Silero VAD: pre-trained enterprise-grade Voice Activity Detector
This report summarizes scanner evidence for snakers4/silero-vad, a Python project with 10,403 GitHub stars. SynthScan examined 8,517 lines of code across 76 source files, recording 51 pattern matches distributed across 8 syntactic categories. The legacy adjusted pattern signal is 6.5 (Moderate pattern signal); it is not an authorship estimate.
Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.
Use each vector to guide manual verification of the underlying findings.
Can maintainers explain intent, assumptions, and trade-offs? 38 finding(s).
Are imports declared and package/API names verified? 8 finding(s).
Are wrappers, guards, and repeated structures necessary? 28 finding(s).
Which changes need focused human review? 51 finding(s).
This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.
Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.
This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.
The scanner identified 51 distinct pattern matches across 8 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.
Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | tests/test_basic.py | 25 | def test_collect_chunks_without_speech(): | CODE |
| LOW | tests/test_vad_iterator.py | 22 | def test_vad_iterator_ends_speech_at_low_threshold(onnx, threshold): | CODE |
| LOW | tests/test_audio_backends.py | 38 | def test_backends_agree_on_speech_timestamps(path, model, monkeypatch): | CODE |
| LOW | tests/test_audio_backends.py | 57 | def test_backends_are_identical_without_resampling(monkeypatch): | CODE |
| LOW | tests/test_audio_backends.py | 69 | def test_torchaudio_loader_failure_falls_back_to_torchcodec(path, monkeypatch): | CODE |
| LOW | tests/test_audio_backends.py | 83 | def test_torchaudio_without_torchcodec_reports_the_pin(without_torchcodec, monkeypatch): | CODE |
| LOW | tests/test_audio_backends.py | 94 | def test_stereo_is_averaged_not_ffmpeg_downmixed(without_torchaudio): | CODE |
| LOW | tests/test_optional_deps.py | 23 | def test_import_does_not_pull_optional_packages(): | CODE |
| LOW | tests/test_optional_deps.py | 38 | def test_onnxruntime_imported_only_when_a_session_is_built(): | CODE |
| LOW | tests/test_optional_deps.py | 49 | def test_lazy_sequence_attributes_still_resolve(): | CODE |
| LOW | tests/test_optional_deps.py | 62 | def test_no_audio_backend_raises_actionable_error(without_torchaudio, without_torchcodec): | CODE |
| LOW | tests/test_optional_deps.py | 74 | def test_vad_runs_without_any_audio_backend(without_torchaudio, without_torchcodec): | CODE |
| LOW | tests/test_optional_deps.py | 84 | def test_torchcodec_backend_without_torchaudio(without_torchaudio, tmp_path): | CODE |
| LOW | tests/test_sequence_parity.py | 89 | def test_multichannel_audio_is_rejected_like_stock(): | CODE |
| LOW | tuning/utils.py | 37 | def build_audiomentations_augs(p): | CODE |
| LOW | tuning/utils.py | 123 | def get_ground_truth_annotated(self, annotation, audio_length_samples): | CODE |
| LOW | tuning/utils.py | 326 | def calculate_best_thresholds(all_predicts, all_gts): | CODE |
| LOW | src/silero_vad/sequence_vad.py | 152 | def get_speech_timestamps_sequence(audio, | CODE |
| LOW | src/silero_vad/utils_vad.py | 421 | def get_speech_timestamps_from_probs(speech_probs: List[float], | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | examples/c++/wav.h | 1 | // Copyright (c) 2016 Personal (Binbin Zhang) | COMMENT |
| LOW | examples/c++/silero.h | 1 | #ifndef SILERO_H | COMMENT |
| LOW | examples/cpp_libtorch/wav.h | 1 | // Copyright (c) 2016 Personal (Binbin Zhang) | COMMENT |
| LOW | examples/cpp_libtorch/silero_torch.h | 1 | //Author : Nathan Lee | COMMENT |
| LOW | examples/cpp_libtorch_deprecated/wav.h | 1 | // Copyright (c) 2016 Personal (Binbin Zhang) | COMMENT |
| LOW | examples/cpp_libtorch_deprecated/silero_torch.h | 1 | //Author : Nathan Lee | COMMENT |
| LOW | examples/cpp/silero-vad-onnx.cpp | 1 | #ifndef _CRT_SECURE_NO_WARNINGS | COMMENT |
| LOW | examples/cpp/wav.h | 1 | // Copyright (c) 2016 Personal (Binbin Zhang) | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | src/silero_vad/__init__.py | 7 | CODE | |
| LOW | src/silero_vad/__init__.py | 8 | CODE | |
| LOW | src/silero_vad/__init__.py | 8 | CODE | |
| LOW | src/silero_vad/__init__.py | 8 | CODE | |
| LOW | src/silero_vad/__init__.py | 8 | CODE | |
| LOW | src/silero_vad/__init__.py | 8 | CODE | |
| LOW | src/silero_vad/__init__.py | 8 | CODE | |
| LOW | src/silero_vad/__init__.py | 8 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | examples/openvino/convert.py | 49 | CODE | |
| LOW | examples/openvino/convert.py | 129 | CODE | |
| LOW | examples/openvino/convert.py | 164 | CODE | |
| LOW | examples/openvino/verify.py | 116 | CODE | |
| LOW | …ebRTC_integration/microphone_and_webRTC_integration.py | 76 | CODE | |
| LOW | tuning/utils.py | 326 | CODE | |
| LOW | src/silero_vad/utils_vad.py | 421 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | src/silero_vad/__init__.py | 4 | except: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | src/silero_vad/sequence_vad.py | 152 | CODE | |
| LOW | src/silero_vad/utils_vad.py | 281 | CODE | |
| LOW | src/silero_vad/utils_vad.py | 421 | CODE | |
| LOW | src/silero_vad/utils_vad.py | 144 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | tests/conftest.py | 36 | except Exception: | CODE |
| LOW | tuning/utils.py | 142 | except Exception as e: | CODE |
| LOW | src/silero_vad/utils_vad.py | 250 | except Exception: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | src/silero_vad/__init__.py | 20 | __all__ = ['load_silero_vad', | CODE |