monika-rvc-tests

Test RVC models on the DDLC character Monika, via various hyperparams and datasets.

monika-test-0 (~07/2023)

• Trained on augmented dataset of ~10 10 second clips
• Trained for ~100 epochs
• RVC1
• "Version 1" ("0" in the old numbering)

monika-test-2 (~07/2023)

• Trained on augmented dataset of ~10 10 second clips (augmented via tortoise tts)
• Trained for 100 epochs
• RVC1

monika-test-4 (~07/2023)

• Trained on smaller but better dataset of ~2 10 second clips (augmented via 11labs)
• Trained for 150 epochs
• RVC1

monika-test-7 (08/22/2023)

• Trained on augmented dataset of ~10+ 10 second clips (augmented via tortoise tts)
• Trained for 60 epochs (720 steps)
• Better quality than others
• "Version 2" ("1" in old numbering)
• RVC2

monika-test-8 (08/22/2023)

• Trained on smaller but better dataset of ~5 10 second clips (some augmented via 11labs)
• Trained for 60 epochs (660 steps)
• Even clearer quality but with slightly more artifacting than monika-test-7 (still better than pre 7th ones)
• "Version 2a" ("1a" in old numbering)
• RVC2

ct-m3 (~10/2023)

• Trained on preprocessed version of dataset of ~5 10 second clips
• Trained for ~100 epochs
• Test model
• RVC1

ct-m4 (~10/2023)

• Trained on preprocessed version of dataset of ~5 10 second clips
• Trained for ~200 epochs
• Test model
• RVC1

ct-m4a (~10/2023)

• Trained on preprocessed version of dataset of ~5 10 second clips
• Trained for ~200 epochs
• "Version 4" ("3" in old numbering)
• RVC2

fused2 (~02/2024)

• Merge between ct-m3 and another model ("Sayori"-based model, with ratio of 75% to 25%)
• Somewhat clearer quality
• Yet another test model
• RVC2

fused5 (~01/2025)

• 50-50 merge between ct-m5 (~06/2024) and fused2
• In addition to merging, experiment with fine-tuning on more synthetic data which doubled preprocessed dataset size
• Sliiightly better than fused2; seems not to "break" where fused2 does, otherwise they seem almost the same
• RVC2

mm26a (2026)

• Trained on preprocessed and combined version of original dataset of ~5 10 second clips + 32 synthetic Chatterbox-generated ~10+ second raw voice clips
• Trained for 20 epochs
• RVC1

mm26e (2026)

• Trained on preprocessed and combined version of original dataset of ~5 10 second clips + 32 synthetic Chatterbox-generated ~10+ second preprocessed voice clips
• Trained for 20 epochs
• RVC1

mm26eg (2026)

• 50-50 merge between mm26e and mm26g
• RVC1

mm26f (2026)

• Trained on preprocessed and combined version of original dataset of ~5 10 second clips + 32 synthetic Chatterbox-generated ~10+ second preprocessed voice clips
• Trained for 20 epochs
• RVC2

mm26g (2026)

• Trained on best clips of original dataset + 5 synthetic Chatterbox-generated ~20+ second preprocessed voice clips
• Trained for 50 epochs
• RVC1