20s chunks and bugfix

audio_analyzer.py

@@ -70,7 +70,7 @@ class AudioAnalyzer:
         audio = audio[:600000]
 
         # Process in chunks to save memory
-        chunk_size = 10000  # Process in 10-second chunks
+        chunk_size = 20000  # Process in 20-second chunks
         processed_audio = AudioSegment.empty()
         
         for i in tqdm(range(0, len(audio), chunk_size), desc="Processing audio"):

utils.py

@@ -1,6 +1,6 @@
 import re
 
-def clean_trait(self, trait):
+def clean_trait(trait):
     # Remove line breaks, leading/trailing whitespace, and unnecessary dashes
     cleaned_trait = trait.replace('\n', '').strip()
     cleaned_trait = re.sub(r'^-+', '', cleaned_trait).strip()