PulseAugur
EN
LIVE 21:28:15

New open-source Turkish speech recognition model ufakzeka-kulak released

By PulseAugur Editorial · [1 sources] ·

A new open-source Turkish speech-to-text model named ufakzeka-kulak has been developed, featuring 31.6 million parameters. This model utilizes a FastConformer encoder with a token-and-duration transducer (TDT) and a CTC head, trained on nearly 5,000 hours of licensed data. It is capable of producing cased, punctuated Turkish text with numbers written out as words. Evaluations show competitive performance against models like Whisper, achieving a word error rate of 0.0921 on the FLEURS Turkish test set. AI

IMPACT Provides a new open-source option for Turkish speech recognition, potentially improving accessibility and research in the language.

RANK_REASON Release of a new open-source model with performance benchmarks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Hugging Face Daily Papers →

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

New open-source Turkish speech recognition model ufakzeka-kulak released

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Release of a new open-source model with performance benchmarks. [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
8 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

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

    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 …

RELATED ENTITIES

RELATED TOPICS