updates

app.py

@@ -55,7 +55,7 @@ def preprocess(filename, max_frames=0, resize=(224,224)):
     video = np.expand_dims(video, axis=0)
     return video
 
-def translate(video_file, text):
+def translate(video_file, text=None):
 
     video = preprocess(video_file, max_frames=0, resize=(224,224))
 
@@ -82,7 +82,7 @@ This application surfaces a model for translation of American Sign Language (ASL
 which comprises of a fine-tuned MoViNets CNN model and a T5 encoder-decoder model 
 to generate translations from the video embeddings. This model architecture achieves a BLEU score of 1.98 
 and an average cosine similarity score of 0.21 when trained and evaluated on the YouTube-ASL dataset. 
-More information about the models can be found in our GitHub repository <a href=https://github.com/deanna-emery/ASL-Translator>here</a>.
+More information about the model training and instructions to download the models can be found in our GitHub repository <a href=https://github.com/deanna-emery/ASL-Translator>here</a>.
 
 A limitation of this architecture is the size of the MoViNets model, making it especially slow during inference on a CPU. 
 We do not recommend uploading videos longer than 4 seconds as the video embedding generation may take some time. 
@@ -108,7 +108,7 @@ article =  """The captions for the example videos are as follows in order: \n
 
 # Gradio App interface
 gr.Interface(fn=translate,
-              inputs=gr.Video(label='Video', show_label=True, max_length=10), 
+              inputs=[gr.Video(label='Video', show_label=True, max_length=10, sources='upload'), 'text'], 
               outputs="text",
               allow_flagging="never",
               title=title,