Dataset from Disney Infinity only. Includes breathy sounds, grunts, groan, and laughs. Mainly for talking or speech, singing might work depending on the input audio.

Tip: De-reverb your audio first before inferencing.

Dataset Info:
- Disney Infinity Files
- 32Khz Sample Rate
- 8 Minutes and 49 Seconds Length

Training Settings:
- Harvest
- 4 Batch Size
- 300 Epochs
- 40K Sample Rate
- Titan Pretrain

Model Link:
https://huggingface.co/SCRFilms/ElsaFrozenV4/resolve/main/elsa_disney.zip?download=true

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/SCRFilms/ElsaFrozenV4/resolve/main/elsa_disney.zip?download=true Hosted on Hugging Face