Vocapia2Transcriber, Vocapia to Transcriber conversion macro
Location : “transcription” macro directory
Parameters
- vocapia file : process only one file
- vocapia directory : process the XML files of the directory
- result directory
- retokenize_words : true (false to keep vocapia tokenization)
Conversion rules : - Word ->w
-
stime ->time -
stime ->start -
etime ->end - all other attributes are transfered (conf, dur…)
-
fix tokenization for TXM “j’ai”>“j’” “ai”- see #3004, fixing quickly the tokenisation raises the same problems than tokenizing text. Hence, it is better to implement the re-tokenize import option
-
- AudioDoc ->Trans
- SpeakerList ->Speakers
- SegmentList ->Episode + Section
- SpeechSegment ->Turn
(from redmine: issue id 2997, created on 2021/01/19 by Matthieu Decorde)