Model reference · open weights

DeepFilterNet3-CoreML

DeepFilterNet3-CoreML is an open-weight audio or speech model from aufklarer, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio aufklarer 1 variants 5k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What DeepFilterNet3-CoreML is

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). 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) Files Usage Add speech-swift to Package.swift: Then denoise: CLI: Source - Base model: Rikorose/DeepFilterNet3 (Apache-2.0) License - Model weights: Apache-2.0 / MIT dual license - CoreML conversion: Apache-2.0 Links - speech-swift — Apple SDK - soniqo.audio — website - MLX vs CoreML on Apple Silicon — a practical guide — related blog post - soniqo.audio/blog — blog Reference - DeepFilterNet3 paper

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makeraufklarer
TypeAudio & music
Variants1
Runs withcoreml
Based onRikorose/DeepFilterNet3
Released2026-03-04
Popularity5k downloads / month
Likes4
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
DeepFilterNet3-CoreMLBF16Weights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys deepfilternet3-coreml for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (deepfilternet3-coreml below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="deepfilternet3-coreml" -F file=@audio.mp3

Details

Languages, data & research

Tags

coreml deepfilternet3 speech-enhancement denoising apple-silicon deepfilternet int8 palettization audio-to-audio

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want DeepFilterNet3-CoreML on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms