Xi Jinping Voicebank for Speech Synthesis Fine-Tuning

1 hour and 30 minutes of audio clips extracted from public video footage of Xi Jinping. The dataset is intended for fine-tuning text-to-speech models and was uploaded by KritiAI on June 8, 2025. It includes scripts for processing audio files using Whisper and preparing data for the Bert-VITS2 framework.

Use Cases

• Fine-tuning a text-to-speech model based on the provided 1.5 hours of audio.
• Creating a voice clone for research or development purposes using the described processing pipeline.
• Generating synthetic speech in Mandarin Chinese based on the characteristics of the source voice.

Strengths

• Contains 1 hour and 30 minutes of processed audio clips suitable for model training.
• Source material is explicitly stated to be from public domain footage.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset's size, file formats, and license are unknown.

Provenance

Source

Public video footage.

Collection Method

Audio extracted and processed using Whisper and custom scripts.

Freshness

Last updated 2025-06-08 17:26:49; freshness should be verified.