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
Model tree for TeeZee/Orpheus-TTS-pl-v1.0
Base model
meta-llama/Llama-3.2-3B-Instruct
Finetuned
canopylabs/orpheus-3b-0.1-pretrained
Finetuned
canopylabs/orpheus-3b-0.1-ft
Finetuned
unsloth/orpheus-3b-0.1-ft