Dataset · simon3000
Genshin Impact voice lines
simon3000/genshin-voice
654k wav files of Genshin Impact character voice lines in Chinese, English, Japanese, and Korean.
What's inside
The dataset contains voice lines from the game Genshin Impact: 654,252 wav files. Some records lack a speaker (7,291, 1%), a transcription (52,693, 8%), and an inGameFilename (1,088, 0%). Languages include Chinese, English, Japanese, and Korean; downloads by speaker are grouped by language and ZIP size.
What you can do with it
- Train ASR for game voice lines
- Fine-tune TTS or LoRA for character voices
- Audio-based speaker classification
- Tasks
- Audio classification, Automatic speech recognition, Text → speech
- Languages
- Chinese, English, Japanese, Korean
- Size
- 100K–1M rows
- Downloads this month
- 18.6K
- Likes
- 307
Models trained on it
- rijulpaul/Qwen3-TTS-12Hz-0.6B-Wriothesley-LoRa-16Text → speech 752
- rijulpaul/Qwen3-TTS-12Hz-0.6B-Wriothesley-LoRa-32Text → speech 269
- rijulpaul/Qwen3-TTS-12Hz-0.6B-Zhongli-LoRa-16Text → speech 138
- ZzWater/ViiTorVoice-NARText → speech 125
- Anthropic-ai/aivoiceText → speech 117
- rijulpaul/Qwen3-TTS-12Hz-0.6B-Nefer-LoRa-32Text → speech 107
- rijulpaul/Qwen3-TTS-12Hz-0.6B-Zhongli-LoRa-32Text → speech 98
- rijulpaul/Qwen3-TTS-12Hz-0.6B-Nefer-LoRa-64Text → speech 90
How to load it
from datasets import load_dataset
ds = load_dataset("simon3000/genshin-voice")