Langdrift

Clocks how differently an original and its translation land in a listener's wetware, using a brain-activation model.

Maker / Starside Labs crew

TypeScript Python Modal Meta FAIR TRIBE v2

Translation that lands right, not just reads right

Langdrift puts the audio of an original up against its translation and kicks back a drift score: how far apart the two land in the skull. It catches translations that are technically clean but emotionally or contextually off the mark.

What it does

  • Stacks original vs translation audio with Meta FAIR’s TRIBE v2 model (trained on fMRI data)
  • Maps brain-activation patterns across the cortex
  • Returns a drift score for the cognitive gap between versions

The rig

TypeScript/Node.js CLI wired to a Python backend on Modal (A10G GPU). Core model: Meta FAIR TRIBE v2 with Wav2Vec-BERT 2.0 encoding and Pearson correlation scoring. Part of the Starside Labs crew.

Let's link up, choom.

Always down to trade notes, talk shop, or just ping. The net is the fastest way to reach me.

Ping me