Update README: correct progressive update interval to 500ms

README.md

@@ -26,7 +26,7 @@ Real-time speech recognition with smart progressive streaming, powered by **Para
 - **⚡ Smart Progressive Streaming**: Intelligent window management with sentence-aware boundaries
   - Growing window (0-15s) for accuracy
   - Sentence-aware sliding window (>15s) to maintain context
-  - Real-time updates every 250ms
+  - Real-time updates every 500ms
 
 - **🔒 Privacy-First**: All processing happens locally in your browser - no data sent to servers
 
@@ -62,7 +62,7 @@ This demo implements the smart progressive streaming algorithm from the [speech-
 
 1. **Growing Window (0-15s)**:
    - Accumulates audio for better accuracy
-   - Re-transcribes entire buffer every 250ms
+   - Re-transcribes entire buffer every 500ms
 
 2. **Sliding Window (>15s)**:
    - Locks completed sentences as "fixed"
@@ -78,7 +78,7 @@ Web Audio API (16kHz)
      ↓
 Audio Processor (accumulate chunks)
      ↓
-Progressive Streaming Handler (250ms updates)
+Progressive Streaming Handler (500ms updates)
      ↓
 Web Worker → Parakeet ONNX Model (via parakeet.js + WebGPU)
      ↓
@@ -106,7 +106,7 @@ Transcription Display (yellow fixed + cyan active)
 ## Performance
 
 - **First result**: <500ms latency
-- **Progressive updates**: 250ms cadence
+- **Progressive updates**: 500ms cadence
 - **RTF (Real-time Factor)**: ~0.3-0.5x with WebGPU
 - **Model loading**: 1-2 minutes (one-time, cached locally)