PulseAugur
中
实时 00:21:36
English(EN) ufakzeka-kulak: Building and Evaluating a 31.6M-Parameter Turkish Speech Recognizer from Scratch

新的土耳其语TTS和STT模型利用合成数据提高性能 · 跟踪3个来源

研究人员开发了新的土耳其语文本到语音(TTS)和语音到文本(STT)模型。Antalia-2 Mini是一个拥有760万参数的TTS模型,在使用合成语音进行训练后,在Freya-TR-Eval基准测试上达到了1.09%的词错误率。Alania-2是一个拥有4.88亿参数的更大TTS模型,也利用了合成数据,并提供语音克隆和文本驱动的语音设计等功能,在同一基准测试上达到了1.44%的WER。此外,ufakzeka-kulak是一个拥有3160万参数的土耳其语STT模型,是从头开始训练的,在各种测试集上取得了与Whisper模型相媲美的性能。 AI

影响 这些模型提升了土耳其语在语音技术方面的能力,可能改善土耳其语使用者的可访问性和应用。

排序理由 该集群包含多篇详细介绍新的语音合成和识别模型的研究论文,包括它们的架构、训练数据和基准性能。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新的土耳其语TTS和STT模型利用合成数据提高性能 · 跟踪3个来源

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含多篇详细介绍新的语音合成和识别模型的研究论文,包括它们的架构、训练数据和基准性能。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
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
11 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [3]

  1. arXiv cs.CL TIER_1 English(EN) · Sezgin Saygili, Emre Kaplaner, Oncel Ozgul, Fikri San Koktas ·

    Antalia-2 Mini:一个拥有760万参数、完全使用合成语音训练的土耳其语文本转语音模型

    arXiv:2611.13811v1 Announce Type: new Abstract: Antalia-2 Mini is a single-voice Turkish text-to-speech model with 7,620,931 parameters. It reads characters and produces 48 kHz audio at 41 times real time on an Apple M5 laptop CPU (2 threads). Its training audio came only from Vo…

  2. arXiv cs.CL TIER_1 English(EN) · Sezgin Saygili, Emre Kaplaner, Oncel Ozgul, Fikri San Koktas ·

    Alania-2:土耳其文本转语音,支持即时和微调语音克隆

    arXiv:2611.13845v1 Announce Type: new Abstract: We present Alania-2, a Turkish text-to-speech (TTS) system with two built-in voices, voice design from text descriptions, and two kinds of voice cloning. Alania-2 is a 488M-parameter model with the VoxCPM architecture, which generat…

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

    ufakzeka-kulak:从零开始构建和评估一个拥有3160万参数的土耳其语语音识别器

    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 …