Update evaluate.py

evaluate.py

@@ -814,7 +814,132 @@ def handle_evaluation_request(request, reference_dir, output_dir, sample_rate):
         resume_preprocessing()
         return response
 
-        # Add a new function to get preprocessing status
+def handle_upload_reference(request, reference_dir, sample_rate):
+    """Handle upload of reference audio files and preprocess immediately"""
+    global REFERENCE_CACHE
+    
+    # Pause preprocessing while handling user request
+    pause_preprocessing()
+    
+    try:
+        if "audio" not in request.files:
+            logger.warning("⚠️ Reference upload missing audio file")
+            # Resume preprocessing before returning
+            resume_preprocessing()
+            return jsonify({"error": "No audio file uploaded"}), 400
+
+        reference_word = request.form.get("reference_word", "").strip()
+        if not reference_word:
+            logger.warning("⚠️ Reference upload missing reference word")
+            # Resume preprocessing before returning
+            resume_preprocessing()
+            return jsonify({"error": "No reference word provided"}), 400
+
+        # Validate reference word
+        reference_patterns = [
+            "mayap_a_abak", "mayap_a_ugtu", "mayap_a_gatpanapun", "mayap_a_bengi",
+            "komusta_ka", "malaus_ko_pu", "malaus_kayu", "agaganaka_da_ka",
+            "pagdulapan_da_ka", "kaluguran_da_ka", "dakal_a_salamat", "panapaya_mu_ku",
+            "wa", "ali", "tuknang", "lagwa", "galo", "buri_ke_ini", "tara_na",  
+            "nokarin_ka_ibat", "nokarin_ka_munta", "atiu_na_ku", "nanung_panayan_mu",  
+            "mako_na_ka", "muli_ta_na", "nanu_ing_pengan_mu", "mekeni", "mengan_na_ka",   
+            "munta_ka_karin", "magkanu_ini", "mimingat_ka", "mangan_ta_na", "lakwan_da_ka",  
+            "nanu_maliari_kung_daptan_keka", "pilan_na_ka_banwa", "saliwan_ke_ini",  
+            "makananu_munta_king", "adwa", "anam", "apat", "apulu", "atlu", "dinalan", "libu", "lima",  
+            "metung", "pitu", "siyam", "walu", "masala", "madalumdum", "maragul", "marimla", "malagu", "marok", "mababa", "malapit", "matuling", "maputi", 
+            "arung", "asbuk", "balugbug", "bitis", "buntuk", "butit", "gamat", "kuku", "salu", "tud", 
+            "pisan", "dara", "achi", "apu", "ima", "tatang", "pengari", "koya", "kapatad", "wali", 
+            "pasbul", "awang", "dagis", "bale", "ulas", "sambra", "sulu", "pitudturan", "luklukan", "ulnan"
+        ]
+
+        if reference_word not in reference_patterns:
+            logger.warning(f"⚠️ Invalid reference word: {reference_word}")
+            # Resume preprocessing before returning
+            resume_preprocessing()
+            return jsonify({"error": f"Invalid reference word. Available: {reference_patterns}"}), 400
+
+        # Make sure we have a writable reference directory
+        if not os.path.exists(reference_dir):
+            reference_dir = os.path.join('/tmp', 'reference_audios')
+            os.makedirs(reference_dir, exist_ok=True)
+            logger.warning(f"⚠️ Using alternate reference directory for upload: {reference_dir}")
+
+        # Create directory for reference pattern if it doesn't exist
+        pattern_dir = os.path.join(reference_dir, reference_word)
+        os.makedirs(pattern_dir, exist_ok=True)
+
+        # Save the reference audio file
+        audio_file = request.files["audio"]
+        filename = secure_filename(audio_file.filename)
+        
+        # Ensure filename has .wav extension
+        if not filename.lower().endswith('.wav'):
+            base_name = os.path.splitext(filename)[0]
+            filename = f"{base_name}.wav"
+            
+        file_path = os.path.join(pattern_dir, filename)
+        
+        # Create a temporary file first, then convert to WAV
+        with tempfile.NamedTemporaryFile(delete=False) as temp_file:
+            audio_file.save(temp_file.name)
+            temp_path = temp_file.name
+        
+        try:
+            # Process the audio file
+            audio = AudioSegment.from_file(temp_path)
+            audio = audio.set_frame_rate(sample_rate).set_channels(1)
+            audio.export(file_path, format="wav")
+            logger.info(f"✅ Reference audio saved successfully for {reference_word}: {file_path}")
+            
+            # Clean up temp file
+            try:
+                os.unlink(temp_path)
+            except:
+                pass
+                
+            # Immediately preprocess this new reference file and add to cache
+            asr_model = get_asr_model()
+            asr_processor = get_asr_processor()
+            
+            if asr_model and asr_processor:
+                # Initialize cache for this pattern if needed
+                if reference_word not in REFERENCE_CACHE:
+                    REFERENCE_CACHE[reference_word] = {}
+                    
+                # Preprocess and add to cache
+                result = preprocess_reference_file(file_path, sample_rate, asr_model, asr_processor)
+                if result:
+                    REFERENCE_CACHE[reference_word][filename] = result
+                    logger.info(f"✅ New reference audio preprocessed and added to cache: {filename}")
+            
+        except Exception as e:
+            logger.error(f"❌ Reference audio processing failed: {str(e)}")
+            # Resume preprocessing before returning
+            resume_preprocessing()
+            return jsonify({"error": f"Audio processing failed: {str(e)}"}), 500
+
+        # Count how many references we have now
+        references = glob.glob(os.path.join(pattern_dir, "*.wav"))
+        
+        # Resume preprocessing before returning
+        resume_preprocessing()
+        return jsonify({
+            "message": "Reference audio uploaded successfully",
+            "reference_word": reference_word,
+            "file": filename,
+            "total_references": len(references),
+            "preprocessed": True
+        })
+
+    except Exception as e:
+        logger.error(f"❌ Unhandled exception in reference upload: {str(e)}")
+        logger.debug(f"Stack trace: {traceback.format_exc()}")
+        
+        # Make sure to resume preprocessing even if there's an error
+        resume_preprocessing()
+        return jsonify({"error": f"Internal server error: {str(e)}"}), 500
+
+# Add a new function to get preprocessing status
 def get_preprocessing_status():
     """Get the current status of reference audio preprocessing"""
     global PREPROCESSING_COMPLETE, REFERENCE_CACHE, PREPROCESSING_ACTIVE, PREPROCESSING_PAUSE