Update README.md

Fixed the description of the preprocessing and added acknowledgment.
mattiadg · Apr 12, 2020 · 66b4d0f · 66b4d0f
1 parent 2d15240
commit 66b4d0f
Showing 1 changed file with 4 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -44,7 44,7 @@ bash FBK-fairseq-st/scripts/word_level2char_level.sh $INPUT_FILE.tok
 As of now, the only supported audio format are *.npz* and *.h5*.
 
 ```
-python preprocess.py -s <audio_format> -t fr --format <h5 | npz> --inputtype audio \
 python preprocess.py -s <source_language> -t <target_language> --format <h5 | npz> --inputtype audio \
  --trainpref <path_to_train_data> [[--validpref <path_to_validation_data>] \
  [--testpref <path_to_test_data>]] --destdir <path to output folder>
 ```
@@ -195,6 195,9 @@ If you use this software for your research, then please cite it as:
 }
 ```
 
 ## Acknowledgment
 This codebase is part of a project financially supported by an Amazon ML Grant.
 
 ======================================
 
 The following was the official fairseq-py documentation when we began developing FBK-fairseq (August 2018)