spb/tools-spboucher-ai

1{2  "slug": "whisper",3  "name": "Whisper",4  "aliases": ["openai-whisper", "OpenAI Whisper"],5  "vendor": { "name": "OpenAI", "slug": "openai", "website": "https://developers.openai.com/api/docs" },6  "homepage_url": "https://github.com/openai/whisper",7  "docs_url": "https://github.com/openai/whisper",8  "repo_url": "https://github.com/openai/whisper",9  "license_url": "https://github.com/openai/whisper/blob/main/LICENSE",10  "product_type": "model",11  "product_status": "maintenance",12  "summary": "OpenAI's open-source multilingual speech recognition model family with MIT-licensed code and weights, a Python package and CLI for transcription, translation and language identification",13  "description": "Whisper is a general-purpose speech recognition model released by OpenAI in 2022 with code and weights under the MIT license. A single Transformer sequence-to-sequence model trained on a large, diverse audio corpus performs multilingual transcription, translation into English and language identification. Six sizes are published, from tiny to large, plus turbo, an optimized variant of large-v3 that trades a little accuracy for speed and is not trained for translation; English-only variants exist for the smaller sizes. The `openai-whisper` Python package exposes `load_model` and `transcribe`, and a `whisper` CLI handles files directly; dependencies are PyTorch, tiktoken and ffmpeg.\n\nWhisper is the foundation of a large downstream ecosystem: faster-whisper and whisper.cpp reimplement inference for CPUs and small devices, mlx-whisper ports it to Apple Silicon, and OpenAI's hosted transcription API offers the same capability without local setup. The original repository changes infrequently and serves mainly as a reference, so projects needing speed or long-form robustness usually pick one of the derivatives. Accuracy varies substantially by language and audio quality, timestamps are approximate, and speaker diarization is not included.",14  "capabilities": ["Multilingual transcription and translation to English", "Automatic language identification", "Six model sizes plus turbo for faster inference", "Python API and CLI", "MIT-licensed weights usable in derivative runtimes"],15  "workflows": ["Transcribe lecture recordings offline with the CLI", "Pick a model size to balance accuracy and speed on available hardware", "Swap to mlx-whisper or faster-whisper for production throughput"],16  "advantages": ["Permissive MIT license for code and weights", "Strong multilingual coverage", "Large ecosystem of optimized reimplementations"],17  "limitations": ["Reference implementation is slow compared with derivatives", "No speaker diarization and approximate timestamps", "Accuracy drops on low-resource languages and noisy audio"],18  "prerequisites": ["Python with PyTorch and ffmpeg", "GPU recommended for larger models"],19  "audiences": ["Researchers and students transcribing interviews or lectures", "Developers embedding speech recognition offline"],20  "alternatives": ["mlx-whisper", "elevenlabs", "openai-platform"],21  "categories": [{ "slug": "speech-vision-multimodal", "primary": true }],22  "tags": ["speech", "open-source", "python", "cli", "transcription", "model"],23  "use_cases": ["run-local-models"],24  "operating_systems": ["macos", "linux", "windows"],25  "execution_modes": ["local"],26  "interfaces": ["cli", "library"],27  "deployment_models": ["embedded"],28  "integrations": ["PyTorch", "ffmpeg", "mlx-whisper", "whisper.cpp", "faster-whisper"],29  "data_formats": ["MP3", "WAV", "M4A", "FLAC", "SRT/VTT output"],30  "languages": ["Python"],31  "source_model": "open-source",32  "license_spdx": "MIT",33  "pricing_model": ["open-source", "free"],34  "self_hostable": true,35  "sources": [36    { "url": "https://github.com/openai/whisper", "type": "official_site", "title": "openai/whisper", "supports": ["name", "summary", "capabilities", "prerequisites"], "checked_at": "2026-11-02", "note": "The announcement page on openai.com returns 403 to automated clients; the repository is the canonical reference" },37    { "url": "https://github.com/openai/whisper", "type": "repository", "supports": ["license_spdx", "languages"], "checked_at": "2026-11-02" },38    { "url": "https://github.com/openai/whisper/blob/main/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02" }39  ],40  "confidence": "high",41  "uncertainty_note": "product_status is set to maintenance because the repository receives infrequent updates and the README carries no roadmap; OpenAI has not declared it deprecated.",42  "discovery_method": "editorial-research",43  "depth": "standard",44  "editorial_status": "reviewed",45  "visibility": "public",46  "featured": false,47  "author": "batch-A"48}49