Code for voicing silent speech from EMG. Official repository for the papers "Digital Voicing of Silent Speech" at EMNLP 2020 and "An Improved Model for Voicing Silent Speech" at ACL 2021. Also includes code for converting silent speech to text.
Thanks for your contribution!I‘m a beginner for the research of EMG to Speech. Could you tell me something about the chunks in the info.json? I noticed it’s used in batch_length, but I don't know what's chunks and its source in data collection. Looking forward to your reply very much.
when I run this command in colab : python recognition_model.py --evaluate_saved "./models/recognition_model/model.pt",
it reported the error : [ctcdecode/src/scorer.cpp:57] FATAL: "(access(filename, 0)) == (0)" check failed. Invalid language model path;
I can`t find any about this error.
when I run this command : python recognition_model.py --output_directory "./models/recognition_model/"
it reported the error : raise ValueError("one or more references are empty strings"), ValueError: one or more references are empty strings