Observed arrival · 2026-10-16
Bodéwadmimwen ASR: speech recognition for Potawatomi
Documentation for a Potawatomi speech-recognition project, describing a Whisper-small model adapted with LoRA and how to use its proposed inference interface.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Potawatomi language workers and speech-technology researchers
- Worth noticing
- The sample endpoint instructions still mark its URL and several input requirements as TODOs; the transcribe demo is explicitly simulated.
Field notes
The documentation presents LoRA as a way to adapt a multilingual model without replacing its base weights, motivated by a very small audio corpus. It describes the corpus as held by the Citizen Potawatomi Nation and says raw recordings and restricted or ceremonial material are not published. Some operational details remain unfinished, and the page’s quick-fact metrics do not match the evaluation figures in its explanatory text.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
◎NicheUnusually specific use
One card from the complete issue