VOICEPEAK Japanese Female 1 - RVC v2, 90 epochs (10,600 steps) v1.0 AI Voice Model

VOICEPEAK Japanese Female 1 - RVC v2, 90 epochs (10,600 steps) v1.0

Created: July 4, 2023

This was an experiment with using VOICEPEAK - a japanese ai-powered tts program - as a dataset for an RVC model.

Japanese Female 1's voice model is trained on 36 minutes of audio, from 3 pitches. She has a sweet, neutral sounding voice, and her range is C3-C5. She also has a japanese accent when inferring english audio.

Later iterations of this dataset will include different emotion-based models, however for now the model is only trained with a normal inflection.

CHANGELOG:

7/2/2023: Released the model.

You can download the model here: https://huggingface.co/hobqueer/VOICEPEAKJapaneseFemale1/resolve/main/VOICEPEAKJapaneseFemale1.zip

Reposted due to the prior thread being filled up with unrelated things.

Additional Details:

Tags: RVC v2

Download Link: https://huggingface.co/hobqueer/VOICEPEAKJapaneseFemale1/resolve/main/VOICEPEAKJapaneseFemale1.zip Hosted on Hugging Face

Convert this model in EasyAIVoice

Sample deck

Pitch previews

Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.

samples ready

female base · pitch 0 Generated female reference sample

Autorun

Run

male

female

female-base generated sample male-base generated sample Enrichment pending: no scores or voice accords yet Ctrl/Cmd-click = select multiple pitches