Instructions to use canopylabs/orpheus-3b-0.1-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use canopylabs/orpheus-3b-0.1-ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="canopylabs/orpheus-3b-0.1-ft")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("canopylabs/orpheus-3b-0.1-ft") model = AutoModelForCausalLM.from_pretrained("canopylabs/orpheus-3b-0.1-ft") - Inference
- Notebooks
- Google Colab
- Kaggle
Encoding type for audio generated by Orpheus
#19
by pooja-gajjar - opened
I am able to generate audio with only encoding type PCM. Is it possible to generate audio of an encoding type mulaw and linear 16? if yes, how??
Also want to know if there is any ssml support for Orpheus