I grabbed over 1 minute of clean audio clips from the anime and trained it on Google colab for 250 epochs.

Tip: Raise the transpose number and pitch to get better accurate results, for a male to male voice between +6 and +12 is accurate.

Additional Details:

Tags: Game Freak, Nintendo, Anime, huggingface, ai-model

Related URL: https://huggingface.co/Ryanham1lton/Totodile/resolve/main/Totodile.zip?download=true

Download Link: https://huggingface.co/Ryanham1lton/Totodile/resolve/main/Totodile.zip?download=true Hosted on Hugging Face

Convert this model in EasyAIVoice

Voice accords

Main sonic traits

Selected-sample labels, grouped by what they describe.

Age

teenage

child

young adult

Music use

adlibs

a song hook

rap

Style/timbre

anime

villain

energetic

Use case

podcasts

assistant agents

education and e-learning

Sample deck

Lean and sweet spot

Pick a pitch, compare the Quality Score, then Run. Hold Ctrl or Cmd to select multiple pitches.

top 1.76 · avg 1.33

female

14

male

4

female base · pitch 0 Quality Score 1.42 · heard as female

Autorun

Run

male

-16 0.97 -12 1.41 -8 1.28 -4 1.34 0 1.33 4 1.43 8 1.44 12 1.67 16 1.76

female

-16 1.41 -12 1.29 -8 1.15 -4 1.22 0 1.42 4 1.46 8 1.07 12 1.23 16 1.00

heard female heard male Quality Score = estimated audio quality, higher is better Ctrl/Cmd-click = select multiple pitches

Similar voices

This voice model sounds like

Nearby voices from generated samples. Pick a pitch in the Sample Deck to refresh the matches.

Finding nearby voices for this pitch...