harvard-edge multilingual_kws issues

harvard-edge / multilingual_kws

Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus

153 stars 35 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Change MSWC data download links to Cloudflare instead of Google

#43 morphine00 closed 4 days ago
2
dataset of multilingual_context_73_0.8011

#42 farzadhallaji closed 6 months ago
1
Where can I find the used keywords (total 760) and splits from the paper?

#41 V0XNIHILI closed 1 year ago
3
Fix link to dataset Youtube video

#40 V0XNIHILI closed 1 year ago
1
Reproducing paper results

#39 sathibault opened 1 year ago
0
OperatorNotAllowedInGraphError during Transfer Learning

#38 ccioflan opened 1 year ago
0
ERROR: Cannot find key when Running docker

#37 manarsaaldossari opened 2 years ago
0
How to train it for more than one target_keyword?

#36 twshen2000 closed 4 months ago
3
some empty directories in MSWC? or the 16KHz reencode?

#35 mmaz opened 2 years ago
0
Using multilingual_kws with microphone streaming

#34 wesbz closed 2 years ago
5
UMAP visualization transitive dependency on old numpy

#33 mmaz opened 2 years ago
0
words with apostrophes are not correctly being extracted

#32 mmaz opened 2 years ago
0
add version info to each tarball

#31 mmaz closed 2 years ago
0
Coleman stats

#30 chooper1 opened 2 years ago
0
Arabic word formatting

#29 mmaz opened 2 years ago
1
GCS transfer

#28 mmaz closed 2 years ago
1
expand and validate text normalization/cleaning filters

#27 mmaz opened 2 years ago
1
Changes

#26 chooper1 closed 2 years ago
1
is Mozilla SWTS in the dataset?

#25 mmaz closed 2 years ago
2
Add TFDS integration/flow

#24 colbybanbury closed 2 years ago
0
TFDS api

#23 mmaz opened 2 years ago
2
words greater than 2^3 are probably > 1s

#22 mmaz opened 2 years ago
1
Add zero shot classification and POS Tagging tutorials

#21 Ciroye opened 2 years ago
0
found duplicates at __2 and __3 etc

#20 mmaz closed 2 years ago
3
re-run few shot experiments with same split of unknown/silence as the DSCNN tests

#19 mmaz opened 2 years ago
0
Dscnn comparison

#18 colbybanbury closed 2 years ago
0
rerun DSCNN tests with fixed AudioSeed data for unknown sampling

#17 mmaz closed 2 years ago
1
Dataset Code

#16 Sharad24 opened 2 years ago
0
generate a sibling dataset with speech context

#15 mmaz opened 2 years ago
1
verify 1-1 match between final audio files and splits

#14 mmaz opened 2 years ago
0
Bug: Some languages (basque, polish) seem to have a higher total length duration than in original common Voice

#13 Sharad24 opened 2 years ago
0
Re-creating alignments for Common Voice 7

#12 Sharad24 opened 2 years ago
0
Lithuanian clips not validated

#11 Sharad24 closed 2 years ago
1
Some percentage of wavs (~3%) are below 1s according to soxi, others can't be opened

#10 mmaz opened 2 years ago
1
Filter out NaNs from Common Voice tsvs, distinguish between intentional "nan" in language vocabulary

#9 mmaz opened 2 years ago
0
Re-encode mp3/opus clips to exactly 1s

#8 mmaz closed 2 years ago
0
check for 16KHz in AudioDataset

#7 mmaz opened 2 years ago
0
support evaluate mode in input_data

#6 mmaz closed 2 years ago
0
Create dscnn-comparison.py

#5 colbybanbury closed 2 years ago
0
is there the inference.py？

#4 huacilang closed 2 years ago
1
First time user

#3 El-Yazid closed 2 years ago
4
Coleman changes

#2 chooper1 closed 3 years ago
0
word counts

#1 mmaz closed 3 years ago
2