|
Download README.md from iky1e/DPDFNet4-CoreML: direct link, hf CLI and curl.
- Browser
- Download file 2.56 kB
-
https://huggingface.co/iky1e/DPDFNet4-CoreML/resolve/main/README.md
- Command line
-
hf download hf://iky1e/DPDFNet4-CoreML/README.md
-
curl -L -o README.md https://huggingface.co/iky1e/DPDFNet4-CoreML/resolve/main/README.md
2.56 kB
| license: apache-2.0 | |
| library_name: coreml | |
| tags: | |
| - coreml | |
| - audio | |
| - speech-enhancement | |
| - noise-suppression | |
| - streaming | |
| - dpdfnet | |
| # DPDFNet-4 Core ML | |
| Stateful Core ML and MLX assets for **DPDFNet-4**, CEVA's 16 kHz real-time speech-enhancement model. This repository is the default DPDFNet-4 source for the [`DeepFilterNetCoreML`](https://github.com/kylehowells/DeepFilterNet-mlx) Swift product. | |
| ## Origin | |
| - Official implementation: [ceva-ip/DPDFNet](https://github.com/ceva-ip/DPDFNet) | |
| - Official models: [Ceva-IP/DPDFNet](https://huggingface.co/Ceva-IP/DPDFNet) | |
| - Paper: [DPDFNet](https://arxiv.org/abs/2512.16420) | |
| - Swift runtime and conversions: [kylehowells/DeepFilterNet-mlx](https://github.com/kylehowells/DeepFilterNet-mlx) | |
| - Conversion script: [`Scripts/Conversion/convert_dpdfnet_to_coreml.py`](https://github.com/kylehowells/DeepFilterNet-mlx/blob/feature/deepfilternet4/Scripts/Conversion/convert_dpdfnet_to_coreml.py) | |
| ## Runtime contract | |
| | Property | Value | | |
| |---|---:| | |
| | Sample rate | 16,000 Hz | | |
| | Input hop | 160 samples / 10 ms | | |
| | FFT | 320 samples | | |
| | DPRNN blocks | 4 | | |
| | Fixed algorithmic delay | 800 samples / 50 ms | | |
| ## Recommended model | |
| `DPDFNet4-Streaming-FP32.mlpackage` is the production default. Its conversion validation against the PyTorch graph produced 0.9999999999 output correlation. The FP16 explicit-state and resident-state variants are included for device-specific experiments but are not selected automatically because their fidelity is lower. | |
| Current 60-second Swift/Core ML validation: 13.953 seconds total (4.30x real time), with 0.99999999 waveform correlation to official ONNX. Live p50/p95 model processing latency was 3.686/4.171 ms on the development Apple Silicon Mac. Device results vary. | |
| ## Swift usage | |
| ```swift | |
| import DeepFilterNetCoreML | |
| let enhancer = try await DeepFilterNetCoreMLStreamer.load( | |
| configuration: .init(variant: .dpdfNet4) | |
| ) | |
| let output = try enhancer.processHop(input160Samples) | |
| ``` | |
| ## Files | |
| - `DPDFNet4-Streaming-FP32.mlpackage`: recommended explicit FP32 state graph. | |
| - `DPDFNet4-Streaming.mlpackage`: explicit FP16 state graph. | |
| - `DPDFNet4-Streaming-State.mlpackage`: Core ML `MLState` graph for supported OS versions. | |
| - `DPDFNet4-initial-state-f32.bin`: canonical recurrent-state initialization. | |
| - `config.json` and `model.safetensors`: matching Swift MLX/DSP model assets. | |
| - `conversion-report.json`: graph-level validation and measured conversion latency. | |
| ## License | |
| Apache-2.0, matching the official CEVA DPDFNet repository. See `LICENSE` and the original project. | |