Update README.md

README.md

@@ -1,11 +1,37 @@
 ---
-license: cc-by-4.0
+license: apache-2.0
 pipeline_tag: audio-to-audio
 tags:
 - pytorch
 - audio
 - upsampling
 ---
+# FlashSR
 
+FlashSR is a 2MB audio super-resolution model based on the HierSpeech++ architecture. It upscales 16kHz audio to 48kHz at speeds ranging from 200x to 400x real-time.
 
-This is a high quality and incredibly fast audio upsampler. It upscales audio from 16khz to 48khz rapidly, far exceeding speeds of alternatives such as resemble-enhance/clearervoice and reaching above 120x realtime on consumer gpus.
+### Details
+* **Model Size:** 2MB
+* **Input Rate:** 16kHz
+* **Output Rate:** 48kHz
+* **Inference Speed:** 200x - 400x real-time depending on gpu and dtype
+
+### Performance Summary
+FlashSR is designed for high-speed frequency reconstruction. It offers a significantly lower computational footprint compared to alternatives such as Resemble-Enhance and ClearerVoice, while maintaining similar output quality.
+
+
+
+### Benchmark Comparison
+
+| Model | Speed | Size |
+| :--- | :--- | :--- |
+| **FlashSR** | **200x - 400x realtime** | **2MB** |
+| Resemble-Enhance | < 20x realtime | ~700MB+ |
+| ClearerVoice | < 20x realtime | ~200MB+ |
+
+### Usage
+Usage instructions and source code are available on GitHub:
+https://github.com/ysharma3501/FlashSR
+
+### Credits
+Thanks to the authors of **HierSpeech++** as this was based on it's 48khz upsampler.