audio-Driven motion generation"],"readme":"# Freeform Co-Speech Gesture Generation\n\nThe repo for work \"Free-form Co-Speech Gesture Generation\"\n\n- source code \n- data preparation (partially)\n\n### Video Demo\n[![](https://res.cloudinary.com/marcomontalbano/image/upload/v1639640143/video_to_markdown/images/youtube--Wb5VYqKX_x0-c05b58ac6eb4c4700831b2b3070cd403.jpg)](https://youtu.be/Wb5VYqKX_x0 \"\")\n\n### Data \u0026 Pretrained model\nAvaliable through \n- [Google Drive](https://drive.google.com/drive/folders/1v8_4agLNM2jmRuSKnflkdbEcKWZkdtka?usp=sharing)\n\n\u003c!-- - [Baidu Yun](https://pan.baidu.com/s/18aeNlFuUNHbavlJFeSMn-Q) 提取码: 1vji --\u003e\n\nUnzip everything in *pose_dataset*, then change the *Data.data_root* in src/config/*.json. You should be seeing directory structure like this:\n\n    pose_dataset\n    |-videos\n    |   |-Speaker_A\n    |   |-Speaker_B\n    |   |-...\n    |   |-test_audios\n    |-ckpt\n\nThe rest of the data will be updated after I finish checking the annotations.\n\n### Inference\nGenerated gestures for an example audio clip:\n\n    bash demo.sh ../sample_audio/clip000040_ozfGHONpdTA.wav ../sample_audio/clip000040_ozfGHONpdTA.TextGrid\n\nVisualise the generated motions:\n\n    bash visualse.sh\n\nGenerate gestures for a speaker in test_audios:\n\n    cd src\n    bash infer.sh  \\\n            pose_dataset/ckpt/ckpt-99.pth \\\n            pose_dataset/ckpt/freeMo.json \\\n            \u003cpost_fix\u003e \\\n            \u003cspeaker_name\u003e\n\nThe results will be saved as \"pose_dataset/videos/test_audios/\u003cspeaker_name\u003e/*_\u003cpost_fix\u003e.json\", including the json file of 64 randomly generated gesture sequences for every audio. \n\nTo visualise the results, run\n\n    bash visualise/visualise_all.sh \u003cspeaker_name\u003e \u003cpost_fix\u003e\n\nRemember to change the file path in all files.\n\n### Training\n    \n    bash train.sh\n\nFor any problem, please let us know.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTheTempAccount%2FCo-Speech-Motion-Generation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTheTempAccount%2FCo-Speech-Motion-Generation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTheTempAccount%2FCo-Speech-Motion-Generation/lists"}