{"id":20126547,"url":"https://github.com/thefloatingstring/agora","last_synced_at":"2026-06-05T18:31:57.555Z","repository":{"id":70750571,"uuid":"578044281","full_name":"TheFloatingString/AGORA","owner":"TheFloatingString","description":"Automated Generation and Omission Recurrent Architecture (AGORA). This model inputs speech (audio recording) and replaces hate speech and profanity with generated textual content. (Speech to text model.) McGill's submission to Project X, 2022-23.","archived":false,"fork":false,"pushed_at":"2024-04-02T13:45:39.000Z","size":587081,"stargazers_count":0,"open_issues_count":18,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-13T08:12:44.414Z","etag":null,"topics":["generative-model","hate-speech-detection","speech-to-text"],"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/TheFloatingString.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","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":"2022-12-14T05:48:08.000Z","updated_at":"2023-12-19T01:42:17.000Z","dependencies_parsed_at":"2024-02-19T17:40:26.426Z","dependency_job_id":"2343b7a1-dba2-44b5-9ea0-0d49f088899d","html_url":"https://github.com/TheFloatingString/AGORA","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheFloatingString%2FAGORA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheFloatingString%2FAGORA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheFloatingString%2FAGORA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TheFloatingString%2FAGORA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TheFloatingString","download_url":"https://codeload.github.com/TheFloatingString/AGORA/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241570921,"owners_count":19984002,"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":["generative-model","hate-speech-detection","speech-to-text"],"created_at":"2024-11-13T20:16:37.564Z","updated_at":"2026-06-05T18:31:57.548Z","avatar_url":"https://github.com/TheFloatingString.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AGORA - Automated Generation and Omission Recurrent Architecture\n\nGiven a speech input (audio recording), this model replaces harmful speech with generated textual content. (Speech to text model.)\n\n\n### Installation and Setup\n\nConfigure environment variables:\n\n```\nset OPENAI_API_KEY_AGORA=\u003cAPI_KEY\u003e\n```\n\nSetup\n```\ngit clone https://github.com/TheFloatingString/agora.git\ncd agora\npip install -r requirements.txt\n```\n\nIn a Python file:\n```python\nfrom src.agora import Agora\n\nagora_model = Agora()\nresponse = agora_model.transcribe_audio(\"filepath_to_speech_audio.wav\")\nprint(response[\"outputText\"])\n```\n\n### Quickstart examples\n\n```\npython -m quickstart.run_sample\n```\n\n### Analyze AGORA's ability to Recognize Offensive Content in the Jigsaw Dataset\n\nNote: move `train.csv` into `data/jigsaw-data` from the Jigsaw dataset on Kaggle (https://www.kaggle.com/competitions/jigsaw-toxic-comment-classification-challenge/data)\n\n```\npython -m src.run_jigsaw_data\npython -m src.analyze_results\n```\n\n### Filter and Paraphrase the Speech-to-Text Functionality for Offensive Content\n\nRun the folowing, while making sure to change the filename from `1` to `10` at each new run.\n\n**Warning: the audio files contain explicit content.**\n\n```\npython -m src.run_audio_files\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthefloatingstring%2Fagora","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthefloatingstring%2Fagora","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthefloatingstring%2Fagora/lists"}