Contains Sinhala phonological tokenization and few other NLP utilities
Ransaka Ravihara
Ransaka
AI & ML interests
NLP, Computer Vision
Recent Activity
liked a dataset 3 days ago
ranzaka/cse_financial_reports published a dataset 12 days ago
Ransaka/SIDAC updated a collection 25 days ago
Sinhala NLP ToolkitOrganizations
models 52
Ransaka/sinlib
Updated • 416k
Ransaka/TrOCR-Sinhala
Image-to-Text • 0.3B • Updated • 151 • 5
Ransaka/sinhala-n-gram-collection
Updated
Ransaka/whisper-base-chekpoint
72.6M • Updated • 8
Ransaka/sinhala-transliteration-t5
22.4M • Updated • 13
Ransaka/singlish-gpt2
Text Generation • 63.6M • Updated • 75
Ransaka/singlish_tokenizer_16k
Updated
Ransaka/singlish-tokenizer-gpt2
Updated
Ransaka/singlish-tokenizer-bert
Updated
Ransaka/mBart-sin-en
0.6B • Updated • 5
datasets 25
Ransaka/ai-vs-human-generated-dataset-sample
Viewer • Updated • 200 • 25
Ransaka/ai-vs-human-generated-dataset
Viewer • Updated • 85.5k • 103
Ransaka/titanic-test-split
Viewer • Updated • 418 • 25
Ransaka/titanic-train-split
Viewer • Updated • 891 • 18
Ransaka/typo_dataset_synthetic
Viewer • Updated • 100 • 22
Ransaka/sinhala-roman-pairs
Viewer • Updated • 230k • 14
Ransaka/TSIN
Viewer • Updated • 102k • 17
Ransaka/SIDAC
Viewer • Updated • 754k • 25
Ransaka/SSOCR-V.1
Viewer • Updated • 94.1k • 21
Ransaka/SSOCR-1k
Viewer • Updated • 1k • 17