Skip to content

Dataset · Kit-Lemonfoot

Voice datasets for voice cloning and TTS

Kit-Lemonfoot/LemonfootVoiceDatasets

Audio recordings and manual transcriptions in English and Japanese for training voice models.

What's inside

A custom collection of audio datasets in English and Japanese used to train RVC, Style BertVITS2, and GPT-SoVITS models. It also includes sets with manual transcriptions in LJSpeech format, originally prepared for the 15.ai service.

What you can do with it

  • Training and fine-tuning text-to-speech (TTS) models such as GPT-SoVITS and Style BertVITS2
  • Training voice conversion models (RVC)
Tasks
Audio → audio, Text → speech
Languages
English, Japanese
Downloads this month
108
Likes
10

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("Kit-Lemonfoot/LemonfootVoiceDatasets")