Skip to content

Commit 5955720

Browse files
committed
new batch for annotation + bugfix: matching also *_anonym_video* files
1 parent 3ee2c14 commit 5955720

File tree

2 files changed

+85
-1
lines changed

2 files changed

+85
-1
lines changed

data_preparation/distribute_to_annotators/Makefile

+84
Original file line numberDiff line numberDiff line change
@@ -317,6 +317,90 @@ distrib_2024-10-04 :
317317
SELECTION_RULE='$$$$((i+1+39))' \
318318
TRANSCRIPT_TYPE=from_scratch
319319

320+
distrib_2025-01-31 :
321+
make distribute \
322+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
323+
SRC_DIR=03.auto_transcripts/null \
324+
SRC_FILES=B1ML_23*.xml \
325+
TGT_DIR=05.for_annotators/2025-01-31 \
326+
ANNOTATORS="AP ET KV LR ZM" \
327+
SELECTION_RULE='$$$$((i+1))' \
328+
TRANSCRIPT_TYPE=from_scratch
329+
make distribute \
330+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
331+
SRC_DIR=03.auto_transcripts/null \
332+
SRC_FILES=B1ML_23*.xml \
333+
TGT_DIR=05.for_annotators/2025-01-31 \
334+
ANNOTATORS="AP ET KV LR ZM" \
335+
SELECTION_RULE='$$$$((i+1+5))' \
336+
TRANSCRIPT_TYPE=from_scratch
337+
make distribute \
338+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
339+
SRC_DIR=03.auto_transcripts/null \
340+
SRC_FILES=B1ML_23*.xml \
341+
TGT_DIR=05.for_annotators/2025-01-31 \
342+
ANNOTATORS="AP ET KV LR ZM" \
343+
SELECTION_RULE='$$$$((i+1+10))' \
344+
TRANSCRIPT_TYPE=from_scratch
345+
make distribute \
346+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
347+
SRC_DIR=03.auto_transcripts/null \
348+
SRC_FILES=B1ML_23*.xml \
349+
TGT_DIR=05.for_annotators/2025-01-31 \
350+
ANNOTATORS="AP ET KV LR ZM" \
351+
SELECTION_RULE='$$$$((i+1+15))' \
352+
TRANSCRIPT_TYPE=from_scratch
353+
make distribute \
354+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
355+
SRC_DIR=03.auto_transcripts/null \
356+
SRC_FILES=B1ML_23*.xml \
357+
TGT_DIR=05.for_annotators/2025-01-31 \
358+
ANNOTATORS="AP ET KV LR ZM" \
359+
SELECTION_RULE='$$$$((i+1+20))' \
360+
TRANSCRIPT_TYPE=from_scratch
361+
362+
distrib_2025-03-07 :
363+
make distribute \
364+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
365+
SRC_DIR=03.auto_transcripts/null \
366+
SRC_FILES=B1ML_23*.xml \
367+
TGT_DIR=05.for_annotators/2025-03-07 \
368+
ANNOTATORS="AP ET KV LR ZM" \
369+
SELECTION_RULE='$$$$((i+1+25))' \
370+
TRANSCRIPT_TYPE=from_scratch
371+
make distribute \
372+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
373+
SRC_DIR=03.auto_transcripts/null \
374+
SRC_FILES=B1ML_23*.xml \
375+
TGT_DIR=05.for_annotators/2025-03-07 \
376+
ANNOTATORS="ET KV LR ZM" \
377+
SELECTION_RULE='$$$$((i+1+30))' \
378+
TRANSCRIPT_TYPE=from_scratch
379+
make distribute \
380+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
381+
SRC_DIR=03.auto_transcripts/null \
382+
SRC_FILES=B1ML_23*.xml \
383+
TGT_DIR=05.for_annotators/2025-03-07 \
384+
ANNOTATORS="ET KV ZM" \
385+
SELECTION_RULE='$$$$((i+1+34))' \
386+
TRANSCRIPT_TYPE=from_scratch
387+
make distribute \
388+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
389+
SRC_DIR=03.auto_transcripts/null \
390+
SRC_FILES=B1ML_23*.xml \
391+
TGT_DIR=05.for_annotators/2025-03-07 \
392+
ANNOTATORS="ET KV ZM" \
393+
SELECTION_RULE='$$$$((i+1+37))' \
394+
TRANSCRIPT_TYPE=from_scratch
395+
make distribute \
396+
DATA_DIR=/lnet/work/projects/evaldio/tmp/data_preparation/UJOP/CCE-B1_2024_05_21 \
397+
SRC_DIR=03.auto_transcripts/null \
398+
SRC_FILES=B1ML_23*.xml \
399+
TGT_DIR=05.for_annotators/2025-03-07 \
400+
ANNOTATORS="ET KV ZM" \
401+
SELECTION_RULE='$$$$((i+1+40))' \
402+
TRANSCRIPT_TYPE=from_scratch
403+
320404
distribute_manual :
321405
mkdir -p $(TGT_DIR_PATH)
322406

data_preparation/distribute_to_annotators/audio_to_transcript2annot_name.sh

+1-1
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
src_f=$1
44
annotator=$2
55
transcripttype=$3
6-
src_pattern='\(.*\)_anonym_audio\(_video\)\?\.xml'
6+
src_pattern='\(.*\)_anonym_.*\.xml'
77

88
if [ -z "$transcripttype" ]; then
99
transcripttype=`echo "$src_f" | md5sum | cut -c1-10`

0 commit comments

Comments
 (0)