Dictate
BetaA transcriber that knows when you stopped.
Words, with the brain on timing. Speech to text.
| Platforms | Python, JavaScript |
|---|---|
| Engine | FlyCore v0.1.0 |
| Weights | v0.1.0-beta |
| Input ports | Audio (antennae) → mechanosensory (2,668); Speech embedding → olfactory (2,282) |
| Output ports | Segments: text, t0, t1 ← central |
| Co-processors | Speech recogniser |
The 3D view needs WebGPU or WebGL2.
Install
Python
pip
pip install flycoreJavaScript
Terminal
npm i @flylabs/flycoreUsage
Dictate pairs a compact speech co-processor with the connectome. The co-processor produces words; the brain decides segmentation, turn-taking and when a command is complete.
Python
import flycore
brain = flycore.load("flylabs/dictate") # engine + weights + adapters
for seg in brain.stream(flycore.io.Microphone()):
print(seg.text, seg.t0, seg.t1)
# "open the settings" 3.10 4.02Figures
Figures marked target are design targets for the first release, not measurements.
| Endpoint error | 180 mstarget vs. human annotation; fixed threshold 550 ms |
|---|---|
| Languages | 25target from the co-processor |
Limits
- Beta: co-processor covers 25 languages; the brain is language-agnostic.
- Word accuracy is the co-processor's, not the brain's.