arxiv:2609.06970
Joseph Cheng
indiejoseph
AI & ML interests
Cantonese NLP
Recent Activity
liked a dataset about 5 hours ago
jazza234234/british-dataset upvoted a paper 9 days ago
CantoneseLLM v2: Reasoning in a Low-Resource Language authored a paper 14 days ago
CantoneseLLM v2: Reasoning in a Low-Resource LanguageOrganizations
models 16
indiejoseph/w2v2bert_yue_nculeus_tone
0.6B • Updated
indiejoseph/SoulX-Podcast-1.7B-AWQ-MeanFlow-InPaint
Text-to-Speech • 2B • Updated
indiejoseph/CosyVoice2-Inpaint
Updated
indiejoseph/colglmasr
Updated
indiejoseph/jyutvoice
Updated
indiejoseph/sensevoice-yue
Updated
indiejoseph/cosyvoice2-yue-llm
Updated
indiejoseph/bart-translation-zh-yue
Translation • 0.1B • Updated • 42 • 3
indiejoseph/bert-base-cantonese
Fill-Mask • 0.1B • Updated • 656 • 9
indiejoseph/bart-base-cantonese
0.1B • Updated • 12
datasets 15
indiejoseph/canto-songs
Viewer • Updated • 2.91k • 2
indiejoseph/tts-dataset-202505
Viewer • Updated • 1
indiejoseph/c4-cantonese-filtered
Viewer • Updated • 21.6k • 76 • 1
indiejoseph/cc100-yue
Viewer • Updated • 176k • 27 • 2
indiejoseph/yue-zh-translation
Viewer • Updated • 212k • 75 • 11
indiejoseph/wikipedia-translate-zhhk-zhcn
Viewer • Updated • 1.3k • 29 • 1
indiejoseph/ted-translation-zhhk-zhcn
Viewer • Updated • 6.48k • 49 • 1
indiejoseph/wikipedia-en-filtered
Viewer • Updated • 17.3k • 86 • 2
indiejoseph/wikipedia-zh-yue-summaries
Viewer • Updated • 7.11k • 89 • 1
indiejoseph/cantonese-cot
Viewer • Updated • 74.8k • 61 • 4