TITAN
A robust, general-purpose model that gives clean results and handles accents and noise well. Requires fewer training epochs.
Sample Rates: 32k, 40k, 48k
Ov2Super
Works well for small, clean English datasets. Trained on bright, emotional voices. Requires fewer training epochs.
Sample Rates: 32k, 40k
RIN_E3
Trained from scratch on a large English dataset. Best used with high-quality datasets due to its sensitivity to noise.
Sample Rate: 40k
SnowieV3.1-X-RinE3-40K
SnowieV3.1
Trained on Russian and Japanese data. Helps to improve pronunciation in other languages.
Sample Rates: 32k, 40k, 48k
Snowie_RuPretrain
