Silero VAD v6.2.1 CoreML

Provideraufklarer
Categoryvoice-activity-detection
Licensemit
Downloads3.4K
Stars0

Overview

Silero VAD v6.2.1 CoreML is a highly optimized voice activity detection model specifically ported for Apple silicon. Unlike general-purpose audio classifiers, this model is designed for low-latency, real-time speech boundary detection, making it an essential utility for developers building voice-to-text pipelines or interactive AI assistants on iOS and macOS. It effectively filters out non-speech noise to trigger downstream processing only when human speech is present, significantly reducing CPU overhead and battery drain. By leveraging the CoreML framework, it provides native hardware acceleration, offering a performance-to-power ratio that outperforms generic PyTorch or TensorFlow implementations on Apple devices.

Highlights

  • Native CoreML acceleration for iOS and macOS devices
  • Low-latency real-time speech boundary detection
  • Reduces power consumption by filtering non-speech audio
  • Ideal for pre-processing voice-to-text pipelines
  • Lightweight footprint with minimal system overhead

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("aufklarer/Silero-VAD-v6.2.1-CoreML")
tokenizer = AutoTokenizer.from_pretrained("aufklarer/Silero-VAD-v6.2.1-CoreML")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download aufklarer/Silero-VAD-v6.2.1-CoreML

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download aufklarer/Silero-VAD-v6.2.1-CoreML config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('aufklarer/Silero-VAD-v6.2.1-CoreML')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/aufklarer/Silero-VAD-v6.2.1-CoreML

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/aufklarer/Silero-VAD-v6.2.1-CoreML

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('aufklarer/Silero-VAD-v6.2.1-CoreML')
tokenizer = AutoTokenizer.from_pretrained('aufklarer/Silero-VAD-v6.2.1-CoreML')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model aufklarer/Silero-VAD-v6.2.1-CoreML

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model aufklarer/Silero-VAD-v6.2.1-CoreML README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('aufklarer/Silero-VAD-v6.2.1-CoreML')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/aufklarer/Silero-VAD-v6.2.1-CoreML.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/aufklarer/Silero-VAD-v6.2.1-CoreML.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'aufklarer/Silero-VAD-v6.2.1-CoreML')

Full Documentation

来源: HuggingFace

---
license: mit
language:

  • en

tags:
  • audio

  • speech

  • voice-activity-detection

  • coreml

  • ios

  • macos

base_model:
  • snakers4/silero-vad

library_name: coreml
pipeline_tag: voice-activity-detection
---

Silero VAD v6.2.1 CoreML

CoreML export of Silero VAD v6.2.1 for Apple platforms. The package includes a drop-in 32 ms streaming model and a faster 256 ms aggregate variant.

Model Table

| Model | Format | Precision | Input | New audio per call | Size |
|---|---:|---:|---:|---:|---:|
| silero_vad.mlmodelc | CoreML mlprogram | Float16 | [1, 1, 576] | 512 samples / 32 ms | 640 KB |
| silero_vad_256ms.mlmodelc | CoreML mlprogram | Float16 | [1, 1, 4160] | 4096 samples / 256 ms | 760 KB |

Both variants use explicit LSTM state tensors:

| Name | Shape | Description |
|---|---:|---|
| audio | [1, 1, 576] or [1, 1, 4160] | 64-sample left context plus current audio |
| h | [1, 1, 128] | LSTM hidden state |
| c | [1, 1, 128] | LSTM cell state |
| probability | [1] | Speech probability |
| h_out | [1, 1, 128] | Updated hidden state |
| c_out | [1, 1, 128] | Updated cell state |

Files

| File | Description |
|---|---|
| silero_vad.mlmodelc/ | 32 ms streaming CoreML bundle |
| silero_vad_256ms.mlmodelc/ | 256 ms aggregate CoreML bundle using noisy-OR over eight internal 32 ms windows |
| config.json | Runtime metadata, shapes, upstream version, and variant list |

Performance

Benchmarked on an Apple Silicon Mac using a 50-file VAD set with 2,445.9 seconds of audio, onset 0.25, offset 0.20, min speech 0.25s, min silence 0.10s.

| Model | File F1 | Span F1 | Precision | Recall | FAR | Miss Rate | Throughput |
|---|---:|---:|---:|---:|---:|---:|---:|
| v5.1.2 CoreML baseline | 100.00% | 86.27% | 100.00% | 75.86% | 0.00% | 24.14% | 410.0xRT |
| v6.2.1 silero_vad.mlmodelc | 98.04% | 87.47% | 99.98% | 77.74% | 3.44% | 22.26% | 412.4xRT |
| v6.2.1 silero_vad_256ms.mlmodelc | 92.59% | 93.88% | 99.97% | 88.49% | 7.80% | 11.51% | 1442.2xRT |

The 32 ms variant preserves the existing streaming interface and is the safest drop-in replacement. The 256 ms variant is substantially faster and more recall-oriented, but uses coarser probability frames.

Usage

swift
import CoreML

let config = MLModelConfiguration()
config.computeUnits = .all
let modelURL = Bundle.main.url(forResource: "silero_vad", withExtension: "mlmodelc")!
let model = try MLModel(contentsOf: modelURL, configuration: config)

For a complete Swift runtime, see:

Source

Converted from snakers4/silero-vad, tag v6.2.1.

View official source
Join our Telegram