This model finetunes the pretrained model canopylabs/orpheus-3b-0.1-pretrained using the finetuning pipeline. Full finetuning with Unsloth for 1 epochs.
Datasets
vietnhat/us-jennifer-higgs-metadata5-v2,
vietnhat/us-michael-higgs-metadata1-v2,
vietnhat/us-jill-higgs-metadata2-v2,
vietnhat/us-mack-higgs-metadata3-v2
Inference
Available voice (American): michael, mack, jill, jennifer`
temperature = 0.5
top_p = 0.8
repetition_penalty = 1.1