Automatic Speech Recognition
Transformers
Safetensors
lite-whisper
feature-extraction
audio
whisper
hf-asr-leaderboard
custom_code
Instructions to use efficient-speech/lite-whisper-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use efficient-speech/lite-whisper-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="efficient-speech/lite-whisper-tiny", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("efficient-speech/lite-whisper-tiny", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Improve model card with abstract and sample usage
Verified signatureThis PR enhances the model card for `lite-whisper-tiny` by adding a detailed abstract from the paper "LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation." This provides a more comprehensive overview of the model's methodology and benefits. Furthermore, it incorporates a "Quick Start" section with a Python code snippet, directly sourced from the official GitHub repository. This sample usage demonstrates how to load and use the model with the `transformers` library, making it significantly easier for users to get started. The model name in the sample code has been adjusted to `efficient-speech/lite-whisper-tiny` to match the specific model this card describes.24089af
-
Update README.md
Verified signatureef17f27 -
Update README.md
Verified signatured8321ba -
Upload LiteWhisperForConditionalGeneration
Verified signature82f14ab -
initial commit
Verified signature412355c