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

该数据集是TV-24kHz-2025.12-Neutral-FT-Mini数据集的标记化版本，专门为Orpheus TTS Thorsten-Voice的直接微调准备。包含60个标记化的德语语音样本，优化用于快速实验和精确的说话者适应。适用于轻量级Orpheus TTS微调、说话者身份细化以及韵律和发音调整。数据来源为Thorsten-Voice/TV-24kHz-2025.12-Neutral-FT-Mini，说话者为Thorsten，语言为德语，录制日期为2025年12月。数据集经过24,000 Hz的音频重采样、-24dB的响度归一化，并使用Orpheus TTS预处理进行标记化。采用Creative Commons Zero (CC0 1.0)许可证发布，允许任何用途，包括商业和衍生作品，无需署名要求。

This dataset is the tokenised version of the TV-24kHz-2025.12-Neutral-FT-Mini dataset, prepared specifically for direct fine-tuning of Orpheus TTS Thorsten-Voice. It contains 60 tokenised German speech samples, optimised for fast experimentation and precise speaker adaptation. This dataset is intended for lightweight Orpheus TTS fine-tuning, speaker identity refinement, and prosody and articulation adjustments. The source dataset is Thorsten-Voice/TV-24kHz-2025.12-Neutral-FT-Mini, with the speaker being Thorsten, language German, and recording date December 2025. The dataset has been processed with audio resampled to 24,000 Hz, loudness normalized to -24dB, and tokenised using Orpheus TTS preprocessing. It is released under the Creative Commons Zero (CC0 1.0) license, free for any use, including commercial and derivative works, without attribution requirements.