string update in app

infer_onnx.py

@@ -198,11 +198,15 @@ title = """
 
 description = """
  
-🍵 Matcha-TTS, a new approach to non-autoregressive neural TTS, that uses conditional flow matching (similar to rectified flows) to speed up ODE-based speech synthesis
+🍵 Matxa és un model TTS multilocutor multidialectal que utilitza 🥑  alVoCat com a vocoder. Es basen en arquitectures Matcha-TTS i Vocos.
 
-For vocoders we use [Vocos](https://huggingface.co/BSC-LT/vocos-mel-22khz-cat) trained in a catalan set of ~28 hours.
+Podeu provar les veus a continuació i saber els detalls tècnics a la pestanya "Informació".
 
-[Matcha](https://huggingface.co/BSC-LT/matcha-tts-cat-multispeaker) was trained using openslr69 and festcat datasets
+----
+
+🍵 Matxa is a multispeaker multidialect TTS model which uses 🥑 alVoCat as a vocoder. They are based on Matcha-TTS and Vocos architectures. 
+
+You can synthesize test sentences below and check the technical details in the "About" tab.
 
 """