testing sample audios fix

.gitattributes

@@ -32,4 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -textss
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+audios/*.wav filter=lfs diff=lfs merge=lfs -text

backend/session_manager.py

@@ -111,40 +111,60 @@ class SessionManager:
         # Sample clips (for the reference/sample section)
         # Use hardcoded reference audio files instead of dataset clips
         import os
+        import base64
+        
         mos_dir = os.path.dirname(os.path.dirname(__file__))
         audios_dir = os.path.join(mos_dir, "audios")
         
         male_path = os.path.join(audios_dir, "male.wav")
         female_path = os.path.join(audios_dir, "female.wav")
         
-        print(f"[INFO] Sample audio paths:")
-        print(f"  Male: {male_path} (exists: {os.path.exists(male_path)})")
-        print(f"  Female: {female_path} (exists: {os.path.exists(female_path)})")
-        if os.path.exists(male_path):
-            print(f"  Male file size: {os.path.getsize(male_path)} bytes")
-        if os.path.exists(female_path):
-            print(f"  Female file size: {os.path.getsize(female_path)} bytes")
+        # Helper function to load audio as base64 data URL (for LFS compatibility)
+        def load_audio_as_data_url(path):
+            if os.path.exists(path):
+                try:
+                    with open(path, "rb") as f:
+                        audio_bytes = f.read()
+                    # Check if it's an LFS pointer (small text file)
+                    if len(audio_bytes) < 200 and b"version https://git-lfs.github.com" in audio_bytes:
+                        print(f"[WARN] {path} is an LFS pointer, cannot load")
+                        return None
+                    b64 = base64.b64encode(audio_bytes).decode("ascii")
+                    return f"data:audio/wav;base64,{b64}"
+                except Exception as e:
+                    print(f"[ERROR] Failed to load {path}: {e}")
+                    return None
+            print(f"[ERROR] File not found: {path}")
+            return None
+        
+        male_audio = load_audio_as_data_url(male_path)
+        female_audio = load_audio_as_data_url(female_path)
         
-        sample_clips = [
-            Clip(
-                id="reference_male",
-                model="reference",
-                speaker="male",
-                exercise="reference",
-                exercise_id="ref_male",
-                transcript="TENGAH Approach to CAMEL, CAMEL identified on squawk, QNH 29.80, Delta 4 hot, report abeam Tuas.",
-                audio_url=male_path,
-            ),
-            Clip(
-                id="reference_female",
-                model="reference",
-                speaker="female",
-                exercise="reference",
-                exercise_id="ref_female",
-                transcript="JOHOR climbing to flight level 300, contact Approach on 123.45.",
-                audio_url=female_path,
-            ),
-        ]
+        sample_clips = []
+        if male_audio:
+            sample_clips.append(
+                Clip(
+                    id="reference_male",
+                    model="reference",
+                    speaker="male",
+                    exercise="reference",
+                    exercise_id="ref_male",
+                    transcript="TENGAH Approach to CAMEL, CAMEL identified on squawk, QNH 29.80, Delta 4 hot, report abeam Tuas.",
+                    audio_url=male_audio,
+                )
+            )
+        if female_audio:
+            sample_clips.append(
+                Clip(
+                    id="reference_female",
+                    model="reference",
+                    speaker="female",
+                    exercise="reference",
+                    exercise_id="ref_female",
+                    transcript="JOHOR climbing to flight level 300, contact Approach on 123.45.",
+                    audio_url=female_audio,
+                )
+            )
 
         session_data: Dict[str, Any] = {
             "session_id": session_id,