Create stats_data.py

stats_data.py

@@ -0,0 +1,34 @@
+import pandas as pd
+
+# Metadata for speakers available in the demo
+SPEAKER_META = {
+    "M05": {"Gender": "Male", "Severity": "Severe", "Dataset": "Torgo"},
+    "F01": {"Gender": "Female", "Severity": "Severe", "Dataset": "Torgo"},
+    "M01": {"Gender": "Male", "Severity": "Moderate", "Dataset": "Torgo"},
+    "M04": {"Gender": "Male", "Severity": "Moderate", "Dataset": "Torgo"},
+    "M02": {"Gender": "Male", "Severity": "Mild", "Dataset": "Torgo"},
+    "M03": {"Gender": "Male", "Severity": "Mild", "Dataset": "Torgo"},
+    "F03": {"Gender": "Female", "Severity": "Mild", "Dataset": "Torgo"},
+    "F04": {"Gender": "Female", "Severity": "Mild", "Dataset": "Torgo"},
+    "F02 (UA)": {"Gender": "Female", "Severity": "Severe (Isolated)", "Dataset": "UA-Speech"}
+}
+
+def get_indomain_breakdown():
+    data = {
+        "Speaker": ["M05", "F01", "M01", "M04", "M02", "M03", "F03", "F04"],
+        "Severity": ["Severe", "Severe", "Moderate", "Moderate", "Mild", "Mild", "Mild", "Mild"],
+        "Whisper Tiny": ["12.1%", "12.6%", "32.7%", "31.8%", "62.1%", "58.4%", "61.2%", "59.1%"],
+        "5K Model (Ours)": ["33.1%", "34.2%", "47.2%", "45.6%", "84.5%", "81.8%", "83.5%", "82.8%"],
+        "10K Model (Ours)": ["25.4%", "24.1%", "44.1%", "41.2%", "79.1%", "77.5%", "79.0%", "78.2%"]
+    }
+    return pd.DataFrame(data)
+
+def get_experimental_summary():
+    data = {
+        "Experiment Condition": ["In-Domain (Seen Torgo)", "LOSO (Unseen Torgo F01)", "Zero-Shot (UA-Speech F02)"],
+        "Whisper Tiny (Baseline)": ["41.50%", "12.38%", "4.33%"],
+        "5K Pure Model Score": ["58.77%", "N/A", "6.19%"],
+        "10K Triple-Mix Score": ["54.67%", "24.76%", "5.98%"],
+        "Relative Gain (Best vs Baseline)": ["+41.6%", "+100.0%", "+42.9%"]
+    }
+    return pd.DataFrame(data)