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", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Facing issues in pipeline
#22
by aaacurse - opened
When using the model in transformers pipeline i am getting the tokens in output["audio"] but the sampling rate in output is None and the audio which is being generated by the pipeline is if 0s. I tried explicitly defining the sampling rate but that too didn't work.