feat: implement accumulative LLM paragraph engine and harden 4-process pipeline

main_v2.py

@@ -1,26 +1,16 @@
-import sys
-from unittest.mock import MagicMock
-
-# Comprehensive workaround for missing _lzma in some Python builds
-try:
-    import lzma
-except ImportError:
-    mock_lzma = MagicMock()
-    mock_lzma.FORMAT_XZ = 1
-    mock_lzma.FORMAT_ALONE = 2
-    mock_lzma.FORMAT_RAW = 3
-    mock_lzma.CHECK_NONE = 0
-    mock_lzma.CHECK_CRC32 = 1
-    mock_lzma.CHECK_CRC64 = 4
-    mock_lzma.CHECK_SHA256 = 10
-    sys.modules["_lzma"] = MagicMock()
-    sys.modules["lzma"] = mock_lzma
-
 import multiprocessing
 import argparse
 import json
 import os
-from engine_transcribe import run_transcription
+import sys
+from dotenv import load_dotenv
+
+# Load environment variables from .env if present
+load_dotenv()
+
+# Light imports (heavy ones moved inside run functions)
+from engine_transcribe import run_transcription, list_audio_devices
+from engine_llm import run_llm_processor
 from engine_translate import run_translation
 from engine_distribute import run_distribution
 
@@ -40,6 +30,7 @@ def main():
     parser = argparse.ArgumentParser(description="Multi-process Transcription and Translation.")
     
     # Transcribe Args
+    parser.add_argument("-l", "--list-devices", action="store_true", help="Show available audio devices and exit")
     parser.add_argument("--model", type=str, default=defaults.get("model", "mlx-community/whisper-base-mlx"))
     parser.add_argument("--device", type=int, default=defaults.get("device"))
     parser.add_argument("--lang", type=str, default=defaults.get("lang"))
@@ -55,15 +46,17 @@ def main():
     parser.add_argument("--logprob-threshold", type=float, default=defaults.get("logprob_threshold", -0.8))
     parser.add_argument("--compression-threshold", type=float, default=defaults.get("compression_threshold", 2.2))
     
+    # LLM Args
+    parser.add_argument("--post-correct", action="store_true", default=defaults.get("post_correct", False))
+    parser.add_argument("--post-correct-llm", action="store_true", default=defaults.get("post_correct_llm", False))
+    parser.add_argument("--post-correct-model", type=str, default=defaults.get("post_correct_model", "qwen:2b"))
+    parser.add_argument("--llm-paragraph", action="store_true", default=defaults.get("llm_paragraph", False))
+
     # Translate Args
     parser.add_argument("-es", action="store_true", default=defaults.get("es", False))
     parser.add_argument("-fr", action="store_true", default=defaults.get("fr", False))
     parser.add_argument("-ar", action="store_true", default=defaults.get("ar", False))
     parser.add_argument("-en", action="store_true", default=defaults.get("en", False))
-    parser.add_argument("--post-correct", action="store_true", default=defaults.get("post_correct", False))
-    parser.add_argument("--post-correct-llm", action="store_true", default=defaults.get("post_correct_llm", False))
-    parser.add_argument("--post-correct-model", type=str, default=defaults.get("post_correct_model", "qwen:2b"))
-    parser.add_argument("--llm-paragraph", action="store_true", default=defaults.get("llm_paragraph", False))
     parser.add_argument("--mt-max-chars", type=int, default=defaults.get("mt_max_chars", 250))
     parser.add_argument("--mt-max-new-tokens", type=int, default=defaults.get("mt_max_new_tokens", 150))
     parser.add_argument("--mt-num-beams", type=int, default=defaults.get("mt_num_beams", 4))
@@ -73,27 +66,49 @@ def main():
     
     args = parser.parse_args()
 
+    # Handle device listing
+    if args.list_devices:
+        list_audio_devices()
+        return
+
+    # Handle interactive device selection
+    if args.device is None:
+        list_audio_devices()
+        try:
+            val = input("\nSelect input device index (or press Enter for default): ").strip()
+            if val:
+                args.device = int(val)
+        except EOFError:
+            pass # Non-interactive environment
+        except ValueError:
+            print("[Main] Invalid index, using default.")
+
     # Queues
-    q_trans_to_tl = multiprocessing.Queue()
+    q_trans_to_llm = multiprocessing.Queue()
+    q_llm_to_tl = multiprocessing.Queue()
     q_tl_to_dist = multiprocessing.Queue()
 
     # Processes
-    p_transcribe = multiprocessing.Process(target=run_transcription, args=(q_trans_to_tl, args))
-    p_translate = multiprocessing.Process(target=run_translation, args=(q_trans_to_tl, q_tl_to_dist, args))
+    p_transcribe = multiprocessing.Process(target=run_transcription, args=(q_trans_to_llm, args))
+    p_llm = multiprocessing.Process(target=run_llm_processor, args=(q_trans_to_llm, q_llm_to_tl, args))
+    p_translate = multiprocessing.Process(target=run_translation, args=(q_llm_to_tl, q_tl_to_dist, args))
     p_distribute = multiprocessing.Process(target=run_distribution, args=(q_tl_to_dist, args))
 
     print("[Main] Starting processes...")
     p_transcribe.start()
+    p_llm.start()
     p_translate.start()
     p_distribute.start()
 
     try:
         p_transcribe.join()
+        p_llm.join()
         p_translate.join()
         p_distribute.join()
     except KeyboardInterrupt:
         print("\n[Main] Stopping processes...")
         p_transcribe.terminate()
+        p_llm.terminate()
         p_translate.terminate()
         p_distribute.terminate()
         sys.exit(0)