Alania-2 概述与架构
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 generates continuous audio latents with a diffusion head on top of a language-model backbone. We train it from scratch on 18,195 hours of Turkish speech, 90% of which is synthetic speech produced by a larger teacher model and filtered automatically.
文本规范化组件
A text normalizer rewrites numbers, abbreviations and foreign names into the words a Turkish speaker would say; without it, none of 96 test sentences with digits kept all its critical parts, such as an amount or a date, through synthesis and speech recognition, against 86 with it.
性能评估
Freya-TR-Eval 基准测试
On Freya-TR-Eval, a public benchmark of 495 Turkish sentences scored with automatic speech recognition, Alania-2 reaches a word error rate of 1.44%, compared with 5.99% for our previous system.
内置语音与模型规模比较
On its built-in voices, it comes within half a point of character error rate of a 2.3B-parameter model at under a quarter of the size, and a 7.6M-parameter single-voice model trained with the same recipe matches the most intelligible systems we measured, which suggests that training data matters more for intelligibility than model size.
语音克隆的实践发现
We also report practical findings on voice cloning:
- Conditioning on the reference audio alone, rather than continuing it, cuts skipped words from 21.9% to 1.7%.
- 20-30 seconds of reference audio works best.
- A low-rank adapter trained in about two minutes raises speaker similarity well above instant cloning.
推理引擎与资源发布
Finally, we describe inference-engine changes that bring first audio down to 32 ms for a single stream. We release our evaluation harness and three Turkish speech and text datasets.