Automatic Speech Recognition
Transformers
Safetensors
lite-whisper
feature-extraction
audio
whisper
hf-asr-leaderboard
custom_code
Instructions to use efficient-speech/lite-whisper-medium-fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use efficient-speech/lite-whisper-medium-fast with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="efficient-speech/lite-whisper-medium-fast", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("efficient-speech/lite-whisper-medium-fast", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Improve model card: Add abstract, sample usage, update paper and project page links
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card by:
- Adding the paper's abstract for a comprehensive overview of LiteASR's methodology and results.
- Including a "Quick Start" sample usage code snippet from the GitHub repository, demonstrating how to use the model with the Hugging Face Transformers library.
- Updating the paper link to the official Hugging Face papers page:
https://huggingface.co/papers/2502.20583. - Adding a link to the project page:
https://efeslab.github.io/LiteASR/, found in the GitHub README. - Refining the initial section to prominently feature the paper title, and links to the paper, code, and project page.
- Removing the introductory placeholder comment
<!-- Provide a quick summary of what the model is/does. -->.
These changes make the model card more informative and user-friendly, aligning it with Hugging Face's best practices for documentation.