doc: update screenshot table

Author: fumiama

README.md

@@ -27,11 +27,13 @@ An easy-to-use voice conversion framework based on VITS.
 
 > There's a [one-click downloader](https://github.com/fumiama/RVC-Models-Downloader) for models/integration packages/tools. Welcome to try.
 
-| Training and inference Webui | Real-time voice changing GUI |
-| :--------: | :---------: |
-| ![web](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/assets/129054828/092e5c12-0d49-4168-a590-0b0ef6a4f630) | ![realtime-gui](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/assets/41315874/95b36866-b92d-40c7-b5db-6a35ca5caeac) |
-| go-web.bat | go-realtime-gui.bat |
-| You can freely choose the action you want to perform. | We have achieved an end-to-end latency of 170ms. With the use of ASIO input and output devices, we have managed to achieve an end-to-end latency of 90ms, but it is highly dependent on hardware driver support. |
+| Training and inference Webui |
+| :--------: |
+| ![web](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/assets/41315874/17e48404-2627-4fad-a0ec-65f9065aeade) |
+
+| Real-time voice changing GUI |
+| :---------: |
+| ![realtime-gui](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/assets/41315874/95b36866-b92d-40c7-b5db-6a35ca5caeac) |
 
 ## Features:
 + Reduce tone leakage by replacing the source feature to training-set feature using top1 retrieval;