{"id":31769194,"url":"https://github.com/second-state/silero_vad_jit","last_synced_at":"2025-10-10T02:41:42.172Z","repository":{"id":308154555,"uuid":"1015985898","full_name":"second-state/silero_vad_jit","owner":"second-state","description":null,"archived":false,"fork":false,"pushed_at":"2025-08-04T13:32:20.000Z","size":12,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-14T10:59:26.359Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Rust","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/second-state.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}},"created_at":"2025-07-08T10:16:28.000Z","updated_at":"2025-08-16T01:16:36.000Z","dependencies_parsed_at":"2025-08-04T15:54:16.488Z","dependency_job_id":null,"html_url":"https://github.com/second-state/silero_vad_jit","commit_stats":null,"previous_names":["second-state/silero_vad_jit"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/second-state/silero_vad_jit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fsilero_vad_jit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fsilero_vad_jit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fsilero_vad_jit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fsilero_vad_jit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/second-state","download_url":"https://codeload.github.com/second-state/silero_vad_jit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/second-state%2Fsilero_vad_jit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279002541,"owners_count":26083403,"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":"2025-10-10T02:00:06.843Z","response_time":62,"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":[],"created_at":"2025-10-10T02:41:40.360Z","updated_at":"2025-10-10T02:41:42.166Z","avatar_url":"https://github.com/second-state.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Silero-VAD V5 in Rust (based on LibTorch)\n\nThis is a Rust implementation of [Silero-VAD V5](https://github.com/snakers4/silero-vad), **rewritten by Claude from the original Python version**. Silero-VAD is a Voice Activity Detection (VAD) system that can detect speech segments in audio files, separating speech from silence and noise.\n\nThe implementation uses LibTorch for PyTorch model inference and maintains full compatibility with the original Python version's results. It provides the same functionality including speech detection, timestamp generation, and configurable parameters for different use cases.\n\n## What is VAD?\n\nVoice Activity Detection (VAD) is used to:\n- **Detect speech segments** in audio recordings\n- **Generate timestamps** for when speech starts and ends\n- **Remove silence** from audio for further processing\n- **Preprocess audio** for speech recognition systems\n- **Analyze conversations** and meetings\n\n## Requirements\n\n- **Rust**: 1.70.0 or later\n- **LibTorch**: 1.13.0 or later\n- **System**: GCC 11.4.0+ (Linux), MSVC 2019+ (Windows), or Xcode Command Line Tools (macOS)\n\n## LibTorch Installation\n\n### Download LibTorch\n\n#### Linux\n```bash\n# CPU Version\nwget https://download.pytorch.org/libtorch/cpu/libtorch-cxx11-abi-shared-with-deps-2.4.0%2Bcpu.zip\nunzip libtorch-cxx11-abi-shared-with-deps-2.4.0+cpu.zip\n\n# CUDA Version\nwget https://download.pytorch.org/libtorch/cu128/libtorch-cxx11-abi-shared-with-deps-2.4.0%2Bcu128.zip\nunzip libtorch-cxx11-abi-shared-with-deps-2.4.0+cu128.zip\n```\n\n#### Windows\n```powershell\n# CPU Version\nInvoke-WebRequest -Uri \"https://download.pytorch.org/libtorch/cpu/libtorch-win-shared-with-deps-2.4.0%2Bcpu.zip\" -OutFile \"libtorch-cpu.zip\"\nExpand-Archive -Path \"libtorch-cpu.zip\" -DestinationPath \".\"\n\n# CUDA Version\nInvoke-WebRequest -Uri \"https://download.pytorch.org/libtorch/cu128/libtorch-win-shared-with-deps-2.4.0%2Bcu128.zip\" -OutFile \"libtorch-cuda.zip\"\nExpand-Archive -Path \"libtorch-cuda.zip\" -DestinationPath \".\"\n```\n\n#### macOS\n```bash\n# CPU Version\nwget https://download.pytorch.org/libtorch/cpu/libtorch-macos-arm64-2.4.0.zip\nunzip libtorch-macos-arm64-2.4.0.zip\n```\n\n### Set Environment Variables\n\n#### Linux/macOS\n```bash\nexport LIBTORCH=/path/to/libtorch\nexport LD_LIBRARY_PATH=${LIBTORCH}/lib:$LD_LIBRARY_PATH  # Linux\nexport DYLD_LIBRARY_PATH=${LIBTORCH}/lib:$DYLD_LIBRARY_PATH  # macOS\n```\n\n#### Windows\n```powershell\n$env:LIBTORCH = \"C:\\path\\to\\libtorch\"\n$env:PATH += \";C:\\path\\to\\libtorch\\lib\"\n```\n\n## Download Model\n\n```bash\n# Download the PyTorch JIT model\nwget https://github.com/snakers4/silero-vad/raw/master/files/silero_vad.jit\n```\n\n## About\n\nThis Rust implementation was created by Claude AI as a faithful port of the original Python Silero-VAD implementation. It maintains the same algorithm logic, parameter handling, and output format while leveraging Rust's performance and safety features.\n\nThe implementation includes all features from the Python version:\n- Speech timestamp detection\n- Configurable thresholds and durations\n- Speech padding\n- Progress tracking\n- Multiple output formats\n\n## License\n\nThis project follows the same license as the original Silero-VAD project.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsecond-state%2Fsilero_vad_jit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsecond-state%2Fsilero_vad_jit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsecond-state%2Fsilero_vad_jit/lists"}