Speech + text dataset collection based on the ParlaMint data. Paper describing the construction process: https://www.arxiv.org/abs/2409.15397.
AI & ML interests
NLP for South Slavic (and other under-resourced) languages
Recent Activity
View all activity
Organization Card
The CLARIN Knowledge Centre for South Slavic languages (CLASSLA) offers expertise on language resources and technologies for South Slavic languages.
Its basic activities are:
- giving researchers, students, citizen scientists and other interested parties information on the available resources and technologies via its documentation
- supporting them in producing, modifying or publishing resources and technologies via its helpdesk
- organizing training activities
models
27

classla/ParlaCAP-Topic-Classifier
Text Classification
•
0.6B
•
Updated
•
80
•
1

classla/wav2vecbert2-filledPause
Audio Classification
•
0.6B
•
Updated
•
4.48k
•
1

classla/xlm-r-parlasent
Text Classification
•
0.6B
•
Updated
•
158
•
2

classla/Wav2Vec2BertPrimaryStressAudioFrameClassifier
Audio Classification
•
0.6B
•
Updated
•
125
•
1

classla/multilingual-IPTC-news-topic-classifier
Text Classification
•
0.6B
•
Updated
•
53.2k
•
15

classla/xlm-roberta-base-multilingual-text-genre-classifier
Text Classification
•
0.3B
•
Updated
•
785
•
28

classla/wav2vec2-large-slavic-parlaspeech-hr-lm
Automatic Speech Recognition
•
Updated
•
1.04k
•
3

classla/xlm-r-bertic
Fill-Mask
•
Updated
•
136
•
3

classla/xlm-r-slobertic
Fill-Mask
•
Updated
•
37

classla/whisper-large-v3-mici-princ
Automatic Speech Recognition
•
2B
•
Updated
•
19
•
1
datasets
21
classla/ParlaSpeech-PL
Viewer
•
Updated
•
531k
•
19
•
1
classla/ParlaSpeech-HR
Viewer
•
Updated
•
868k
•
175
•
1
classla/ParlaSpeech-RS
Viewer
•
Updated
•
278k
•
641
classla/mak_na_konac
Viewer
•
Updated
•
8.46k
•
76
•
1
classla/Mici_Princ
Viewer
•
Updated
•
372
•
24
•
1
classla/ParlaSpeech-CZ
Viewer
•
Updated
•
711k
•
231
•
1
classla/xlm-r-bertic-data
Updated
•
45
•
2
classla/COPA-MK
Viewer
•
Updated
•
1k
•
43
classla/COPA-SR_lat
Viewer
•
Updated
•
1k
•
30
classla/COPA-SR
Viewer
•
Updated
•
1k
•
49