{"id":15136439,"url":"https://github.com/chaoticbyte/audio-summarize","last_synced_at":"2025-10-23T11:31:24.149Z","repository":{"id":252992990,"uuid":"842132993","full_name":"ChaoticByte/audio-summarize","owner":"ChaoticByte","description":"An audio summarizer (faster-whisper and BART glued together)","archived":true,"fork":false,"pushed_at":"2024-08-16T18:19:50.000Z","size":18,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-30T18:05:39.744Z","etag":null,"topics":["ai","ai-summarizer","audio","bart","ctranslate2","faster-whisper","nlp","speech-to-text","summarization","whisper"],"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/ChaoticByte.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-13T18:29:06.000Z","updated_at":"2025-01-11T15:12:39.000Z","dependencies_parsed_at":"2024-08-13T22:04:33.581Z","dependency_job_id":null,"html_url":"https://github.com/ChaoticByte/audio-summarize","commit_stats":null,"previous_names":["chaoticbyte/audio-summarize"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChaoticByte%2Faudio-summarize","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChaoticByte%2Faudio-summarize/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChaoticByte%2Faudio-summarize/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChaoticByte%2Faudio-summarize/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChaoticByte","download_url":"https://codeload.github.com/ChaoticByte/audio-summarize/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":237821545,"owners_count":19371781,"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":["ai","ai-summarizer","audio","bart","ctranslate2","faster-whisper","nlp","speech-to-text","summarization","whisper"],"created_at":"2024-09-26T06:21:47.154Z","updated_at":"2025-10-23T11:31:23.839Z","avatar_url":"https://github.com/ChaoticByte.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# audio-summarize\n\nAn audio summarizer that glues together [faster-whisper](https://github.com/SYSTRAN/faster-whisper) and [BART](https://huggingface.co/facebook/bart-large-cnn).\n\n## Supported Languages\n\nOnly English summarization is supported.\n\n## Dependencies\n\n- Python 3 (tested: 3.12)\n\n## Setup\n\nCreate a virtual environment for python, activate it and install the required python packages:\n\n```bash\npython3 -m venv .venv\nsource .venv/bin/activate\npip3 install -r requirements.txt\n```\n\n## Run\n\n1. In your terminal, make shure you have your python venv activated\n2. Run audio-summarize.py\n\n### Usage\n\n```\n./audio-summarize.py -i filepath -o filepath [-m name]\n                   [--summin n] [--summax n] [--segmax n]\n\noptions:\n  -h, --help   show this help message and exit\n  --summin n   The minimum lenght of a segment summary [10] (min: 5)\n  --summax n   The maximum lenght of a segment summary [90] (min: 5)\n  --segmax n   The maximum number of tokens per segment [375] (5 - 500)\n  -m name      The name of the whisper model to be used [small.en]\n  -i filepath  The path to the media file\n  -o filepath  Where to save the output text to\n```\n\nExample:\n\n```bash\n./audio-summarize.py -i ./tmp/test.webm -o ./tmp/output.txt\n```\n\n## How does it work?\n\nTo summarize a media file, the program executes the following steps:\n\n1. Convert and transcribe the media file using [faster-whisper](https://github.com/SYSTRAN/faster-whisper), using [ffmpeg](https://www.ffmpeg.org/) and [ctranslate2](https://github.com/OpenNMT/CTranslate2/) under the hood\n2. Semantically split up the transcript into segments using [semantic-text-splitter](https://github.com/benbrandt/text-splitter) and the tokenizer for BART\n3. Summarize each segment using BART ([`facebook/bart-large-cnn`](https://huggingface.co/facebook/bart-large-cnn))\n4. Write the results to a text file\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchaoticbyte%2Faudio-summarize","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchaoticbyte%2Faudio-summarize","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchaoticbyte%2Faudio-summarize/lists"}