Collection · 3 entries

Speech and audio models

Recognition and synthesis models, grouped so the two directions are easy to compare.

Edited by SAVRN research · last revised 2026-09-18

Entries in this collection

Model · Speech recognition

Published by OpenAI

Why it is here: Speech recognition across many languages.

Open weights apache-2.0 1.5B parameters

Model · Speech recognition

Published by OpenAI

Why it is here: The smaller Whisper, for constrained hardware.

Open weights apache-2.0 242M parameters

Model · Speech recognition

Published by Pyannote

Why it is here: Speaker diarization, gated by its publisher.

Access requested at publisher mit