update files

app.py

@@ -11,7 +11,7 @@ DESCRIPTION='''
 OWSM is an Open Whisper-style Speech Model from [CMU WAVLab](https://www.wavlab.org/).
 It reproduces Whisper-style training using publicly available data and an open-source toolkit [ESPnet](https://github.com/espnet/espnet).
 
-OWSM v3 is trained on 180k hours of paired speech data. It supports various speech-to-text tasks:
+OWSM v3 has 889M parameters and is trained on 180k hours of paired speech data. It supports various speech-to-text tasks:
 - Speech recognition for 151 languages
 - Any-to-any language speech translation
 - Timestamp prediction
@@ -20,6 +20,8 @@ OWSM v3 is trained on 180k hours of paired speech data. It supports various spee
 
 For more details, please check out our [paper](https://arxiv.org/abs/2309.13876) (Peng et al., ASRU 2023).
 
+We also have a [Colab demo](https://colab.research.google.com/drive/1zKI3ZY_OtZd6YmVeED6Cxy1QwT1mqv9O?usp=sharing) where you can use a free GPU.
+
 ```
 @article{peng2023owsm,
   title={Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data},

requirements.txt

@@ -1,4 +1,3 @@
 torch==2.1.0
 torchaudio
 espnet @ git+https://github.com/espnet/espnet@d3254133c595ea8271072ee49a1b4ceb3ed4fd7a
-espnet_model_zoo