deanna-emery commited on
Commit
906dedd
·
1 Parent(s): 788178f
Files changed (1) hide show
  1. app.py +5 -2
app.py CHANGED
@@ -77,11 +77,14 @@ def translate(video_file, true_caption=None):
77
  title = "American Sign Language Translation: An Approach Combining MoViNets and T5"
78
 
79
  description = """
80
- This application surfaces a model for translation of American Sign Language (ASL).
81
  The model comprises of a fine-tuned MoViNet CNN model to generate video embeddings and a T5 encoder-decoder model
82
  to generate translations from the video embeddings. This model architecture achieves a BLEU score of 1.98
83
  and an average cosine similarity score of 0.21 when trained and evaluated on the YouTube-ASL dataset.
84
- 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>.
 
 
 
85
 
86
  A limitation of this architecture is the size of the MoViNets model, making it especially slow during inference on a CPU.
87
  We do not recommend uploading videos longer than 4 seconds as the video embedding generation may take some time.
 
77
  title = "American Sign Language Translation: An Approach Combining MoViNets and T5"
78
 
79
  description = """
80
+ This application hosts a model for translation of American Sign Language (ASL).
81
  The model comprises of a fine-tuned MoViNet CNN model to generate video embeddings and a T5 encoder-decoder model
82
  to generate translations from the video embeddings. This model architecture achieves a BLEU score of 1.98
83
  and an average cosine similarity score of 0.21 when trained and evaluated on the YouTube-ASL dataset.
84
+ More information about the model training and instructions to download the models
85
+ can be found in our <a href=https://github.com/deanna-emery/ASL-Translator>GitHub repository</a>.
86
+ You can also find a overview of the project approach
87
+ <a href=https://www.ischool.berkeley.edu/projects/2023/signsense-american-sign-language-translation>here/a>.
88
 
89
  A limitation of this architecture is the size of the MoViNets model, making it especially slow during inference on a CPU.
90
  We do not recommend uploading videos longer than 4 seconds as the video embedding generation may take some time.