Underdog demos 32MB Woof speech model for edge devices
The 32MB Woof model runs locally in browsers and supports typing to speech without internet.
1
Stories per day · 30 days
1 RSS
Relatedblock4dessa4full-duplex3voice-ai2apache-2.01edge-ai1local-ai1on-device1open-model1privacy-notice1speech-recognition1turkish1
7 stories, newest first · one card per story
Stories tagged #speech-model
ufakzeka-kulak Turkish speech recognizer released
Open-source 31.6M-parameter Turkish speech-to-text model outperforms Whisper base on FLEURS and Common Voice tests.
Block unveils Dessa, a full-duplex speech model trained only on speech
The captured page gives no availability, size, languages or benchmark figures beyond the headline.
1
Block releases Dessa, a local full-duplex speech model
Dessa is not publicly available, and Block has asked safety researchers to test it first.
2
Block unveils Dessa, a speech-only model not yet public
It runs locally on a MacBook Pro M4 Max, was trained on one NVIDIA GB200 NVL72, and Block wants security testers.
2
Block privacy notice covers the dessa.com speech service
The October 21 notice covers only dessa.com, not Square, Cash App, Afterpay, or TIDAL.
Tencent's Gander aims to keep talking while it works in the background
Tencent's Hunyuan Speech team introduces Gander, a full-duplex voice model pairing a conversational 'cerebellum' with a swappable background agent 'brain'.
7