Update README.md

README.md

@@ -15,9 +15,9 @@ This vits model was trained on the [KTH/hungarian-single-speaker-tts](https://hu
 The corpus consists of a single speaker, with 4515 segments extracted from [this](https://librivox.org/egri-csillagok-by-geza-gardonyi/) single LibriVox audiobook. It consists about 10 hours of audio data.
 
 ## Training
-The model was trained on a single RTX 3090 GPU. The training took about 1 day for the first checkpoint (Step 93000).
-Based on the quality of the preview model, we are aiming for 250K Steps.
+The model was trained on a single RTX 3090 GPU for 3 days, 200K steps with a batchsize of 16. 
+We saved some checkpoints with the optimizers, so the model could be train further, however we didn't notice any noticable effect after step 150K. 
 
 ## Usage
-The model can be used with [JayWalnut's git repo](https://github.com/jaywalnut310/vits), but you have to modify the `text/cleaners.py` file to contain our `hungarian_cleaners` method.
+The model `diana_final.pth` can be used with [JayWalnut's git repo](https://github.com/jaywalnut310/vits), but you have to modify the `text/cleaners.py` file to contain our `hungarian_cleaners` method.
 We provided the necessary files in our repo to do so.