{"id":18228122,"url":"https://github.com/tcsenpai/youlama","last_synced_at":"2025-07-28T21:32:11.273Z","repository":{"id":260912675,"uuid":"868044583","full_name":"tcsenpai/youlama","owner":"tcsenpai","description":"YouTube Summarizer is a Streamlit-based web application that allows users to generate summaries of YouTube videos using AI-powered language models.","archived":false,"fork":false,"pushed_at":"2024-11-20T21:23:56.000Z","size":556,"stargazers_count":27,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-12-03T09:05:01.934Z","etag":null,"topics":["ai","llama","local","ollama","privacy","summarization","youtube"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"wtfpl","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tcsenpai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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":"2024-10-05T10:30:26.000Z","updated_at":"2024-12-02T06:49:23.000Z","dependencies_parsed_at":"2024-11-22T13:02:54.414Z","dependency_job_id":null,"html_url":"https://github.com/tcsenpai/youlama","commit_stats":{"total_commits":6,"total_committers":2,"mean_commits":3.0,"dds":"0.16666666666666663","last_synced_commit":"d915ac1b6143228f91d24fb1a2e3a7e1607af7ef"},"previous_names":["tcsenpai/youlama"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tcsenpai%2Fyoulama","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tcsenpai%2Fyoulama/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tcsenpai%2Fyoulama/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tcsenpai%2Fyoulama/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tcsenpai","download_url":"https://codeload.github.com/tcsenpai/youlama/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":227957843,"owners_count":17847290,"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","llama","local","ollama","privacy","summarization","youtube"],"created_at":"2024-11-04T07:03:58.589Z","updated_at":"2025-07-28T21:32:11.230Z","avatar_url":"https://github.com/tcsenpai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# YouLama\n\nA powerful web application for transcribing and summarizing YouTube videos and local media files using faster-whisper and Ollama.\n\n## Features\n\n- 🎥 YouTube video transcription with subtitle extraction\n- 🎙️ Local audio/video file transcription\n- 🤖 Automatic language detection\n- 📝 Multiple Whisper model options\n- 📚 AI-powered text summarization using Ollama\n- 🎨 Modern web interface with Gradio\n- 🐳 Docker support with CUDA\n- ⚙️ Configurable settings via config.ini\n\n## Requirements\n\n- Docker and Docker Compose\n- NVIDIA GPU with CUDA support\n- NVIDIA Container Toolkit\n- Ollama installed locally (optional, for summarization)\n\n## Installation\n\n1. Clone the repository:\n```bash\ngit clone \u003crepository-url\u003e\ncd youlama\n```\n\n2. Install NVIDIA Container Toolkit (if not already installed):\n```bash\n# Add NVIDIA package repositories\ndistribution=$(. /etc/os-release;echo $ID$VERSION_ID)\ncurl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -\ncurl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list\n\n# Install nvidia-docker2 package\nsudo apt-get update\nsudo apt-get install -y nvidia-docker2\n\n# Restart the Docker daemon\nsudo systemctl restart docker\n```\n\n3. Install Ollama locally (optional, for summarization):\n```bash\ncurl https://ollama.ai/install.sh | sh\n```\n\n4. Copy the example configuration file:\n```bash\ncp .env.example .env\n```\n\n5. Edit the configuration files:\n- `.env`: Set your environment variables\n- `config.ini`: Configure Whisper, Ollama, and application settings\n\n## Running the Application\n\n1. Start Ollama locally (if you want to use summarization):\n```bash\nollama serve\n```\n\n2. Build and start the YouLama container:\n```bash\ndocker-compose up --build\n```\n\n3. Open your web browser and navigate to:\n```\nhttp://localhost:7860\n```\n\n## Configuration\n\n### Environment Variables (.env)\n\n```ini\n# Server configuration\nSERVER_NAME=0.0.0.0\nSERVER_PORT=7860\nSHARE=true\n```\n\n### Application Settings (config.ini)\n\n```ini\n[whisper]\ndefault_model = base\ndevice = cuda\ncompute_type = float16\nbeam_size = 5\nvad_filter = true\n\n[app]\nmax_duration = 3600\nserver_name = 0.0.0.0\nserver_port = 7860\nshare = true\n\n[models]\navailable_models = tiny,base,small,medium,large-v1,large-v2,large-v3\n\n[languages]\navailable_languages = en,es,fr,de,it,pt,nl,ja,ko,zh\n\n[ollama]\nenabled = false\nurl = http://host.docker.internal:11434\ndefault_model = mistral\nsummarize_prompt = Please provide a comprehensive yet concise summary of the following text. Focus on the main points, key arguments, and important details while maintaining accuracy and completeness. Here's the text to summarize: \n```\n\n## Features in Detail\n\n### YouTube Video Processing\n- Supports youtube.com, youtu.be, and invidious URLs\n- Automatically extracts subtitles if available\n- Falls back to transcription if no subtitles found\n- Optional AI-powered summarization with Ollama\n\n### Local File Transcription\n- Supports various audio and video formats\n- Automatic language detection\n- Multiple Whisper model options\n- Optional AI-powered summarization with Ollama\n\n### AI Summarization\n- Uses locally running Ollama for text summarization\n- Configurable model selection\n- Customizable prompt\n- Available for both local files and YouTube videos\n\n## Tips\n\n- For better accuracy, use larger models (medium, large)\n- Processing time increases with model size\n- GPU is recommended for faster processing\n- Maximum audio duration is configurable (default: 60 minutes)\n- YouTube videos will first try to use available subtitles\n- If no subtitles are available, the video will be transcribed\n- Ollama summarization is optional and requires Ollama to be running locally\n- The application runs in a Docker container with CUDA support\n- Models are downloaded and cached in the `models` directory\n- The container connects to the local Ollama instance using host.docker.internal\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details. ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftcsenpai%2Fyoulama","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftcsenpai%2Fyoulama","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftcsenpai%2Fyoulama/lists"}