issues
search
k2-fsa
/
text_search
Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup
https://k2-fsa.github.io/text_search/
53
stars
14
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Add more documentations
#71
zhu-han
closed
2 weeks ago
0
fix model encoder to use a different model than the default
#70
annapovey
closed
1 week ago
0
Help with using this tool for creating TTS training data
#69
weedwind
opened
1 month ago
3
Use streaming asr to transcript the audio
#68
pkufool
opened
2 months ago
0
License file addition for easier reference
#67
vijayaditya
opened
3 months ago
0
Segment durations exceed "max_duration"
#66
katpovey
opened
4 months ago
0
Add subtitle alignment recipe
#65
pkufool
closed
3 months ago
0
Add tool to calculate overlap ratio
#64
pkufool
closed
7 months ago
0
revert the change of end_time
#63
pkufool
closed
7 months ago
0
Release v1.11
#62
pkufool
closed
7 months ago
0
If break at period, it has to be followed by space
#61
pkufool
closed
7 months ago
0
Minor fixes & update pypi token
#60
pkufool
closed
8 months ago
0
Fix dataloader in parallel
#59
pkufool
closed
8 months ago
0
Fix break segments and overlap
#58
pkufool
closed
8 months ago
0
Resample cuts since model works at 16kHz
#57
nshmyrev
closed
10 months ago
1
Make is_overlap work according to documentation
#56
nshmyrev
closed
8 months ago
3
Can't download librilight-text
#55
shuaijiang
closed
8 months ago
2
Associate multiple version of reference
#54
pkufool
opened
12 months ago
0
Error: "RuntimeError: shape '[1, 0, 2]' is invalid for input of size 15319040"
#53
npovey
opened
1 year ago
4
use relative path
#52
pkufool
closed
1 year ago
0
support modified beam search
#51
pkufool
closed
1 year ago
0
Add model download script
#50
pkufool
closed
1 year ago
0
Fix the prefix spaces and punctuations; upgrade to version 0.9
#49
pkufool
closed
1 year ago
0
Fix puctuations and upgrade to version 0.8
#48
pkufool
closed
1 year ago
0
Wheels
#47
pkufool
closed
1 year ago
0
Support macos wheels
#46
pkufool
closed
1 year ago
0
Fix doc building
#45
pkufool
closed
1 year ago
0
Release to pypi with a github CI
#44
pkufool
closed
1 year ago
0
ImportError: cannot import name 'str2bool' from 'textsearch.utils'
#43
npovey
closed
1 year ago
1
Minor fixes to the whole pipeline
#42
pkufool
closed
1 year ago
0
Add run.sh to combine the whole pipeline
#41
pkufool
closed
1 year ago
0
Add scripts to transcript the audios
#40
pkufool
closed
1 year ago
0
Add data prepare pipeline for librilight
#39
pkufool
closed
1 year ago
0
Remove close matches and get candidates
#38
pkufool
closed
1 year ago
0
Refactor; Some fixes to split aligned queries
#37
pkufool
closed
1 year ago
0
Example usage docs; update docs
#36
danpovey
closed
8 months ago
1
doc location
#35
danpovey
closed
1 year ago
1
Add setup and upload to pypi
#34
pkufool
closed
1 year ago
0
Archieve the proposal
#33
pkufool
closed
1 year ago
0
Close matches cpp version
#32
pkufool
closed
1 year ago
0
Fix building doc
#31
csukuangfj
closed
1 year ago
0
Add documentation
#30
csukuangfj
closed
1 year ago
1
Add librilight recipe
#29
pkufool
closed
1 year ago
3
Implement find_candidate_matches and some minor fixes.
#28
pkufool
closed
1 year ago
1
Implement faster alignment
#27
pkufool
closed
1 year ago
0
Replace int64_t with int32_t for suffix array computation.
#26
csukuangfj
closed
1 year ago
3
Add renumbering for computing suffix arrays
#25
csukuangfj
closed
1 year ago
0
Support renumbering in create_suffix_array
#24
csukuangfj
closed
1 year ago
1
Hide the implementation detail of create_suffix_array.
#23
csukuangfj
closed
1 year ago
0
Combine the whole pipeline
#22
pkufool
closed
1 year ago
1
Next