{"id":31144105,"url":"https://github.com/liteobject/whisperlab","last_synced_at":"2025-10-04T21:46:35.251Z","repository":{"id":314837059,"uuid":"1056912947","full_name":"LiteObject/WhisperLab","owner":"LiteObject","description":"A Python application that captures real-time audio and transcribes it using OpenAI Whisper. The transcribed text is displayed on the console with intelligent audio buffering for optimal speech recognition.","archived":false,"fork":false,"pushed_at":"2025-09-15T03:55:42.000Z","size":13,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-15T05:42:42.243Z","etag":null,"topics":["ai","llm","openai","speech-to-text","whisper"],"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/LiteObject.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-15T02:54:56.000Z","updated_at":"2025-09-15T03:55:45.000Z","dependencies_parsed_at":"2025-09-16T19:16:26.493Z","dependency_job_id":null,"html_url":"https://github.com/LiteObject/WhisperLab","commit_stats":null,"previous_names":["liteobject/whisperlab"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/LiteObject/WhisperLab","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiteObject%2FWhisperLab","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiteObject%2FWhisperLab/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiteObject%2FWhisperLab/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiteObject%2FWhisperLab/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LiteObject","download_url":"https://codeload.github.com/LiteObject/WhisperLab/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiteObject%2FWhisperLab/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278380461,"owners_count":25977216,"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","status":"online","status_checked_at":"2025-10-04T02:00:05.491Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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","llm","openai","speech-to-text","whisper"],"created_at":"2025-09-18T14:12:20.631Z","updated_at":"2025-10-04T21:46:35.235Z","avatar_url":"https://github.com/LiteObject.png","language":"Python","readme":"# WhisperLab\n\nA Python application that captures real-time audio and transcribes it using OpenAI Whisper. The transcribed text is displayed on the console with intelligent audio buffering for optimal speech recognition.\n\n## Project Structure\n\n```\nWhisperLab/\n├── .git/\n├── .venv/\n├── src/\n│   ├── __init__.py\n│   ├── main.py\n│   ├── audio_capture.py\n│   ├── transcription.py\n│   ├── config.py\n│   └── test_microphone.py\n├── requirements.txt\n├── run.py\n├── .gitignore\n└── README.md\n```\n\n## Installation\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/LiteObject/WhisperLab.git\n   cd WhisperLab\n   ```\n\n2. Create a virtual environment (recommended):\n   ```bash\n   python -m venv .venv\n   # On Windows:\n   .venv\\Scripts\\activate\n   # On macOS/Linux:\n   source .venv/bin/activate\n   ```\n\n3. Install the required dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n## Usage\n\n### Quick Start\n\n**Option 1: Using the runner script (Recommended)**\n```bash\npython run.py\n```\n\n**Option 2: Running from src directory**\n```bash\ncd src\npython main.py\n```\n\n### How It Works\n\nThe application uses intelligent audio buffering for better transcription:\n\n1. **Loads the Whisper model** (this may take a moment on first run)\n2. **Starts capturing audio** from your default microphone\n3. **Buffers audio for 3 seconds** to ensure quality transcription\n4. **Transcribes every 2 seconds** when sufficient audio is detected\n5. **Displays transcribed text** with clear indicators\n6. **Press Ctrl+C** to stop the application\n\n### Expected Output\n\nWhen working correctly, you'll see output like:\n```bash\nLoading Whisper model: base\nWhisper model 'base' loaded successfully\nStarting WhisperLab...\nPress Ctrl+C to stop\nStarting audio recording...\nRecording started at 16000 Hz, 1 channel(s)\nTranscription thread started...\n🎤 Transcribing 3.0s of audio (level: 0.0456)...\n✅ Transcribed #1: Hello, this is a test of the whisper transcription system.\n🎤 Transcribing 3.0s of audio (level: 0.0523)...\n✅ Transcribed #2: How are you doing today?\n```\n\n### Tips for Best Results\n\n- **Speak clearly** for 3-5 seconds at a time\n- **Wait 2-3 seconds** between phrases for processing\n- **Ensure good microphone placement** and volume\n- **Minimize background noise** for better accuracy\n\n## Startup Microphone Check\n\nWhisperLab automatically performs a quick microphone test when starting up:\n\n```bash\npython run.py\n```\n\nOutput:\n```\n🔍 Checking microphone availability...\n🚀 Quick Microphone Test (3 seconds)\n✅ Microphone working!\n✅ Microphone check passed!\n\nStarting WhisperLab...\n```\n\n### Configuring Microphone Check\n\nYou can control the startup microphone check behavior:\n\n**Environment Variables:**\n- `WHISPERLAB_MIC_CHECK_ENABLED=false` - Disable startup microphone check\n- `WHISPERLAB_MIC_CHECK_EXIT_ON_FAIL=true` - Exit automatically if microphone fails\n\n**Example:**\n```bash\n# Skip microphone check\nset WHISPERLAB_MIC_CHECK_ENABLED=false\npython run.py\n\n# Exit automatically if microphone doesn't work\nset WHISPERLAB_MIC_CHECK_EXIT_ON_FAIL=true\npython run.py\n```\n\n## Dependencies\n\nThis project requires the following Python packages:\n- `openai-whisper` - OpenAI's Whisper model for speech recognition\n- `sounddevice` - Cross-platform audio I/O library\n- `soundfile` - Audio file I/O\n- `numpy` - Numerical computing library\n- `torch` - PyTorch deep learning framework\n- `librosa` - Audio analysis library\n\nSee `requirements.txt` for the complete list of dependencies.\n\n## Features\n\n- **Real-time audio capture** with intelligent buffering\n- **Speech-to-text transcription** using OpenAI Whisper\n- **Smart audio processing** with 3-second buffers for better accuracy\n- **Console output** with clear status indicators\n- **Multithreaded architecture** for smooth audio processing\n- **Built-in microphone testing** tool for troubleshooting\n\n## Troubleshooting\n\n### Test Your Microphone\nIf you're not seeing transcriptions, first test your microphone:\n```bash\ncd src\npython test_microphone.py\n```\n\nThis will:\n- Show available audio devices\n- Record 5 seconds of audio\n- Display audio levels and detection status\n- Help diagnose microphone issues\n\n## Requirements\n\n- Python 3.7 or higher\n- Microphone access\n- Compatible audio drivers\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fliteobject%2Fwhisperlab","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fliteobject%2Fwhisperlab","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fliteobject%2Fwhisperlab/lists"}