Sign in to view source links and access this dataset
Description
Thorsten-Voice created a small, high-quality dataset of 60 newly recorded German speech samples, last updated in December 2025. The dataset is designed for speaker refinement and voice matching in Orpheus text-to-speech models. The samples are spoken in a neutral, relaxed, everyday style, closely reflecting the natural speaking voice of the original speaker.
Use Cases
Speaker adaptation for TTS models based on the 60 high-quality German speech samples.
Voice matching and refinement based on the neutral, relaxed speaking style described.
Fine-tuning Orpheus TTS models based on the dataset's specific design purpose.
Strengths
Contains 60 newly recorded, high-quality German speech samples.
Samples are recorded in a neutral, relaxed, everyday style, closely reflecting the speaker's natural voice.
Dataset is specifically designed for fine-tuning Orpheus TTS models.
Limitations
Column-level documentation is absent; field semantics must be inferred after download.
Row count is unknown, which may limit suitability assessment for larger-scale tasks.
Data may reflect the specific bias inherent to a single speaker's voice and recording style.
Provenance
Source
Thorsten-Voice
Collection Method
Newly recorded speech samples.
Time Range
2025
Freshness
Last updated 2025-12-12 20:46:08.
Geography
Germany (based on language)
License is unknown; terms of use must be verified before download.