Instructions to use Cyleux/oc1b-16bit_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cyleux/oc1b-16bit_2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Cyleux/oc1b-16bit_2")# Load model directly from transformers import AutoFeatureExtractor, AutoModelForTextToWaveform extractor = AutoFeatureExtractor.from_pretrained("Cyleux/oc1b-16bit_2") model = AutoModelForTextToWaveform.from_pretrained("Cyleux/oc1b-16bit_2") - Notebooks
- Google Colab
- Kaggle
metadata
library_name: transformers
base_model: unsloth/csm-1b
tags:
- text-to-speech
- csm
- merged
Cyleux/oc1b-16bit_2
Full-parameter CSM checkpoint finetuned from unsloth/csm-1b in oc-voice-2026-dualvoice-b200-full-cold-speakerprefix-p90-whine-3ep-20260506.
Source checkpoint path on the Modal checkpoint volume:
/checkpoints/oc-voice-2026-dualvoice-b200-full-cold-speakerprefix-p90-whine-3ep-20260506/checkpoint-19581