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
Please post issues on GitHub
pinned#17 opened about 1 year ago
by
amuvarma
School health partnership Ankura Hospital Khammam Proposal
#26 opened 20 days ago
by
rameshankura333
Update README.md
#25 opened about 2 months ago
by
sevyan
Reducing latency by lowering sample rate
1
#24 opened 11 months ago
by
liambarryarm
SNAC output quality with high-pitch speech
2
#23 opened 11 months ago
by
matthen
Facing issues in pipeline
#22 opened about 1 year ago
by
aaacurse
Tiny and small versions of the model
1
#21 opened about 1 year ago
by
stopthinking
Encoding type for audio generated by Orpheus
#19 opened about 1 year ago
by
pooja-gajjar
150M如何使用
1
#15 opened about 1 year ago
by
jmosu
The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (130304)
1
#14 opened about 1 year ago
by
DrNicefellow
Zero-shot voice cloning docs - where?
6
#13 opened about 1 year ago
by
Garkpit
✅ Clean List of Singular, Lowercase, Paralinguistic Words
#12 opened about 1 year ago
by
PlayAI
Gradio space for Free testing of this? Zero shot voice cloning?
2
#8 opened about 1 year ago
by
krigeta
Serious licensing issue
👍😔 8
6
#5 opened about 1 year ago
by
JLouisBiz
forget csm - orpheus is my new best friend
➕👍 14
5
#1 opened about 1 year ago
by
shadowlilac