Television News Visual Explorer: ASR Of All Uncaptioned Broadcasts 2001-Present Complete

We are excited today to announce that we have completed machine transcription of every single uncaptioned broadcast in the entire TV News Archive's 2001-present history, including all broadcasts from traditionally captioned channels that for any reason lacked captioning. In all, 5.15 million broadcasts from 237 different channels totaling 10.2 billion seconds (171M minutes / 2.85M hours) were ASR'd through GCP's state-of-the-art LSM Chirp, resulting in 17 billion words over 93.8 billion characters totaling 93.9GB of transcription text. We believe this is one of the largest global multilingual applications of LSM ASR to worldwide television news ever performed and we are immensely excited to begin exploring how this vast new transcription archive can help journalists and scholars understand our global world over the past quarter century.