feat: refactor transcription, translation, and distribution into multiple processes

main_v2.py

@@ -0,0 +1,84 @@
+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 sys
+import json
+import os
+from engine_transcribe import run_transcription
+from engine_translate import run_translation
+from engine_distribute import run_distribution
+
+def main():
+    config_path = "config.json"
+    defaults = {}
+    if os.path.exists(config_path):
+        with open(config_path, "r") as f:
+            defaults = json.load(f)
+
+    parser = argparse.ArgumentParser(description="Multi-process Transcription and Translation.")
+    
+    # Transcribe Args
+    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"))
+    parser.add_argument("--silence", type=int, default=defaults.get("silence", 1000))
+    parser.add_argument("--max-buffer", type=int, default=defaults.get("max_buffer", 20))
+    parser.add_argument("--channels", type=int, default=defaults.get("channels", 1))
+    
+    # Translate Args
+    parser.add_argument("-es", action="store_true", default=defaults.get("es", False), help="Enable Spanish translation")
+    parser.add_argument("-fr", action="store_true", default=defaults.get("fr", False), help="Enable French translation")
+    parser.add_argument("-ar", action="store_true", default=defaults.get("ar", False), help="Enable Arabic translation")
+    
+    # Distribute Args
+    parser.add_argument("-i", "--ingest", action="store_true", default=defaults.get("ingest", False), help="Enable data transmission to server")
+    
+    args = parser.parse_args()
+
+    # Queues for communication
+    # Transcribe -> Translate
+    q_trans_to_tl = multiprocessing.Queue()
+    # Translate -> Distribute
+    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_distribute = multiprocessing.Process(target=run_distribution, args=(q_tl_to_dist, args))
+
+    print("[Main] Starting processes...")
+    p_transcribe.start()
+    p_translate.start()
+    p_distribute.start()
+
+    try:
+        p_transcribe.join()
+        p_translate.join()
+        p_distribute.join()
+    except KeyboardInterrupt:
+        print("\n[Main] Stopping processes...")
+        p_transcribe.terminate()
+        p_translate.terminate()
+        p_distribute.terminate()
+        sys.exit(0)
+
+if __name__ == "__main__":
+    multiprocessing.freeze_support()
+    main()