A Norwegian (Bokmal) text-to-speech model fine-tuned for the Østnorsk/Oslo dialect.
This model is currently in preview, You can expect things like weird artefacts,
But generally, per our testing, it outperforms VibeVoice 7B per our unscientific qualitative eval.
1from transformers import AutoProcessor, AutoModel
2import torch
3
4processor = AutoProcessor.from_pretrained("heiertech/Prat-9B")
5model = AutoModel.from_pretrained("heiertech/Prat-9B", torch_dtype=torch.bfloat16)
6
7# Generate speech
8text = "Hei, dette er en test av den norske stemmen."
9inputs = processor(text=text, return_tensors="pt")
10outputs = model.generate(**inputs)
This model is based on
VibeVoice-7B.
Note that despite the name, VibeVoice-7B is actually a 9B parameter model.
The 7B only refers to the size of the llm backbone based on Qwen2.5 7B
