QUAN-Transcribe-1.0
SOTA Fast Vietnamese speech recognition, offline and streaming, built on top of Google's EmbeddingGemma 2.
audio → text · made by qnguyen3
Sold by
Nobody in the catalogue publishes a price for this yet.
About
QUAN-Transcribe-1.0 — a text model from qnguyen3.
It takes audio and returns text. It was published in October 2026. The catalogue files it under transcribe. Its weights are published under the gemma licence, which attaches conditions the plain open licences do not.
Every current figure
- Maker
- qnguyen3
- Register
- model
- Takes
- audio
- Returns
- text
- Published
- October 2026
- Parameters
- 102 million · read from its own weights
- Licence
- gemma
Known as 1 name
qnguyen3/QUAN-Transcribe-1.0