Update README.md

README.md

@@ -5,7 +5,7 @@ license: cc-by-nc-nd-4.0
 
 ## 🔍 Overview
 The **Vietnamese Streaming Speech-to-Text (ASR)** model is built on the **ZipFormer architecture with chunk size 16,32,64** — an improved variant of the Conformer — featuring only **30 million parameters** yet.  
-On CPU, the model can transcribe a **12-second audio clip in just 0.3 seconds**, significantly faster than most traditional ASR systems without requiring a GPU.
+On CPU, the model can transcribe a **1-second audio chunk in just 0.05 seconds**, designed for streaming-based tasks with low latency requirements.
 
 ---
 
@@ -67,8 +67,8 @@ Comprehensive details about **training data**, **optimization strategies**, **ar
 
 | **Device** | **Audio Length** | **Inference Time** |
 |-------------|------------------|--------------------|
-| CPU (Hugging Face Basic) | 12 seconds | **0.3 s** |
-| GPU (RTX 3090) | 12 seconds | **< 0.1 s** |
+| CPU (Hugging Face Basic) | 1 seconds audio chunk | **0.05 s** |
+| GPU (RTX 3090) | 1 seconds audio chunk | **< 0.01 s** |
 
 ---