Rename OSt files to e.g. "raw-revised-transcript" (@pyRis)
Process the files with our segmenter (@pyRis), saving them as OSt.
Have the OSt files manually revised by 'exotic annotators' (@srdecny), they should directly save the outputs here, they can even edit in place. The correction will primarily affect the segmentation and casing, because the words themselves are probably already revised from the past.
The Czech ASR transcripts that Jonas used were not properly cased and segmented. This concerns all the subdirectories of: https://github.com/ELITR/elitr-testset/tree/master/documents/czech-asr
Please: