ModelPrésentéExterne

Silero VAD v6.2.1 MLX

MLX port of snakers4/silero-vad tag v6.2.1 for voice activity detection on Apple Silicon.

Sourcehuggingface.co/aufklarer/Silero-VAD-v6.2.1-MLX/tree/0046cea48b26401909b24292b688fbc9b6322bc5

TypeOtherModèle de basesnakers4/silero-vadVersionRevision 0046ceaBClasse

Source du modèle

Type: Other
Taille du fichier: 1,18 MB
Modèle de base: snakers4/silero-vad
Version: vRevision 0046cea
Mis à jour: 12 oct. 2026
Téléchargements: 8,5 k
Source: Hugging Face

Description de la source

Silero VAD v6.2.1 MLX

MLX port of snakers4/silero-vad tag v6.2.1 for voice activity detection on Apple Silicon.

Model

Field	Value
Parameters	309,121
Quantization	none, Float32 weights
Format	MLX safetensors
Sample rate	16 kHz
Chunk size	512 samples, 32 ms
Context	64 samples
Upstream	`snakers4/silero-vad:v6.2.1`

Files

File	Size	Description
`model.safetensors`	1.2 MB	MLX weights
`config.json`	456 B	Model metadata and runtime shape config
`README.md`	-	Model card

Performance

Measured with speech-swift release tests on Apple Silicon using a 20 s 16 kHz speech fixture, 625 streaming chunks.

Backend	Segment	Latency per chunk	RTF
Silero v6.2.1 MLX	5.184s-8.416s	0.4999 ms	0.01562
Silero v6.2.1 CoreML	5.184s-8.416s	0.0630 ms	0.00197

Parity against the matching CoreML v6.2.1 export:

Metric	Value
Max probability diff	0.060569
Average probability diff	0.001673

The exported safetensors were also checked tensor-by-tensor against the upstream v6.2.1 JIT state dict after conversion; the maximum absolute tensor difference was 0.

Usage

Swift SDK

import SpeechVAD

let vad = try await SileroVADModel.fromPretrained(engine: .mlx)
let segments = vad.detectSpeech(audio: samples, sampleRate: 16000)

CLI

speech vad input.wav

Source

Converted from snakers4/silero-vad tag v6.2.1. The upstream project is MIT licensed.

Links

speech-swift - Apple SDK
Docs - install and CLI docs
soniqo.audio - website
blog - blog

Sources

1 source

Hugging FacePrincipalVersion 0046cea48b26401909b24292b688fbc9b6322bc5

huggingface.co/aufklarer/Silero-VAD-v6.2.1-MLX/tree/0046cea48b26401909b24292b688fbc9b6322bc5

Vérifié 12 oct.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 1,18 MB · SHA-256 8367dac03e6c…bc0b · Hugging Face

Télécharger

Extraits de sources

3 extraits

Readme2 aoûthuggingface.co/aufklarer/Silero-VAD-v6.2.1-MLX

--- license: mit language: - multilingual tags: - audio - speech - voice-activity-detection - vad - mlx - apple-silicon base_model: snakers4/silero-vad library_name: mlx pipeline_tag: audio-classification --- # Silero VAD v6.2.1 MLX MLX port of [snakers4/silero-vad](https://github.com/snakers4/silero-vad) tag `v6.2.1` for voice activity detection on Apple Silicon. ## Model | Field | Value | |---|---:| | Parameters | 309,121 | | Quantization | none, Float32 weights | | Format | MLX safetensors | | Sample rate | 16 kHz | | Chunk size | 512 samples, 32 ms | | Context | 64 samples | | Upstream | `snakers4/silero-vad:v6.2.1` | ## Files | File | Size | Description | |---|---:|---| | `model.safetensors` | 1.2 MB | MLX weights | | `config.json` | 456 B | Model metadata and runtime shape config | | `README.md` | - | Model card | ## Performance Measured with `speech-swift` release tests on Apple Silicon using a 20 s 16 kHz speech fixture, 625 streaming chunks. | Backend | Segment | Latency per chunk | RTF | |---|---:|---:|---:| | Silero v6.2.1 MLX | 5.184s-8.416s | 0.4999 ms | 0.01562 | | Silero v6.2.1 CoreML | 5.184s-8.416s | 0.0630 ms | 0.00197 | Parity against the matching CoreML v6.2.1 export: | Metric | Value | |---|---:| | Max probability diff | 0.060569 | | Average probability diff | 0.001673 | The exported safetensors were also checked tensor-by-tensor against the upstream v6.2.1 JIT state dict after conversion; the maximum absolute tensor difference was 0. ## Usage ### Swift SDK ```swift import SpeechVAD let vad = try await SileroVADModel.fromPretrained(engine: .mlx) let segments = vad.detectSpeech(audio: samples, sampleRate: 16000) ``` ### CLI ```bash speech vad input.wav ``` ## Source Converted from [snakers4/silero-vad](https://github.com/snakers4/silero-vad) tag `v6.2.1`. The upstream project is MIT licensed. ## Links - [speech-swift](https://github.com/soniqo/speech-swift) - Apple SDK - [Docs](https://soniqo.audio/getting-started) - install and CLI docs - [soniqo.audio](https://soniqo.audio) - website - [blog](https://soniqo.audio/blog) - blog

Note12 oct.huggingface.co/aufklarer/Silero-VAD-v6.2.1-MLX

Source context: 8500 downloads · 1 likes · Pipeline audio-classification · Library mlx · Repo aufklarer/Silero-VAD-v6.2.1-MLX

Note2 aoûthuggingface.co/aufklarer/Silero-VAD-v6.2.1-MLX

Source context: 15972 downloads · 1 likes · Pipeline audio-classification · Library mlx · Repo aufklarer/Silero-VAD-v6.2.1-MLX