Update README.md

README.md

@@ -1,4 +1,20 @@
-This model can perform both verbatim ASR and automatic subtitling. It outputs both modalities with separate decoders.
-It is trained on Flemish Dutch speech, and should be used with the subtitle branch of the ESPnet toolkit (https://github.com/nelfproject/ASR_espnet).
+---
+language:
+- nl
+library_name: espnet
+pipeline_tag: automatic-speech-recognition
+---
+
+# Model
+
+This repository contains the second version of our Automatic Speech Recognition and Subtitle Generation model, with improved architecture and trained on 14000 hours of Flemish broadcast subtitled speech data. 
+It can generate both an exact verbatim transcription with annotation tags as well as a fully formatted and cleaned up subtitle transcription.
+It outputs both modalities with separate decoders.
+
+This repository only hosts the pre-trained model itself and the configuration files. 
+Using this model requires installation of our Flemish Speech&Subtitling branch of the ESPnet toolkit, which you can find on Github [**here**](https://github.com/nelfproject/ASR_espnet_v2).
+The Github page will contain all further details to use the model. To download the model, see the instructions [here](https://huggingface.co/docs/hub/models-downloading).
+
+
 
 Version: April 2024