Slovak Female Speech Recordings for Text-to-Speech

Encompassing Slovak speech recordings from a female voice, suitable for text-to-speech (TTS) model training. It provides Slovak language transcripts and audio with a 48,000 Hz sample rate.

Use Cases

• Train a TTS model using the Slovak speech recordings and corresponding transcripts.
• Fine-tune a vocoder on the 48,000 Hz sample rate audio for high-fidelity Slovak speech synthesis.
• Develop a Slovak voice cloning system using the female voice recordings provided.

Strengths

• Audio is recorded at a 48,000 Hz sample rate, suitable for high-quality synthesis.
• Provides Slovak language transcripts specifically for TTS applications.
• Dataset is tagged for a specific language (Slovak) and gender (female).

Limitations

• The dataset is explicitly noted as not suitable for automatic speech recognition (ASR) tasks.
• Key quantitative details like the number of audio clips, total duration, or speaker count are unknown.
• The lack of column definitions or sample data makes the exact data structure unclear.

Provenance

Source

huggingface

Freshness

Last updated on 2026-03-20.

Geography

Slovakia