Improve model card: add link to code and example usage

README.md

@@ -1,13 +1,13 @@
 ---
-license: apache-2.0
-library_name: transformers
 base_model: openai/whisper-large-v3
-tags:
-  - audio
-  - automatic-speech-recognition
-  - whisper
-  - hf-asr-leaderboard
+library_name: transformers
+license: apache-2.0
 pipeline_tag: automatic-speech-recognition
+tags:
+- audio
+- automatic-speech-recognition
+- whisper
+- hf-asr-leaderboard
 ---
 
 # Model Card for Lite-Whisper large-v3
@@ -16,6 +16,41 @@ pipeline_tag: automatic-speech-recognition
 
 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.
 
+Here's a code snippet to get started:
+```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
 
 Following is the average word error rate (WER) evaluated on the [ESB datasets](https://huggingface.co/datasets/hf-audio/esb-datasets-test-only-sorted):