Silero-vad

Latest version: v5.1.2

Safety actively analyzes 682361 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 1 of 2

5.1.2

A tag to upload new PIP package.

5.1.1

What's Changed

* Fix Golang example by streamer45 in https://github.com/snakers4/silero-vad/pull/496
* fix: rust example for v5 checkpoint by rumbleFTW in https://github.com/snakers4/silero-vad/pull/497
* VadIterator first chunk bag fx by adamnsandle in https://github.com/snakers4/silero-vad/pull/505
* Add java example for wav file & support V5 model by yuguanqin in https://github.com/snakers4/silero-vad/pull/506
* add csharp example by nganju98 in https://github.com/snakers4/silero-vad/pull/507
* downgrade onnxruntime dependency by adamnsandle in https://github.com/snakers4/silero-vad/pull/521
* код для тюнинга by adamnsandle in https://github.com/snakers4/silero-vad/pull/526
* add neg_threshold parameter explicitly by adamnsandle in https://github.com/snakers4/silero-vad/pull/528
* Adamnsandle by adamnsandle in https://github.com/snakers4/silero-vad/pull/529
* Fixed the pyaudio example can not run issue. by gengyuchao in https://github.com/snakers4/silero-vad/pull/539
* Update README.md by adamnsandle in https://github.com/snakers4/silero-vad/pull/540
* Update README.md by adamnsandle in https://github.com/snakers4/silero-vad/pull/541
* Update README.md by snakers4 in https://github.com/snakers4/silero-vad/pull/542
* Adamnsandle by adamnsandle in https://github.com/snakers4/silero-vad/pull/543
* Adamnsandle by adamnsandle in https://github.com/snakers4/silero-vad/pull/549

New Contributors

* rumbleFTW made their first contribution in https://github.com/snakers4/silero-vad/pull/497
* yuguanqin made their first contribution in https://github.com/snakers4/silero-vad/pull/506
* nganju98 made their first contribution in https://github.com/snakers4/silero-vad/pull/507
* gengyuchao made their first contribution in https://github.com/snakers4/silero-vad/pull/539

**Full Changelog**: https://github.com/snakers4/silero-vad/compare/v5.1...v5.1.1

5.1

Experimental PIP package release

- Experimental pip-package release;
- Community PRs to update the examples;

What's Changed

* Adamnsandle by adamnsandle in https://github.com/snakers4/silero-vad/pull/481
* Update microphone_and_webRTC_integration.py by eltociear in https://github.com/snakers4/silero-vad/pull/475
* cpp example by filtercodes in https://github.com/snakers4/silero-vad/pull/482
* Update Golang example to support model v5 by streamer45 in https://github.com/snakers4/silero-vad/pull/489
* Create python-publish.yml by adamnsandle in https://github.com/snakers4/silero-vad/pull/492
* Adamnsandle by adamnsandle in https://github.com/snakers4/silero-vad/pull/493

New Contributors
* eltociear made their first contribution in https://github.com/snakers4/silero-vad/pull/475
* filtercodes made their first contribution in https://github.com/snakers4/silero-vad/pull/482

**Full Changelog**: https://github.com/snakers4/silero-vad/compare/v5.0...v5.1

5.0

![image](https://github.com/snakers4/silero-vad/assets/12515440/5f581592-3035-411e-9803-44a2fda0af8e)

**Performance and Model Size**

- 3x [faster](https://github.com/snakers4/silero-vad/wiki/Performance-Metrics) inference for TorchScript, 10% faster inference for ONNX;
- Now TorchScript is as fast as ONNX;
- Model size is 2x larger, 2MB vs. 1MB;

**Quality**

- The VAD supports more than 6,000 languages now;
- Significanly more robust on noisy data;
- Overall 5-7% quality increase on clean data;
- Quality difference for 8 kHz and 16 kHz is negligible now;
- Quality difference for different window sizes is negligible => window size was deprecated;
- Added [benchmarks ](https://github.com/snakers4/silero-vad/wiki/Quality-Metrics) on 9 unique datasets (2 private) and one holistic multi-domain dataset;

**Changes and deprecations**

- ONNX opset 16;
- `window_size_samples` is deprecated - now the VAD only works with fixed size window;
- VAD now works with 8 kHz and 16 kHz sample rates, only with fixed 256 and 512 sample windows respectively;
- Slightly changed internal logic, now some context (part of previous chunk) is passed along with the current chunk;
- Sample rates that are a multiple of 16 kHz are still supported;

4.0

New V4 VAD Released


- Improved [quality](https://github.com/snakers4/silero-vad/wiki/Quality-Metrics#silero-vad-vs-old-silero-vad)
- Improved [perfomance](https://github.com/snakers4/silero-vad/wiki/Performance-Metrics#silero-vad-performance-metrics)
- Both 8k and 16k sampling rates are now supported by the ONNX model
- Batching is now supported by the ONNX model
- Added audio_forward method for one-line processing of a single or multiple audio without postprocessing
- Hotfix applied - wrong model was uploaded
- Minor hotfix re. PyTorch version

3.1

We finally were able to port a model to ONNX:

- Compact model (~100k params);
- Both PyTorch and ONNX models are not quantized;
- Same quality model as the latest best PyTorch release;
- Only 16kHz available now (ONNX has some issues with if-statements and / or tracing vs scripting) with cryptic errors;
- In our tests, on short audios (chunks) ONNX is 2-3x faster than PyTorch (this is mitigated with larger batches or long audios);
- Audio examples and non-core models moved out of the repo to save space;

Page 1 of 2

Links

Releases

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.