Instructions to use UsefulSensors/moonshine-tiny-ko with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UsefulSensors/moonshine-tiny-ko with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="UsefulSensors/moonshine-tiny-ko")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("UsefulSensors/moonshine-tiny-ko") model = AutoModelForSpeechSeq2Seq.from_pretrained("UsefulSensors/moonshine-tiny-ko") - Notebooks
- Google Colab
- Kaggle
Improve model card: Update title, intro, links, and add project page
#1
by nielsr HF Staff - opened
This PR significantly improves the model card for the moonshine-tiny-ko model by:
- Updating the main title to accurately reflect the paper: "Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices".
- Enhancing the introductory paragraph with a concise description from the paper's abstract.
- Ensuring all internal links to the paper now point to the official Hugging Face Papers page: https://huggingface.co/papers/2509.02523, enhancing Hub integration. The
arxivlink is retained in the metadata. - Adding a direct link to the main GitHub repository (
https://github.com/moonshine-ai/moonshine) under a "Code" label, while also keeping the "Installation" link. - Adding a dedicated "Project Page" section linking to the associated blog post: https://petewarden.com/2024/10/21/introducing-moonshine-the-new-state-of-the-art-for-speech-to-text/.
- Updating the
urlin the BibTeX citation for consistency with the Hugging Face paper link.
These changes enhance the model card's accuracy, clarity, and navigability, making it easier for users to understand and access relevant resources.
theadamsabra changed pull request status to merged