{"id":19302697,"url":"https://github.com/kiritoind/youtube_audio_transcripter","last_synced_at":"2025-06-28T07:33:47.404Z","repository":{"id":222833213,"uuid":"758500650","full_name":"kiritoInd/YouTube_Audio_Transcripter","owner":"kiritoInd","description":"Youtube Audio transcription with WhisperAi , The script downloads audio from a YouTube video and transcribes them into text.","archived":false,"fork":false,"pushed_at":"2024-02-19T07:17:07.000Z","size":20446,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-12T07:41:20.796Z","etag":null,"topics":["jupyter-notebook","machine-learning","speech-recognition","speech-to-text","whisper-ai"],"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/kiritoInd.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":"2024-02-16T13:09:20.000Z","updated_at":"2024-04-13T13:29:50.000Z","dependencies_parsed_at":"2024-11-09T23:35:30.004Z","dependency_job_id":null,"html_url":"https://github.com/kiritoInd/YouTube_Audio_Transcripter","commit_stats":null,"previous_names":["kiritoind/youtube_audio_transcripter"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/kiritoInd/YouTube_Audio_Transcripter","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kiritoInd%2FYouTube_Audio_Transcripter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kiritoInd%2FYouTube_Audio_Transcripter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kiritoInd%2FYouTube_Audio_Transcripter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kiritoInd%2FYouTube_Audio_Transcripter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kiritoInd","download_url":"https://codeload.github.com/kiritoInd/YouTube_Audio_Transcripter/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kiritoInd%2FYouTube_Audio_Transcripter/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262392588,"owners_count":23303938,"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":["jupyter-notebook","machine-learning","speech-recognition","speech-to-text","whisper-ai"],"created_at":"2024-11-09T23:23:28.304Z","updated_at":"2025-06-28T07:33:47.384Z","avatar_url":"https://github.com/kiritoInd.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# README: Transcribing Audio Segments with OpenAI's Whisper Model\n\n---\n\n## Steps\n\n`Clone the Repo`\n\n`run the Run.py`\n\n\u003cimg src=\"./images/st2.png\" width=\"300\" height=\"200\"\u003e\n\n`Input a csv file with youtube links in rows`\n\n![Step 2](./images/st1.png)\n\n`Generate the subtitles`\n\n`Download the csv file after completed`\n\n![Step 3](./images/st3.png)\n\n`Ouput`\n\n![Output](./images/ot.png)\n\n---\n\n## Introduction\n\nThis README provides an overview and instructions for using the provided Python script to transcribe audio segments using OpenAI's Whisper model. The script downloads audio segments from a YouTube video and transcribes them into text.\n\n---\n\n## Dependencies\n\nBefore running the script, ensure you have the following dependencies installed:\n\n- Python 3.x\n- PyTube (`pip install pytube`)\n- MoviePy (`pip install moviepy`)\n- Whisper (`pip install openai-whisper`)\n\n---\n\n## Usage\n\n1. **Clone the Repository:**\n\n   Clone the repository containing the Python script to your local machine.\n\n2. **Run the Script:**\n\n   Open a terminal or command prompt and navigate to the directory containing the Python script.\n\n   Run the script using the following command:\n\n\n3. **Follow the Instructions:**\n\n- The script will prompt you to enter the URL of the YouTube video you want to transcribe.\n- It will download the audio segments from the video and transcribe them using OpenAI's Whisper model.\n- The detected language and recognized text for each audio segment will be printed in the terminal.\n\n---\n\n## Understanding the Script\n\n- The script leverages the PyTube library to download audio segments from the specified YouTube video.\n- It utilizes the Whisper model provided by OpenAI to transcribe the audio segments.\n- Audio segments are processed using log-Mel spectrograms before being transcribed.\n- The script outputs the detected language and recognized text for each audio segment.\n\n---\n\n## Notes\n\n- Ensure you have an active internet connection to download the YouTube video and utilize the Whisper model.\n- The provided script assumes that the audio segments are saved as \"audio1.mp3\", \"audio2.mp3\", and so on in the current directory.\n- Make sure you have appropriate permissions to download and process the audio segments.\n\n---\n\n## Credits\n\n- OpenAI for providing the Whisper model.\n- PyTube and MoviePy developers for creating useful libraries for working with YouTube videos and audio processing in Python.\n\n---\n\n## Disclaimer\n\n- This script is provided as-is and may require adjustments based on your specific requirements and environment.\n- Use the script responsibly and ensure compliance with YouTube's terms of service and copyright policies.\n\n---\n\nFeel free to reach out for further assistance or clarification. Happy transcribing!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkiritoind%2Fyoutube_audio_transcripter","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkiritoind%2Fyoutube_audio_transcripter","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkiritoind%2Fyoutube_audio_transcripter/lists"}