Update README.md

README.md

@@ -1,5 +1,16 @@
-This model performs verbatim ASR. 
-It is trained to jointly perform verbatim ASR and automatic subtitling, after which the subtitle part has been discarded.
-It is trained on Flemish Dutch speech, and can be used with the standard ESPnet toolkit.
+---
+language:
+- nl
+---
+# Model
 
-Version: September 2023
+This repository contains the first version of our Automatic Speech Recognition and Subtitle Generation model, trained on 2000 hours of Flemish broadcast subtitled speech data. 
+It is converted to a simple ASR model, which outputs only a verbatim transcription.
+
+# Usage
+
+This repository only hosts the pre-trained model itself and the configuration files. 
+Using this model requires installation of the ESPnet toolkit, which you can find on Github [**here**](https://github.com/espnet/espnet).
+Th/espnete 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**: September 2023