ufakzeka-kulak: Building and Evaluating a 31.6M-Parameter Turkish Speech Recognizer from Scratch
Paper recorded by Signals 4 on 2026-11-02 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-11-02 on arXiv · recorded by Signals 4 on 2026-11-03
Category: cs.CL · 自然语言处理 · first seen 2026-11-03
Abstract
ufakzeka-kulak is an open Turkish speech-to-text model of 31.6M parameters, a FastConformer encoder with a token-and-duration transducer (TDT) and a CTC head, trained from scratch and released under Apache-2.0. It writes cased, punctuated Turkish with numbers as words. Its 4,977 training hours come from sources whose licences allow commercial use; 281 hours are human-transcribed, and for the other
Read on arXiv →
Cite this page: ufakzeka-kulak: Building and Evaluating a 31.6M-Parameter Turkish Speech Recognizer from Scratch: the #11 most recent of 628 cs.CL papers we have recorded (as of 2026-11-02). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/ufakzeka-kulak-building-and-evaluating-a-31-6m-parameter-turkish-speech-recogniz.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free