Upload 3 files

app.py

@@ -0,0 +1,66 @@
+import gradio as gr
+from similarity import CLAPSimilarity
+import matplotlib.pyplot as plt
+
+# Initialize the CLAPSimilarity instance
+similarity_calculator = CLAPSimilarity(training_embeddings_prefix='training')
+
+def process_query(text, audio_file, max_tracks):
+    if text and not audio_file:
+        # Process text input
+        similarity_scores = similarity_calculator.compute_similarity(
+            input_data=text,
+            input_type='text',
+            max_tracks=int(max_tracks)  # Use user-defined max_tracks
+        )
+    elif audio_file and not text:
+        # Process audio input
+        similarity_scores = similarity_calculator.compute_similarity(
+            input_data=audio_file,
+            input_type='audio',
+            max_tracks=int(max_tracks)  # Use user-defined max_tracks
+        )
+    else:
+        return "Please provide either text or audio input."
+    
+    # Calculate the total sum of scores
+    total_score = sum(similarity_scores.values())
+
+    # Normalize the scores to sum to 100%
+    normalized_scores = {
+        filename: (score / total_score) * 100
+        for filename, score in similarity_scores.items()
+    }
+
+    # Prepare the output data with normalized scores
+    data = [
+        [filename, round(score, 2)] 
+        for filename, score in normalized_scores.items()
+    ]
+    return data
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        text_input = gr.Textbox(label="Enter text query")
+        audio_input = gr.Audio(label="Upload audio", type="filepath")
+        max_tracks_input = gr.Number(
+            label="Max Tracks", value=10, precision=0
+        )  # Add this input field
+
+    with gr.Row():
+        submit_btn = gr.Button("Submit")
+    
+    output_table = gr.Dataframe(
+        headers=["Filename", "Score"],
+        label="Similarity Results",
+        datatype=["str", "number"],
+        interactive=False
+    )
+
+    submit_btn.click(
+        fn=process_query,
+        inputs=[text_input, audio_input, max_tracks_input],  # Include max_tracks_input
+        outputs=[output_table]
+    )
+
+demo.launch()

training_embeddings.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0ef953a91710e1193e89a7ffa258e5d9f96e236997914823f58681586c9ea7
+size 20608