FormosanBank Machine Translation models
FormosanBank
Team
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
FormosanBank
FormosanBank is a machine-readable corpus and tooling ecosystem for Taiwan’s Indigenous Formosan languages. This Hugging Face organization hosts datasets and related resources for research, education, language revitalization, and speech/language technology.
What’s here
- datasets and corpus releases
- text, metadata, and audio-linked resources
- materials for ASR, MT, and NLP
Links
Use and licensing
Licensing may vary by corpus. Please check each dataset card and the project documentation before reuse.
spaces 6
Sleeping
Amis ASR Transcription
🐶
Transcribe Amis audio and export ELAN annotations
Sleeping
Paiwan ASR Transcription
🏃
Transcribe and edit Paiwan audio into searchable text files
Running on Zero
3
Formosan <-> Chinese Machine Translation
💬
MT between 15 Formosan Languages and Chinese
Running on Zero
Formosan <-> English Machine Translation
💬
MT between 15 Formosan Languages and English
Running on Zero
FormosanBank ASR Transcription
🎙
Transcribe spoken audio into text for multiple Formosan languages
models 18
FormosanBank/xls-r-53-stage1-yami-asr
Automatic Speech Recognition • 0.3B • Updated • 14
FormosanBank/xls-r-53-stage1-tsou-asr
Automatic Speech Recognition • 0.3B • Updated • 15
FormosanBank/xls-r-53-stage1-thao-asr
Automatic Speech Recognition • 0.3B • Updated • 14
FormosanBank/xls-r-53-stage1-taroko-asr
Automatic Speech Recognition • 0.3B • Updated • 16
FormosanBank/xls-r-53-stage1-seediq-asr
Automatic Speech Recognition • 0.3B • Updated • 14
FormosanBank/xls-r-53-stage1-sakizaya-asr
Automatic Speech Recognition • 0.3B • Updated • 16
FormosanBank/xls-r-53-stage1-saisiyat-asr
Automatic Speech Recognition • 0.3B • Updated • 14
FormosanBank/xls-r-53-stage1-saaroa-asr
Automatic Speech Recognition • 0.3B • Updated • 16
FormosanBank/xls-r-53-stage1-rukai-asr
Automatic Speech Recognition • 0.3B • Updated • 14
FormosanBank/xls-r-53-stage1-puyuma-asr
Automatic Speech Recognition • 0.3B • Updated • 13
datasets 35
FormosanBank/NTUFormosanCorpus_Grammar
Updated • 17
FormosanBank/TangRecordingsOfTaroko
Updated • 34
FormosanBank/YutasWilang
Viewer • Updated • 1.1k • 2.84k
FormosanBank/YeddaPalemeqBlog_Paiwan
Viewer • Updated • 668 • 1.09k
FormosanBank/Whitehorn_Collection
Updated • 9
FormosanBank/ILRDF_Dict_Yami
Viewer • Updated • 6.44k • 2.32k
FormosanBank/ILRDF_Dict_Tsou
Viewer • Updated • 2.88k • 2.77k
FormosanBank/ILRDF_Dict_Truku
Viewer • Updated • 4.68k • 2.25k
FormosanBank/ILRDF_Dict_Thao
Viewer • Updated • 6.42k • 2.81k
FormosanBank/ILRDF_Dict_Seediq
Viewer • Updated • 5.48k • 3.23k