Surogate Speech is out š small open speech models for agents, the speech side of Surogate.
First language shipped is Romanian, and the numbers came out better than I expected: 5.69% WER on FLEURS with a 116M model. Canary 1B gets 5.95% on the same clips, Whisper large-v3 8.42%. Leaderboard runner, one RTX 5090.
What's in it:
š§ jackrabbit-110m-ro: speech recognition, 2,500Ć real time on one GPU ā” jackrabbit-110m-ro-streaming: live, final text about 0.7 s after you stop talking š£ļø amami-357m-ro: TTS with three voices, runs on a CPU
Serving is one line with our engine: surogate serve --stt surogate/jackrabbit-110m-ro
Transcripts for every clip are public if you want to rescore it.
most labs won't bother teaching a small model to write and think in real romanian. no invented words, no english leaking in mid-sentence, diacritics intact.
we did.
surogate 3.5 is out. 2B and 4B, apache 2.0. invented word-forms cut from 4 per 1k down to ~1.5, and it reasons in the language you prompt it in, every time.