Create README.md

README.md

@@ -0,0 +1,36 @@
+# MERT
+
+## Usage
+
+```python
+import numpy as np
+from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
+
+model_id = 'yangwang825/mert-base'
+batch_size = 4
+num_classes = 10
+max_duration = 1.0
+
+feature_extractor = AutoFeatureExtractor.from_pretrained(
+    model_id, 
+    trust_remote_code=True
+)
+mert = AutoModelForAudioClassification.from_pretrained(
+    model_id,
+    num_labels=num_classes,
+    ignore_mismatched_sizes=True,
+    trust_remote_code=True
+)
+
+# Simulate the list of waveforms
+audio_arrays = [np.random.rand(16000, ) for _ in range(batch_size)]
+inputs = feature_extractor(
+    audio_arrays, # List of waveforms in numpy array format
+    sampling_rate=feature_extractor.sampling_rate, 
+    max_length=int(feature_extractor.sampling_rate * max_duration), 
+    padding=True, 
+    truncation=True, 
+    return_tensors='pt'
+)
+logits = mert(**inputs) # The logits shape is (batch_size, num_classes)
+```