Update to include better recognizer model for dictation

README.md

@@ -3,7 +3,7 @@
 ## Setup
 
 1. Setup a Virtual Audio Cable like [VB-Cable](https://vb-audio.com/Cable/).
-2. For Vosk Recognition, you will need a model, many can be found [here](https://alphacephei.com/vosk/models), I would recommend the [vosk-model-small-en-us](https://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip).
+2. For Vosk Recognition, you will need a model, many can be found [here](https://alphacephei.com/vosk/models), I would recommend the [vosk-model-small-en-us](https://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip) for those with lower tier GPUs, or the [vosk-model-en-us-daanzu-20200905-lgraph](https://alphacephei.com/vosk/models/vosk-model-en-us-daanzu-20200905-lgraph.zip) for those with a slightly above average GPU. Overall, I would recommend the l-graph over the small due to better dictation, but try different models and see what works best for you.
 3. Extract the downloaded Vosk model (preferably to the same directory as `STTTS`).
 3. Open whatever application you wish to use `STTTS` with, and set the Input device/Microphone to the `CABLE Output` device (for CB-Cable).
 4. Download and extract the latest version from [here](https://github.com/krogenth/STTTS/releases).