Update README.md

README.md

@@ -5,39 +5,53 @@ tags:
   - speech_enhancement
   - noise_suppression
   - real_time
+  - fullband
 ---
 
 
 # DPDFNet: Boosting DeepFilterNet2 via Dual-Path RNN
 
-DPDFNet is a family of causal, single-channel speech enhancement models for real-time noise suppression in challenging everyday environments. It extends the DeepFilterNet2 enhancement framework by inserting Dual-Path RNN (DPRNN) blocks into the encoder, strengthening long-range temporal and cross-band modeling while preserving a compact, streaming-friendly design. 
+DPDFNet is a family of causal, single-channel speech enhancement models for real-time noise suppression in challenging everyday environments. It extends the DeepFilterNet2 enhancement framework by inserting Dual-Path RNN (DPRNN) blocks into the encoder, strengthening long-range temporal and cross-band modeling while preserving a compact, streaming-friendly design.
 
-This repository provides four TensorFlow Lite (TFLite) models optimized for mobile and edge deployment:
+This repository provides TensorFlow Lite (TFLite) models optimized for mobile and edge deployment:
 
+**16kHz models**
 * `baseline.tflite`
 * `dpdfnet2.tflite`
 * `dpdfnet4.tflite`
 * `dpdfnet8.tflite`
 
+**48kHz model**
+* `dpdfnet2_48khz_hr.tflite`
+
 ---
 
 ## Key Features
 
-* Causal and low-latency: Designed for streaming use cases such as telephony, conferencing, and embedded devices. 
-* Dual-Path RNN integration: Improves temporal context and frequency-domain interactions for more robust enhancement in difficult noise conditions. 
+* Causal and low-latency: Designed for streaming use cases such as telephony, conferencing, and embedded devices.
+* Dual-Path RNN integration: Improves temporal context and frequency-domain interactions for more robust enhancement in difficult noise conditions.
 * Scalable family: Choose baseline or dpdfnet2/4/8 to balance quality vs. compute.
-* Edge deployment focus: Demonstrated on Ceva NeuPro Nano NPUs in the accompanying work. 
+* Edge deployment focus: Demonstrated on Ceva NeuPro Nano NPUs in the accompanying work.
+* Fullband option: A dedicated 48kHz model is provided for fullband enhancement.
 
 ---
 
 ## Model Variants and Footprint
 
+### 16kHz models
+
 | Model     | Params [M] | MACs [G] | TFLite Size [MB] |
-| --------- | ---------: | -------: | ---------------: |
-| Baseline  |       2.31 |     0.36 |              8.5 |
-| DPDFNet-2 |       2.49 |     1.35 |             10.7 |
-| DPDFNet-4 |       2.84 |     2.36 |             12.9 |
-| DPDFNet-8 |       3.54 |     4.37 |             17.2 |
+| --------- | :--------: | :------: | :--------------: |
+| Baseline  |    2.31    |   0.36   |       8.5        |
+| DPDFNet-2 |    2.49    |   1.35   |      10.7        |
+| DPDFNet-4 |    2.84    |   2.36   |      12.9        |
+| DPDFNet-8 |    3.54    |   4.37   |      17.2        |
+
+### 48kHz model
+
+| Model        | Params [M] | MACs [G] | TFLite Size [MB] |
+| ------------ | :--------: | :------: | :--------------: |
+| DPDFNet-2 HR |    2.58    |   2.42   |      11.6        |
 
 ---
 
@@ -49,8 +63,12 @@ Deployment targets: Mobile devices, embedded NPUs, and edge platforms.
 
 Input and Output:
 
-* Input: 16 kHz mono noisy speech waveform
-* Output: 16 kHz mono enhanced speech waveform
+* **16kHz models**
+  * Input: 16kHz mono noisy speech waveform
+  * Output: 16kHz mono enhanced speech waveform
+* **48kHz model**
+  * Input: 48kHz mono noisy speech waveform
+  * Output: 48kHz mono enhanced speech waveform
 
 Typical applications:
 
@@ -63,7 +81,9 @@ Typical applications:
 
 ## Inference
 
-This repo includes a reference script for running the TFLite models on WAV files using streaming-style, frame-by-frame inference: `run_tflite.py`. 
+This repo includes a inference script for running the TFLite models on WAV files using streaming-style, frame-by-frame inference: `run_tflite.py`.
+
+> **Note:** When using `dpdfnet2_48khz_hr`, the inference script automatically switches to the 48kHz processing pipeline.
 
 ### Setup
 
@@ -78,7 +98,7 @@ pip install tflite-runtime
 
 By default, the script loads models from:
 
-* `./<model_name>.tflite` 
+* `./<model_name>.tflite`
 
 Create the folder and place the `.tflite` files there (or edit `TFLITE_DIR` in the script to match your layout).
 
@@ -90,7 +110,7 @@ The script processes `*.wav` files non-recursively and writes enhanced outputs a
 python run_tflite.py --noisy_dir /path/to/noisy_wavs --enhanced_dir /path/to/out --model_name dpdfnet8
 ```
 
-Available `--model_name` options: `baseline`, `dpdfnet2`, `dpdfnet4`, `dpdfnet8`. 
+Available `--model_name` options: `baseline`, `dpdfnet2`, `dpdfnet4`, `dpdfnet8`, `dpdfnet2_48khz_hr`.
 
 ---