Add scripts

deploy_model.sh

@@ -0,0 +1,35 @@
+#!/bin/bash
+
+# Deploy Myanmar Ghost model
+
+set -e
+
+echo "🚀 Starting model deployment..."
+
+# Parse arguments
+MODEL_PATH=${1:-"outputs/models/best_model.pt"}
+OUTPUT_DIR=${2:-"outputs/deployment"}
+FORMAT=${3:-"safetensors"}
+HUB_REPO=${4:-""}
+
+# Activate virtual environment if exists
+if [ -d "venv" ]; then
+    source venv/bin/activate
+fi
+
+# Install deployment dependencies
+pip install -q safetensors huggingface_hub
+
+# Run deployment pipeline
+python -m src.pipelines.deployment_pipeline \
+    --model_path "$MODEL_PATH" \
+    --output_dir "$OUTPUT_DIR" \
+    --format "$FORMAT" \
+    ${HUB_REPO:+--push_hub --repo_id "$HUB_REPO"}
+
+echo "✅ Deployment complete!"
+echo "Model exported to: $OUTPUT_DIR"
+
+if [ -n "$HUB_REPO" ]; then
+    echo "Pushed to: https://huggingface.co/$HUB_REPO"
+fi

download_sample_data.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+
+# Download sample data for Myanmar Ghost project
+
+set -e
+
+echo "📥 Downloading sample data..."
+
+# Create data directories
+mkdir -p data/raw/audio
+mkdir -p data/raw/transcripts
+mkdir -p data/processed
+
+# Download sample audio (placeholder - replace with actual URLs)
+# Example: wget -O data/raw/audio/sample.wav "https://example.com/sample.wav"
+
+# Create sample metadata
+cat > data/raw/metadata.csv << 'EOF'
+id,audio_file,transcript,sentiment
+utt_001,session_001/speaker_a.wav,မင်္ဂလာပါ,neutral
+utt_002,session_001/speaker_b.wav,ကျေးဇူးပါ,positive
+utt_003,session_002/speaker_a.wav,မကျေနပ်ပါဗျ,negative
+EOF
+
+# Download sample from HuggingFace datasets (if datasets is installed)
+if command -v python &> /dev/null; then
+    python -c "
+from datasets import load_dataset
+# Load a sample dataset
+print('Sample data structure created successfully')
+"
+fi
+
+echo "✅ Sample data downloaded to data/raw/"
+echo ""
+echo "Next steps:"
+echo "  1. Add your actual audio files to data/raw/audio/"
+echo "  2. Update transcripts in data/raw/metadata.csv"
+echo "  3. Run: bash scripts/run_data_pipeline.sh"

run_data_pipeline.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+# Run data processing pipeline
+
+set -e
+
+echo "🔄 Starting data processing pipeline..."
+
+# Activate virtual environment if exists
+if [ -d "venv" ]; then
+    source venv/bin/activate
+fi
+
+# Install dependencies if needed
+if [ -f "requirements.txt" ]; then
+    pip install -q -r requirements.txt
+fi
+
+# Run data pipeline
+python -m src.pipelines.data_pipeline \
+    --input data/raw/metadata.csv \
+    --output data/processed
+
+echo "✅ Data pipeline complete!"
+echo "Processed data saved to data/processed/"

run_federated_server.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+# Start Federated Learning Server
+
+set -e
+
+echo "🚀 Starting Federated Learning Server..."
+
+# Activate virtual environment if exists
+if [ -d "venv" ]; then
+    source venv/bin/activate
+fi
+
+# Default config
+CONFIG=${1:-configs/federated/server_config.yaml}
+
+# Start server
+python -m src.federated.server \
+    --config "$CONFIG" \
+    --address "[::]:8080" \
+    --rounds 5
+
+echo "✅ Federated server started on port 8080"