Skip to content

Dataset · hanamizuki-ai

Genshin Impact character voice acting in Chinese

hanamizuki-ai/genshin-voice-v3.3-mandarin

Paired audio recordings and character voice lines from Genshin Impact in Mandarin for speech synthesis and recognition.

What's inside

Contains audio files of various Genshin Impact character voice lines and corresponding text transcripts. All lines are in Mandarin Chinese. The dataset contains 10k to 100k records extracted from original game assets.

What you can do with it

  • Training or fine-tuning TTS models to generate specific character voices
  • Training ASR systems to recognize Chinese gaming speech
Tasks
Text → speech, Automatic speech recognition
Languages
Chinese
Size
10K–100K rows
Downloads this month
4.5K
Likes
41

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("hanamizuki-ai/genshin-voice-v3.3-mandarin")