Antalia-2 Mini:760万参数土耳其语语音合成模型
[2611.13811v1] Antalia-2 Mini:一个完全基于合成语音训练的 760 万参数土耳其语文本转语音模型
arXiv 通过 DataCite 颁发的 DOI(待注册)
发件人:Sezgin Saygili [查看邮件] [v1] 2026 年 11 月 10 日(周二)09:41:21 UTC(2,276 KB)
查看论文 PDF,标题为《Antalia-2 Mini:一个完全基于合成语音训练的 760 万参数土耳其语文本转语音模型》,作者为 Sezgin Saygili 及另外 3 位作者
BibTeX 格式引用
文献与引用工具
文献浏览器(什么是文献浏览器?)
Connected Papers(什么是 Connected Papers?)
scite 智能引用(什么是智能引用?)
与本文相关的代码、数据和媒体
CatalyzeX 论文代码查找器(什么是 CatalyzeX?)
Hugging Face(什么是 Hugging Face?)
Hugging Face Spaces(什么是 Spaces?)
推荐器与搜索工具
Influence Flower(什么是 Influence Flower?)
CORE 推荐器(什么是 CORE?)
arXivLabs:与社区合作者共同开展的实验性项目
arXivLabs 是一个框架,允许合作者直接在我们的网站上开发和分享新的 arXiv 功能。
与 arXivLabs 合作的个人和组织均已认同并接受我们开放、社区、卓越和用户数据隐私的价值观。arXiv 坚守这些价值观,并且只与遵循这些价值观的伙伴合作。
你有一个能为 arXiv 社区带来价值的项目想法吗?进一步了解 arXivLabs。
译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。
查看英文原文(Antalia-2 Mini: A 7.6-million-parameter Turkish text-to-speech model trained entirely on synthetic speech)
[2611.13811v1] Antalia-2 Mini: A 7.6-million-parameter Turkish text-to-speech model trained entirely on synthetic speech
arXiv-issued DOI via DataCite (pending registration)
From: Sezgin Saygili [view email]
[v1]
Tue, 10 Nov 2026 09:41:21 UTC (2,276 KB)
View a PDF of the paper titled Antalia-2 Mini: A 7.6-million-parameter Turkish text-to-speech model trained entirely on synthetic speech, by Sezgin Saygili and 3 other authors
BibTeX formatted citation
Bibliographic and Citation Tools
Bibliographic Explorer(What is the Explorer?)
Connected Papers(What is Connected Papers?)
scite Smart Citations(What are Smart Citations?)
Code, Data and Media Associated with this Article
CatalyzeX Code Finder for Papers(What is CatalyzeX?)
Hugging Face(What is Huggingface?)
Hugging Face Spaces(What is Spaces?)
Recommenders and Search Tools
Influence Flower(What are Influence Flowers?)
CORE Recommender(What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
原文为英文,正文由自动抓取并保留原文。
原文发布于 arXiv CS/SD(Antalia-2 Mini: A 7.6-million-parameter Turkish text-to-speech model trained entirely on synthetic speech),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。