From 011268e492e78c0bbf75fab2d684274324312f26 Mon Sep 17 00:00:00 2001 From: Alexander Veysov Date: Fri, 17 Dec 2021 22:00:36 +0300 Subject: [PATCH] Polish the copy a bit --- README.md | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 47068ee..b186e31 100644 --- a/README.md +++ b/README.md @@ -29,13 +29,13 @@ https://user-images.githubusercontent.com/36505480/144874384-95f80f6d-a4f1-42cc-

Key Features


-- **High accuracy** +- **Stellar accuracy** Silero VAD has [excellent results](https://github.com/snakers4/silero-vad/wiki/Quality-Metrics#vs-other-available-solutions) on speech detection tasks. - **Fast** - One audio chunk (30+ ms) [takes](https://github.com/snakers4/silero-vad/wiki/Performance-Metrics#silero-vad-performance-metrics) around **1ms** to be processed on a single CPU thread. Using batching or GPU can also improve performance considerably. + One audio chunk (30+ ms) [takes](https://github.com/snakers4/silero-vad/wiki/Performance-Metrics#silero-vad-performance-metrics) around **1ms** to be processed on a single CPU thread. Using batching or GPU can also improve performance considerably. Under certain conditions ONNX may even run up to 2-3x faster. - **Lightweight** @@ -47,12 +47,16 @@ https://user-images.githubusercontent.com/36505480/144874384-95f80f6d-a4f1-42cc- - **Flexible sampling rate** - Silero VAD [supports](https://github.com/snakers4/silero-vad/wiki/Quality-Metrics#sample-rate-comparison) **8000 Hz** and **16000 Hz** (JIT) and **16000 Hz** (ONNX) [sampling rates](https://en.wikipedia.org/wiki/Sampling_(signal_processing)#Sampling_rate). + Silero VAD [supports](https://github.com/snakers4/silero-vad/wiki/Quality-Metrics#sample-rate-comparison) **8000 Hz** and **16000 Hz** (PyTorch JIT) and **16000 Hz** (ONNX) [sampling rates](https://en.wikipedia.org/wiki/Sampling_(signal_processing)#Sampling_rate). - **Flexible chunk size** Model was trained on audio chunks of different lengths. **30 ms**, **60 ms** and **100 ms** long chunks are supported directly, others may work as well. +- **Highly Portable** + + Silero VAD reaps benefits from the rich ecosystems built around **PyTorch** and **ONNX** running everywhere where these runtimes are available. +

Typical Use Cases