Improve model card: Add abstract, sample usage, update paper and project page links

README.md

@@ -10,9 +10,53 @@ tags:
 - hf-asr-leaderboard
 ---
 
-<!-- Provide a quick summary of what the model is/does. -->
+# LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation
 
-Lite-Whisper is a compressed version of OpenAI Whisper with LiteASR. See our [GitHub repository](https://github.com/efeslab/LiteASR) and [paper](https://arxiv.org/abs/2502.20583) for details.
+[📄 Paper](https://huggingface.co/papers/2502.20583) | [💻 Code](https://github.com/efeslab/LiteASR) | [🌐 Project Page](https://efeslab.github.io/LiteASR/)
+
+LiteASR is a compression scheme for automatic speech recognition (ASR) models that leverages the _low-rank_ properties of activation values. Our method can compress OpenAI's Whisper encoder by up to **~50%**.
+
+## Abstract
+Modern automatic speech recognition (ASR) models, such as OpenAI's Whisper, rely on deep encoder-decoder architectures, and their encoders are a critical bottleneck for efficient deployment due to high computational intensity. We introduce LiteASR, a low-rank compression scheme for ASR encoders that significantly reduces inference costs while maintaining transcription accuracy. Our approach leverages the strong low-rank properties observed in intermediate activations: by applying principal component analysis (PCA) with a small calibration dataset, we approximate linear transformations with a chain of low-rank matrix multiplications, and further optimize self-attention to work in reduced dimensionality. Evaluation results show that our method can compress Whisper large-v3's encoder size by over 50%, matching Whisper medium's size with better transcription accuracy, thereby establishing a new Pareto frontier of accuracy and efficiency. The code of LiteASR is available at this https URL .
+
+## Quick Start (Sample Usage)
+
+The easiest way to run our model is to use our integration with HuggingFace Transformers library.
+We provide model weights for the compressed version of OpenAI Whisper series [here](https://huggingface.co/efficient-speech).
+
+```python
+import librosa 
+import torch
+from transformers import AutoProcessor, AutoModel
+
+device = "cuda:0"
+dtype = torch.float16
+
+# load the compressed Whisper model
+model = AutoModel.from_pretrained(
+    "efficient-speech/lite-whisper-large-v3-turbo", 
+    trust_remote_code=True, 
+)
+model.to(dtype).to(device)
+
+# we use the same processor as the original model
+processor = AutoProcessor.from_pretrained("openai/whisper-large-v3")
+
+# set the path to your audio file
+path = "path/to/audio.wav"
+audio, _ = librosa.load(path, sr=16000)
+
+input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features
+input_features = input_features.to(dtype).to(device)
+
+predicted_ids = model.generate(input_features)
+transcription = processor.batch_decode(
+    predicted_ids, 
+    skip_special_tokens=True
+)[0]
+
+print(transcription)
+```
 
 ## Benchmark Results