{"id":40831505,"url":"https://github.com/mahimairaja/fastrtc-whisper-cpp","last_synced_at":"2026-01-21T22:25:51.228Z","repository":{"id":295076063,"uuid":"988611080","full_name":"mahimairaja/fastrtc-whisper-cpp","owner":"mahimairaja","description":"A PyPI package that wraps Whisper.cpp for speech-to-text (STT) transcription, compatible with FastRTC","archived":false,"fork":false,"pushed_at":"2025-06-06T00:55:04.000Z","size":819,"stargazers_count":5,"open_issues_count":4,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-19T03:28:05.963Z","etag":null,"topics":["fastrtc","hugging-face","stt","whisper-ai","whisper-cpp"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/fastrtc-whisper-cpp/","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/mahimairaja.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","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,"zenodo":null},"funding":{"github":["mahimairaja"],"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"lfx_crowdfunding":null,"polar":null,"buy_me_a_coffee":null,"thanks_dev":null,"custom":null}},"created_at":"2025-05-22T20:03:52.000Z","updated_at":"2025-07-10T05:17:20.000Z","dependencies_parsed_at":"2025-06-06T01:32:11.282Z","dependency_job_id":"3ce2f2b6-6500-4d8c-b085-ce4c876d6d17","html_url":"https://github.com/mahimairaja/fastrtc-whisper-cpp","commit_stats":null,"previous_names":["mahimairaja/fastrtc-whisper-cpp"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/mahimairaja/fastrtc-whisper-cpp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mahimairaja%2Ffastrtc-whisper-cpp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mahimairaja%2Ffastrtc-whisper-cpp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mahimairaja%2Ffastrtc-whisper-cpp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mahimairaja%2Ffastrtc-whisper-cpp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mahimairaja","download_url":"https://codeload.github.com/mahimairaja/fastrtc-whisper-cpp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mahimairaja%2Ffastrtc-whisper-cpp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28645548,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-21T21:29:11.980Z","status":"ssl_error","status_checked_at":"2026-01-21T21:24:31.872Z","response_time":86,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["fastrtc","hugging-face","stt","whisper-ai","whisper-cpp"],"created_at":"2026-01-21T22:25:50.707Z","updated_at":"2026-01-21T22:25:51.218Z","avatar_url":"https://github.com/mahimairaja.png","language":"Python","readme":"# Whisper CPP for FastRTC\n\nA PyPI package that wraps Whisper.cpp for speech-to-text (STT) transcription, compatible with the FastRTC STTModel protocol. This package provides efficient, CPU-based speech recognition using the optimized Whisper.cpp implementation.\n\n## Installation\n\n```bash\npip install fastrtc-whisper-cpp\n```\n\nFor audio file loading capabilities, install with the audio extras:\n\n```bash\npip install \"fastrtc-whisper-cpp[audio]\"\n```\n\nFor development:\n\n```bash\npip install \"fastrtc-whisper-cpp[dev]\"\n```\n\n## Usage\n\n### Basic Usage\n\n```python\nfrom fastrtc_whisper_cpp import get_stt_model\nimport numpy as np\n\n# Create the model (downloads from HF if not cached)\nmodel = get_stt_model()\n\n# Example: Create a sample audio array (actual audio would come from a file or mic)\nsample_rate = 16000\naudio_data = np.zeros(16000, dtype=np.float32)  # 1 second of silence\n\n# Transcribe\ntext = model.stt((sample_rate, audio_data))\nprint(f\"Transcription: {text}\")\n```\n\n### Loading Audio Files\n\nIf you've installed with the audio extras:\n\n```python\nfrom fastrtc_whisper_cpp import get_stt_model, load_audio\n\n# Load model\nmodel = get_stt_model()\n\n# Load audio file (automatically resamples to 16kHz)\naudio = load_audio(\"path/to/audio.wav\")\n\n# Transcribe\ntext = model.stt(audio)\nprint(f\"Transcription: {text}\")\n```\n\n### Using with FastRTC\n\n```python\nfrom fastrtc_whisper_cpp import get_stt_model\n\n# Create the model\nwhisper_model = get_stt_model()\n\n# Use within FastRTC applications\n# (Follow FastRTC documentation for integration details)\n```\n\n## Available Models\n\nThe package supports various Whisper.cpp models with different sizes and quantization levels:\n\n- English-only models (faster, smaller):\n  - `tiny.en`, `tiny.en-q5_1`, `tiny.en-q8_0`\n  - `base.en`, `base.en-q5_1`, `base.en-q8_0`\n  - `small.en`, `small.en-q5_1`, `small.en-q8_0`\n  - `medium.en`, `medium.en-q5_0`, `medium.en-q8_0`\n\n- Multilingual models:\n  - `tiny`, `tiny-q5_1`, `tiny-q8_0`\n  - `base`, `base-q5_1`, `base-q8_0`\n  - `small`, `small-q5_1`, `small-q8_0`\n  - `medium`, `medium-q5_0`, `medium-q8_0`\n  - `large-v1`\n  - `large-v2`, `large-v2-q5_0`, `large-v2-q8_0`\n  - `large-v3`, `large-v3-q5_0`\n  - `large-v3-turbo`, `large-v3-turbo-q5_0`, `large-v3-turbo-q8_0`\n\nExample:\n\n```python\nfrom fastrtc_whisper_cpp import get_stt_model\n\n# Choose a specific model\nmodel = get_stt_model(\"medium.en-q8_0\")\n```\n\n## Advanced Configuration\n\nYou can configure the model with specific parameters:\n\n```python\nfrom fastrtc_whisper_cpp import WhisperCppSTT\n\n# Configure with specific model and models directory\nmodel = WhisperCppSTT(\n    model=\"medium.en\",\n    models_dir=\"/path/to/models\"  # Optional custom models directory\n)\n```\n\n## Requirements\n\n- Python 3.10+\n- numpy\n- pywhispercpp\n- librosa (optional, for audio file loading)\n- click (for CLI features)\n\n## Development\n\nClone the repository and install in development mode:\n\n```bash\ngit clone https://github.com/mahimairaja/fastrtc-whisper-cpp.git\ncd fastrtc-whisper-cpp\npip install -e \".[dev,audio]\"\n```\n\n## License\n\nMIT\n\n\n\u003c!-- GitAds-Verify: CDRPYNI76ZF71576X1SKGMXY7P2YWBYW --\u003e\n## GitAds Sponsored\n[![Sponsored by GitAds](https://gitads.dev/v1/ad-serve?source=mahimairaja/fastrtc-whisper-cpp@github)](https://gitads.dev/v1/ad-track?source=mahimairaja/fastrtc-whisper-cpp@github)\n\n","funding_links":["https://github.com/sponsors/mahimairaja"],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmahimairaja%2Ffastrtc-whisper-cpp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmahimairaja%2Ffastrtc-whisper-cpp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmahimairaja%2Ffastrtc-whisper-cpp/lists"}