ModelListadosExterno

DeepFilterNet3 CoreML

Real-time speech enhancement for Apple Silicon. Removes background noise from speech audio. Runs on Neural Engine via CoreML.

Fontehuggingface.co/aufklarer/DeepFilterNet3-CoreML/tree/937bad9811f1ffc1a06ea0d676461b080b2bdc93

TipoOtherModelo baseRikorose/DeepFilterNet3VersãoCoremldataBnota

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 243 B–2,08 MB
Modelo base: Rikorose/DeepFilterNet3
Versão: vCoremldata
Atualizado: 22 de out. de 2026
Fonte: Hugging Face

Descrição da fonte

DeepFilterNet3 — CoreML INT8

Real-time speech enhancement for Apple Silicon. Removes background noise from speech audio. Runs on Neural Engine via CoreML.

2.1M params, INT8 k-means palettization, 2.2 MB
48 kHz native, 10 ms frames
Requires macOS 14+ / iOS 17+

Quality

Measured on 30 VoiceBank-DEMAND test clips via Python CoreMLBackend (replaces only the NN forward; keeps the PyTorch STFT / ERB / deep-filter post-processing intact).

Variant	PESQ	STOI	SI-SDR	Size
PyTorch FP32 (reference)	2.900	0.947	18.19	—
CoreML FP16	2.901	0.947	18.19	4.2 MB
CoreML INT8 (this repo)	2.907	0.947	18.11	2.2 MB

INT8 matches FP16 within run-to-run noise (ΔPESQ +0.006, ΔSI-SDR −0.07 dB, STOI identical) while cutting size by 48%.

Latency (M2 Max)

Duration	Time	RTF
5 s	0.65 s	0.13
10 s	1.2 s	0.12
20 s	4.8 s	0.24

Files

File	Size	Description
`DeepFilterNet3.mlmodelc`	2.2 MB	Pre-compiled CoreML model (runs on Neural Engine)
`auxiliary.npz`	126 KB	ERB filterbank, Vorbis window, normalization states

Usage

Add speech-swift to Package.swift:

.package(url: "https://github.com/soniqo/speech-swift", branch: "main")

Then denoise:

import SpeechEnhancement

let enhancer = try await SpeechEnhancer.fromPretrained()
let clean = try enhancer.enhance(audio: noisyAudio, sampleRate: 48000)

CLI:

swift run audio denoise noisy.wav --output clean.wav

Source

Base model: Rikorose/DeepFilterNet3 (Apache-2.0)

License

Model weights: Apache-2.0 / MIT dual license
CoreML conversion: Apache-2.0

Reference

DeepFilterNet3 paper

Fontes

1 fonte

Hugging FacePrimárioVersão 937bad9811f1ffc1a06ea0d676461b080b2bdc93

huggingface.co/aufklarer/DeepFilterNet3-CoreML/tree/937bad9811f1ffc1a06ea0d676461b080b2bdc93

Verificado 7 de ago.

Artefatos de modelo

3 artefatos

DeepFilterNet3.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 6dc4207ced0f…46cf · Hugging Face

Baixar

DeepFilterNet3.mlmodelc/coremldata.bin

bin · 415 B · SHA-256 b1b2798fa27a…92ca · Hugging Face

Baixar

DeepFilterNet3.mlmodelc/weights/weight.bin

bin · 2,08 MB · SHA-256 6b6adf3f7897…0018 · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme7 de ago.huggingface.co/aufklarer/DeepFilterNet3-CoreML

--- license: apache-2.0 tags: - speech-enhancement - denoising - coreml - apple-silicon - deepfilternet - int8 - palettization base_model: Rikorose/DeepFilterNet3 library_name: coreml pipeline_tag: audio-to-audio --- # DeepFilterNet3 — CoreML INT8 Real-time speech enhancement for Apple Silicon. Removes background noise from speech audio. Runs on **Neural Engine** via CoreML. - **2.1M params**, INT8 k-means palettization, **2.2 MB** - 48 kHz native, 10 ms frames - Requires macOS 14+ / iOS 17+ ## Quality Measured on 30 VoiceBank-DEMAND test clips via Python `CoreMLBackend` (replaces only the NN forward; keeps the PyTorch STFT / ERB / deep-filter post-processing intact). | Variant | PESQ | STOI | SI-SDR | Size | |---------|------|------|--------|------| | PyTorch FP32 (reference) | 2.900 | 0.947 | 18.19 | — | | CoreML FP16 | 2.901 | 0.947 | 18.19 | 4.2 MB | | **CoreML INT8 (this repo)** | **2.907** | **0.947** | **18.11** | **2.2 MB** | INT8 matches FP16 within run-to-run noise (ΔPESQ +0.006, ΔSI-SDR −0.07 dB, STOI identical) while cutting size by 48%. ## Latency (M2 Max) | Duration | Time | RTF | |----------|------|-----| | 5 s | 0.65 s | 0.13 | | 10 s | 1.2 s | 0.12 | | 20 s | 4.8 s | 0.24 | ## Files | File | Size | Description | |------|------|-------------| | `DeepFilterNet3.mlmodelc` | 2.2 MB | Pre-compiled CoreML model (runs on Neural Engine) | | `auxiliary.npz` | 126 KB | ERB filterbank, Vorbis window, normalization states | ## Usage Add [speech-swift](https://github.com/soniqo/speech-swift) to `Package.swift`: ```swift .package(url: "https://github.com/soniqo/speech-swift", branch: "main") ``` Then denoise: ```swift import SpeechEnhancement let enhancer = try await SpeechEnhancer.fromPretrained() let clean = try enhancer.enhance(audio: noisyAudio, sampleRate: 48000) ``` CLI: ```bash swift run audio denoise noisy.wav --output clean.wav ``` ## Source - Base model: [Rikorose/DeepFilterNet3](https://github.com/Rikorose/DeepFilterNet) (Apache-2.0) ## License - Model weights: Apache-2.0 / MIT dual license - CoreML conversion: Apache-2.0 ## Links - [speech-swift](https://github.com/soniqo/speech-swift) — Apple SDK - [soniqo.audio](https://soniqo.audio) — website - [MLX vs CoreML on Apple Silicon — a practical guide](https://blog.ivan.digital/mlx-vs-coreml-on-apple-silicon-a-practical-guide-to-picking-the-right-backend-and-why-you-sh...

Note7 de ago.huggingface.co/aufklarer/DeepFilterNet3-CoreML

Source context: 6178 downloads · 4 likes · Pipeline audio-to-audio · Library coreml · Repo aufklarer/DeepFilterNet3-CoreML