tts engine.py

gradio_tabs/tab6_settings.py

@@ -303,6 +303,77 @@ def create_config_backup():
             outputs=[backup_status]
         )
 
+def create_chunking_test():
+    """Create chunking test interface."""
+    
+    with gr.Column():
+        gr.Markdown("## 🧪 Text Chunking Test")
+        gr.Markdown("Test and verify text chunking logic with custom parameters")
+        
+        with gr.Row():
+            with gr.Column(scale=2):
+                test_text = gr.Textbox(
+                    label="Test Text",
+                    placeholder="Enter custom test text (leave blank for default)...",
+                    lines=4
+                )
+            
+            with gr.Column(scale=1):
+                max_words = gr.Slider(
+                    minimum=5,
+                    maximum=100,
+                    value=30,
+                    step=1,
+                    label="Max Words per Chunk"
+                )
+                min_words = gr.Slider(
+                    minimum=1,
+                    maximum=20,
+                    value=4,
+                    step=1,
+                    label="Min Words per Chunk"
+                )
+        
+        test_btn = gr.Button("🧪 Run Chunking Test", variant="primary")
+        
+        results_output = gr.Textbox(
+            label="Test Results",
+            placeholder="Chunking test results will appear here...",
+            lines=15,
+            interactive=False
+        )
+        
+        def run_chunking_test(text_input, max_w, min_w):
+            """Run the chunking test"""
+            try:
+                from modules.text_processor import test_chunking
+                import io
+                import contextlib
+                
+                # Capture the test_chunking output
+                captured_output = io.StringIO()
+                
+                with contextlib.redirect_stdout(captured_output):
+                    test_chunking(
+                        text_input if text_input.strip() else None,
+                        max_w,
+                        min_w
+                    )
+                
+                # Get the captured results
+                results_text = captured_output.getvalue()
+                return results_text if results_text else "✅ Chunking test completed successfully"
+                
+            except Exception as e:
+                return f"❌ Error running chunking test: {str(e)}"
+        
+        # Wire up the test button
+        test_btn.click(
+            run_chunking_test,
+            inputs=[test_text, max_words, min_words],
+            outputs=[results_output]
+        )
+
 def create_system_info():
     """Create system information display."""
     
@@ -370,6 +441,10 @@ def create_settings_tab():
             with gr.Tab("🔧 Configuration"):
                 create_config_editor(config_manager)
             
+            # Chunking Test
+            with gr.Tab("🧪 Chunking Test"):
+                create_chunking_test()
+            
             # Backup & Restore
             with gr.Tab("💾 Backup"):
                 create_config_backup()

modules/tts_engine.py

@@ -288,7 +288,7 @@ def process_batch(
              chunk = chunk_data['text']
              boundary_type = chunk_data.get("boundary_type", "none")
              chunk_tts_params = chunk_data.get("tts_params", tts_params)
-             result = process_one_chunk(i, chunk, text_chunks_dir, audio_chunks_dir, voice_path, chunk_tts_params, start_time, total_chunks, punc_norm, basename, log_run_func, log_path, device, model, asr_model, boundary_type, enable_asr)
+             result = process_one_chunk(i, chunk, text_chunks_dir, audio_chunks_dir, voice_path, chunk_tts_params, start_time, total_chunks, punc_norm, basename, log_run_func, log_path, device, model, asr_model, boundary_type=boundary_type, enable_asr=enable_asr)
              results.append(result)
         return results
 
@@ -973,8 +973,8 @@ def process_book_folder(book_dir, voice_path, tts_params, device, skip_cleanup=F
                         global_chunk_index, chunk, text_chunks_dir, audio_chunks_dir,
                         voice_path, chunk_tts_params, start_time, total_chunks,
                         punc_norm, book_dir.name, log_run, log_path, device,
-                        model, asr_model, boundary_type,
-                        asr_enabled
+                        model, asr_model, boundary_type=boundary_type,
+                        enable_asr=asr_enabled
                     ))
 
                 # Wait for batch to complete