Update README.md

README.md

@@ -1,3 +1,4 @@
+# Custom Node for ComfyUI
 ---
 license: apache-2.0
 pipeline_tag: audio-to-audio
@@ -11,11 +12,24 @@ tags:
 
 This is the model for NovaSR, a tiny 50kb audio upsampling model that upscales muffled 16khz audio into clear and crisp 48khz audio at speeds from 100-3500x realtime.
 
+### Audio Samples
 
-![image](https://cdn-uploads.huggingface.co/production/uploads/63473b59e5c0717e6737b872/43tQTMGNSgD3ABnabat44.png)
+**Before Processing (16kHz):**
+<audio controls>
+  <source src="samples/speech_sample_before.mp3" type="audio/mpeg">
+  Your browser does not support the audio element.
+</audio>
+
+**After Processing (48kHz):**
+<audio controls>
+  <source src="samples/speech_sample_after.mp3" type="audio/mpeg">
+  Your browser does not support the audio element.
+</audio>
 
+![image](https://cdn-uploads.huggingface.co/production/uploads/63473b59e5c0717e6737b872/43tQTMGNSgD3ABnabat44.png)
 
 ### Details
+
 * **Model Size:** 52kb for pytorch version
 * **Input Rate:** 16kHz
 * **Output Rate:** 48kHz
@@ -23,6 +37,7 @@ This is the model for NovaSR, a tiny 50kb audio upsampling model that upscales m
 * **Mono**
 
 ## Comparisons
+
 Comparisons were done on A100 gpu. Higher realtime means faster processing speeds.
 Comparison on CPU are coming soon.
 
@@ -40,4 +55,5 @@ Please check out the github repo for usage: https://github.com/Saganaki22/ComfyU
 Original Repo: https://github.com/ysharma3501/NovaSR
 
 If you find the model/code helpful, stars or likes would be appreciated.
+
 Thank you.