PulseAugur
EN
LIVE 08:46:29

New open-source Turkish speech recognition model released

By PulseAugur Editorial · [1 sources] ·

Researchers have developed "ufakzeka-kulak," a new open-source Turkish speech recognition model with 31.6 million parameters. This model utilizes a FastConformer encoder combined with a token-and-duration transducer (TDT) and a CTC head. Trained on nearly 5,000 hours of licensed data, it achieves a word error rate (WER) competitive with, and in some cases lower than, Whisper base and small models on specific Turkish test sets, though it falls short of Whisper large-v3. AI

IMPACT Provides a new open-source option for Turkish speech recognition, potentially improving accessibility and performance for Turkish language applications.

RANK_REASON Publication of a new open-source model and its evaluation in a research paper. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New open-source Turkish speech recognition model released

How we ranked this

Signal score
20 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Publication of a new open-source model and its evaluation in a research paper. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Sait Furkan Teke (ufak AI) ·

    ufakzeka-kulak: Building and Evaluating a 31.6M-Parameter Turkish Speech Recognizer from Scratch

    arXiv:2611.03605v1 Announce Type: new 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, punc…

RELATED ENTITIES

RELATED TOPICS