Instructions to use OpenSound/CapSpeech-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenSound/CapSpeech-models with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="OpenSound/CapSpeech-models")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenSound/CapSpeech-models", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download nar_duration_predictor/model.safetensors from OpenSound/CapSpeech-models: direct link, hf CLI and curl.
- Browser
- Download file 439 MB
-
https://huggingface.co/OpenSound/CapSpeech-models/resolve/refs%2Fpr%2F2/nar_duration_predictor/model.safetensors
- Command line
-
hf download hf://OpenSound/CapSpeech-models@refs/pr/2/nar_duration_predictor/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/OpenSound/CapSpeech-models/resolve/refs%2Fpr%2F2/nar_duration_predictor/model.safetensors
439 MB
- Xet hash:
- 3f6bc3c58c4092a85c795e8785dd7f8f785a904aabaaeaf76a4607846446bcff
- Size of remote file:
- 439 MB
- SHA256:
- 17742ae7a884b676f23333db69c48e9262dbb80a8f0a2d05f8469437e77ee13f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.