ML4Audio - pyctcdecode: A simple and fast speech-to-text prediction decoding algorithm

This week the Kensho team will join us to talk about pyctcdecode pyctcdecode is a fast and feature-rich CTC beam search decoder for speech recognition. Ask your questions in https://discuss.huggingface.co/t/ml-for-audio-study-group-pyctcdecode-jan-18/13561 Speakers - Raymond Grossman: Raymond works as a machine learning engineer at Kensho Technologies, specializing in speech and natural language domains. Prior to coming to Kensho, he studied mathematics at Princeton and was an avid Kaggler under the moniker @ToTrainThemIsMyCause. LinkedIn: https://www.linkedin.com/in/raymond-grossman-bb4664114/ - Jeremy Lopez: Jeremy is a machine learning engineer at Kensho Technologies and has worked on a variety of different topics including search and speech recognition. Before working at Kensho, he earned a PhD in experimental particle physics at MIT and continued doing physics research as a postdoc at the University of Colorado Boulder. LinkedIn: https://www.linkedin.com/in/jeremy-lopez-9107b613a/ - Join the discussion at Discord (http://hf.co/join/discord #ml-4-audio-study-group channel). - Check the GitHub repo of pyctcdecode (https://github.com/kensho-technologies/pyctcdecode) - Check out the GitHub repository of the study group (https://github.com/Vaibhavs10/ml-with-audio) Some resources to jump ahead: - https://towardsdatascience.com/beam-search-decoding-in-ctc-trained-neural-networks-5a889a3d85a7 - https://blog.kensho.com/pyctcdecode-a-new-beam-search-decoder-for-ctc-speech-recognition-2be3863afa96