|
Download README.md from Ceva-IP/DPDFNet: direct link, hf CLI and curl.
- Browser
- Download file 4.97 kB
-
https://huggingface.co/Ceva-IP/DPDFNet/resolve/main/README.md
- Command line
-
hf download hf://Ceva-IP/DPDFNet/README.md
-
curl -L -o README.md https://huggingface.co/Ceva-IP/DPDFNet/resolve/main/README.md
4.97 kB
| license: apache-2.0 | |
| pipeline_tag: audio-to-audio | |
| tags: | |
| - speech_enhancement | |
| - noise_suppression | |
| - real_time | |
| - streaming | |
| - causal | |
| - onnx | |
| - tflite | |
| - fullband | |
| # DPDFNet | |
| DPDFNet is a family of **causal, single‑channel** speech enhancement models for **real‑time noise suppression**.\ | |
| It builds on **DeepFilterNet2** by adding **Dual‑Path RNN (DPRNN)** blocks in the encoder for stronger long‑range modeling while staying streaming‑friendly. | |
| **Links** | |
| - Project page (audio samples + architecture): https://ceva-ip.github.io/DPDFNet/ | |
| - Paper (arXiv): https://arxiv.org/abs/2512.16420 | |
| - Code (GitHub): https://github.com/ceva-ip/DPDFNet | |
| - Demo Space: https://huggingface.co/spaces/Ceva-IP/DPDFNetDemo | |
| - Evaluation set: https://huggingface.co/datasets/Ceva-IP/DPDFNet_EvalSet | |
| --- | |
| ## What’s in this repo | |
| - **TFLite**: `*.tflite` (root) | |
| - **ONNX**: `onnx/*.onnx` | |
| - **PyTorch checkpoints**: `checkpoints/*.pth` | |
| --- | |
| ## Model variants | |
| ### 8 kHz narrowband model | |
| | Model | DPRNN blocks | Params (M) | MACs (G) | | |
| |---|:---:|:---:|:---:| | |
| | `dpdfnet2_8khz` | 2 | 2.51 | 1.29 | | |
| | `dpdfnet8_8khz` | 8 | 3.56 | 3.99 | | |
| ### 16 kHz wideband models | |
| | Model | DPRNN blocks | Params (M) | MACs (G) | | |
| |---|:---:|:---:|:---:| | |
| | `baseline` | 0 | 2.31 | 0.36 | | |
| | `dpdfnet2` | 2 | 2.49 | 1.35 | | |
| | `dpdfnet4` | 4 | 2.84 | 2.36 | | |
| | `dpdfnet8` | 8 | 3.54 | 4.37 | | |
| ### 48 kHz fullband model | |
| | Model | DPRNN blocks | Params (M) | MACs (G) | | |
| |---|:---:|:---:|:---:| | |
| | `dpdfnet2_48khz_hr` | 2 | 2.58 | 2.42 | | |
| | `dpdfnet8_48khz_hr` | 8 | 3.63 | 7.17 | | |
| --- | |
| ## Recommended inference (CPU-only, ONNX) | |
| ```bash | |
| pip install dpdfnet | |
| ``` | |
| ### CLI | |
| ```bash | |
| # Enhance one file | |
| dpdfnet enhance noisy.wav enhanced.wav --model dpdfnet4 | |
| # Enhance a directory (uses all CPU cores by default) | |
| dpdfnet enhance-dir ./noisy_wavs ./enhanced_wavs --model dpdfnet2 | |
| # Enhance a directory with a fixed worker count | |
| dpdfnet enhance-dir ./noisy_wavs ./enhanced_wavs --model dpdfnet2 --workers 4 | |
| # Download models | |
| dpdfnet download | |
| dpdfnet download dpdfnet8 | |
| dpdfnet download dpdfnet4 --force | |
| ``` | |
| ### Python API | |
| ```python | |
| import soundfile as sf | |
| import dpdfnet | |
| # In-memory enhancement: | |
| audio, sr = sf.read("noisy.wav") | |
| enhanced = dpdfnet.enhance(audio, sample_rate=sr, model="dpdfnet4") | |
| sf.write("enhanced.wav", enhanced, sr) | |
| # Enhance one file: | |
| out_path = dpdfnet.enhance_file("noisy.wav", model="dpdfnet2") | |
| print(out_path) | |
| # Model listing: | |
| for row in dpdfnet.available_models(): | |
| print(row["name"], row["ready"], row["cached"]) | |
| # Download models: | |
| dpdfnet.download() # All models | |
| dpdfnet.download("dpdfnet4") # Specific model | |
| ``` | |
| ### Real-time Microphone Enhancement | |
| Install `sounddevice` (not included in `dpdfnet` dependencies): | |
| ```bash | |
| pip install sounddevice | |
| ``` | |
| `StreamEnhancer` processes audio chunk-by-chunk, preserving RNN state across | |
| calls. Any chunk size works; enhanced samples are returned as soon as enough | |
| data has accumulated for the first model frame (20 ms). | |
| ```python | |
| import numpy as np | |
| import sounddevice as sd | |
| import dpdfnet | |
| INPUT_SR = 48000 | |
| # Use one model hop (10 ms) as the block size so process() returns | |
| # exactly one hop's worth of enhanced audio on every callback. | |
| BLOCK_SIZE = int(INPUT_SR * 0.010) # 480 samples at 48 kHz | |
| enhancer = dpdfnet.StreamEnhancer(model="dpdfnet2_48khz_hr") | |
| def callback(indata, outdata, frames, time, status): | |
| mono_in = indata[:, 0] if indata.ndim > 1 else indata.ravel() | |
| enhanced = enhancer.process(mono_in, sample_rate=INPUT_SR) | |
| n = min(len(enhanced), frames) | |
| outdata[:n, 0] = enhanced[:n] | |
| if n < frames: | |
| outdata[n:] = 0.0 # silence while the first window accumulates | |
| with sd.Stream( | |
| samplerate=INPUT_SR, | |
| blocksize=BLOCK_SIZE, | |
| channels=1, | |
| dtype="float32", | |
| callback=callback, | |
| ): | |
| print("Enhancing microphone input - press Ctrl+C to stop") | |
| try: | |
| while True: | |
| sd.sleep(100) | |
| except KeyboardInterrupt: | |
| pass | |
| # Optional: drain the final partial window at the end of a recording | |
| tail = enhancer.flush() | |
| ``` | |
| > [!NOTE] | |
| > **Latency** | |
| > The first enhanced output arrives after one full model window (~20 ms) has been buffered. All subsequent blocks are returned with ~10 ms additional delay. | |
| > | |
| > **Sample rate** | |
| > `StreamEnhancer` resamples internally. Pass your device's native rate as `sample_rate`; the return value is at the same rate. | |
| > | |
| > **Block size** | |
| > Using `BLOCK_SIZE = int(SR * 0.010)` (one model hop) gives one enhanced block per callback. Other sizes also work but may produce empty returns while the buffer fills. | |
| > | |
| > **Multiple streams** | |
| > Create a separate `StreamEnhancer` per stream. Call `enhancer.reset()` between independent audio segments to clear RNN state. | |
| --- | |
| ## Citation | |
| ```bibtex | |
| @article{rika2025dpdfnet, | |
| title = {DPDFNet: Boosting DeepFilterNet2 via Dual-Path RNN}, | |
| author = {Rika, Daniel and Sapir, Nino and Gus, Ido}, | |
| year = {2025} | |
| } | |
| ``` | |
| --- | |
| ## License | |
| Apache-2.0 | |