Thorsten-Voice/TV-24kHz-2025.12-Neutral-FT-Mini

该数据集是一个小规模高质量的微调数据集，专门为Orpheus TTS模型的说话人细化和声音匹配而创建。数据集包含60个新录制的德语语音样本，采用中性、放松的日常风格录制，反映了原始说话人的自然说话声音。音频特征包括24,000 Hz的采样率、-24dB的响度标准化，以及干净、未经处理的语音。数据集适用于说话人适应、声音细化、Orpheus TTS模型的微调以及韵律和自然度的改进。数据集采用Creative Commons Zero (CC0 1.0)许可证发布，允许无限制使用。

This dataset is a small, high-quality fine-tuning dataset created specifically for speaker refinement and voice matching in Orpheus TTS models. It consists of 60 newly recorded German speech samples, spoken in a neutral, relaxed, everyday style, closely reflecting the natural speaking voice of the original speaker. Audio characteristics include a sample rate of 24,000 Hz, loudness normalized to -24dB, and clean, unprocessed speech. The dataset is intended for speaker adaptation, voice refinement, fine-tuning Orpheus TTS models, and prosody and naturalness improvements. It is released under the Creative Commons Zero (CC0 1.0) license for unrestricted use.