Upload README.md with huggingface_hub

README.md

@@ -76,40 +76,66 @@ Compatible with various edge AI accelerators including:
 
 Download the complete training and deployment code from the **Files** tab:
 
+### Core Files
 - `dtln_ethos_u55.py` - Model architecture
-- `train_dtln.py` - Training script with quantization-aware training
+- `train_with_hf_datasets.py` - **NEW: Train with Hugging Face datasets (LibriSpeech, DNS Challenge, etc.)**
+- `train_dtln.py` - Training script with local audio files
 - `convert_to_tflite.py` - TFLite INT8 conversion
-- `alif_e7_voice_denoising_guide.md` - Complete deployment guide for edge devices
 - `example_usage.py` - Usage examples
-- `requirements.txt` - Python dependencies
+
+### Documentation
+- **`HF_TRAINING_GUIDE.md`** - **Complete guide for training with Hugging Face datasets**
+- `alif_e7_voice_denoising_guide.md` - Edge device deployment guide
+
+### Requirements
+- `training_requirements.txt` - Training dependencies (TensorFlow, datasets, etc.)
+- `requirements.txt` - Demo app dependencies
 
 ## 🛠️ Quick Start Guide
 
+### Option 1: Train with Hugging Face Datasets (Recommended)
+
 ```bash
-# 1. Install dependencies
-pip install -r requirements.txt
+# 1. Install training dependencies
+pip install -r training_requirements.txt
 
-# 2. Train model
-python train_dtln.py \
-    --clean-dir ./data/clean_speech \
-    --noise-dir ./data/noise \
+# 2. Train with LibriSpeech + DNS Challenge (automatic download)
+python train_with_hf_datasets.py \
     --epochs 50 \
     --batch-size 16 \
+    --samples-per-epoch 1000 \
     --lstm-units 128
 
 # 3. Convert to TFLite INT8
 python convert_to_tflite.py \
     --model ./models/best_model.h5 \
-    --output ./models/dtln_ethos_u55.tflite \
-    --calibration-dir ./data/clean_speech
-
-# 4. (Optional) Optimize for specific hardware accelerator
-# Example for Ethos-U55:
-vela \
-    --accelerator-config ethos-u55-256 \
-    --system-config Ethos_U55_High_End_Embedded \
-    --memory-mode Shared_Sram \
-    ./models/dtln_ethos_u55.tflite
+    --output ./models/dtln_int8.tflite
+```
+
+See **HF_TRAINING_GUIDE.md** for complete instructions with different datasets!
+
+### Option 2: Train with Local Audio Files
+
+```bash
+# 1. Prepare your data
+# data/
+# ├── clean_speech/*.wav
+# └── noise/*.wav
+
+# 2. Install dependencies
+pip install -r training_requirements.txt
+
+# 3. Train model
+python train_dtln.py \
+    --clean-dir ./data/clean_speech \
+    --noise-dir ./data/noise \
+    --epochs 50 \
+    --batch-size 16
+
+# 4. Convert to TFLite
+python convert_to_tflite.py \
+    --model ./models/best_model.h5 \
+    --output ./models/dtln_int8.tflite
 ```
 
 ## 🔧 Training Your Own Model