Experimental work to train Polish language, only 4 epochs but already loss 2.5 and it sounds quite good. No new speakers used. 3h on colab. More to come.

Uploaded finetuned model

  • Developed by: TeeZee
  • License: apache-2.0
  • Finetuned from model : unsloth/orpheus-3b-0.1-ft

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
14
Safetensors
Model size
3.3B params
Tensor type
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TeeZee/Orpheus-TTS-pl-v1.0

Dataset used to train TeeZee/Orpheus-TTS-pl-v1.0