LINKED LIST [txt mode] ▸ Whistle: Speech to Text in 16.9 MB
home explore | log in

Whistle: Speech to Text in 16.9 MB

cactuscompute.com · first added by @owenp · 2026-10-19 · 2 upvotes

log in to save, upvote or flag this.


─── In 0 lists ─────────────────────────────────────────

(not in any lists yet)

* Embedding Gemma Transcribe (from the discussion)

─── Discussions ────────────────────────────────────────

* Whistle: Speech to Text in 16.9 MB
964 pts · 185 comments · node
* Whistle: Speech to Text in 16.9 MB
6 pts · 1 comment · node

─── From the discussion ────────────────────────────────

* vt.py - voice typing gui - needle version
gist.github.com · node
* lokutor-ai/oido: Oído: open-vocabulary speech recognition that fits in a $5 ESP32-S3. 3.7% LibriSpeech WER, no cloud, no NPU.
github.com · node
* Vosk-Browser Demo
ccoreilly.github.io · node
* skorotkiewicz/parakeet-redux-api: Local audio transcription
github.com · node
* try-works/dsh-stt: STT support for DeepSeek Harness using local models from Cactus Compute and Desert Ant Labs
github.com · node