update readme

README.md

@@ -11,9 +11,17 @@ short_description: SmolVLM2 on llama.cpp
 sdk_version: 1.45.1
 ---
 
-# SmolVLM2 Live Inference Demo
+# SmolVLM2 Real‑Time Captioning Demo
 
-This HuggingFace Spaces demo runs SmolVLM2 2.2B, 500M, or 256M Instruct GGUF models on CPU using `llama-cpp-python` (v0.3.9) which builds `llama.cpp` under the hood, and Gradio v5.33.2 for the UI. It captures frames from your webcam every N milliseconds and performs live inference, displaying the model's response in real time.
+This Hugging Face Spaces app uses **Streamlit** + **WebRTC** to capture your webcam feed every *N* milliseconds and run it through the SmolVLM2 model on your CPU, displaying live captions below the video.
+
+## Features
+
+* **CPU‑only inference** via `llama-cpp-python` wrapping `llama.cpp`.
+* **WebRTC camera input** for low‑latency, browser‑native video streaming.
+* **Adjustable interval slider** (100 ms to 10 s) for capture frequency.
+* **Automatic GGUF model download** from Hugging Face Hub when missing.
+* **Debug logging** in the terminal for tracing inference steps.
 
 ## Setup
 
@@ -30,28 +38,38 @@ This HuggingFace Spaces demo runs SmolVLM2 2.2B, 500M, or 256M Instruct GGUF mod
    pip install -r requirements.txt
    ```
 
-3. **Add your GGUF models**
+3. **(Optional) Pre‑download model files**
+   The app automatically downloads these files if they are not present:
+
+   * `SmolVLM2-500M-Video-Instruct.Q4_K_M.gguf`
+   * `mmproj-SmolVLM2-500M-Video-Instruct-Q8_0.gguf`
+
+   To skip download, manually place them in the repo root.
+
+## Usage
 
-   Create a `models/` directory in the root of the repo and upload your `.gguf` files:
+1. **Launch the app**:
 
    ```bash
-   mkdir models
-   # then upload:
-   # - smolvlm2-2.2B-instruct.gguf
-   # - smolvlm2-500M-instruct.gguf
-   # - smolvlm2-256M-instruct.gguf
+   streamlit run app.py
    ```
 
-## Usage
+2. **Open your browser** at the URL shown (e.g. `http://localhost:8501`).
+
+3. **Allow webcam access** when prompted by the browser.
+
+4. **Adjust the capture interval** using the slider.
+
+5. **Click **Start** to begin streaming and captioning.**
+
+6. **View live captions** in the panel below the video.
+
+## File Structure
 
-- **Select Model**: Choose one of the `.gguf` files you uploaded.
-- **System Prompt**: Customize the system-level instructions for the model.
-- **User Prompt**: Provide the user query or instruction.
-- **Interval (ms)**: Set how often (in milliseconds) to capture a frame and run inference.
-- **Live Camera Feed**: The demo will start your webcam and capture frames at the specified interval.
-- **Model Output**: See the model’s response below the camera feed.
+* `app.py` — Main Streamlit + WebRTC application.
+* `requirements.txt` — Python dependencies.
+* `.gguf` model files (auto‑downloaded or user‑provided).
 
-## Notes
+## License
 
-- This demo runs entirely on CPU. Inference speed depends on the model size and your machine's CPU performance.
-- Make sure your browser has permission to access your webcam.
+Licensed under the MIT License.