fix(stt): change default model to large-v3 (large-v3-turbo not supported by lightning-whisper-mlx)

services/mana-stt/app/main.py

@@ -24,7 +24,7 @@ logger = logging.getLogger(__name__)
 
 # Environment
 PORT = int(os.getenv("PORT", "3020"))
-DEFAULT_WHISPER_MODEL = os.getenv("WHISPER_MODEL", "large-v3-turbo")
+DEFAULT_WHISPER_MODEL = os.getenv("WHISPER_MODEL", "large-v3")
 PRELOAD_MODELS = os.getenv("PRELOAD_MODELS", "false").lower() == "true"
 CORS_ORIGINS = os.getenv(
     "CORS_ORIGINS",

services/mana-stt/app/whisper_service.py

@@ -24,7 +24,7 @@ class TranscriptionResult:
     segments: Optional[list] = None
 
 
-def get_whisper_model(model_name: str = "large-v3-turbo", batch_size: int = 12):
+def get_whisper_model(model_name: str = "large-v3", batch_size: int = 12):
     """Get or create Whisper model instance (singleton pattern)."""
     global _whisper_model
 
@@ -54,7 +54,7 @@ def get_whisper_model(model_name: str = "large-v3-turbo", batch_size: int = 12):
 def transcribe_audio(
     audio_path: str,
     language: Optional[str] = None,
-    model_name: str = "large-v3-turbo",
+    model_name: str = "large-v3",
 ) -> TranscriptionResult:
     """
     Transcribe audio file using Lightning Whisper MLX.
@@ -105,7 +105,7 @@ async def transcribe_audio_bytes(
     audio_bytes: bytes,
     filename: str,
     language: Optional[str] = None,
-    model_name: str = "large-v3-turbo",
+    model_name: str = "large-v3",
 ) -> TranscriptionResult:
     """
     Transcribe audio from bytes (for API uploads).
@@ -142,20 +142,15 @@ async def transcribe_audio_bytes(
             pass
 
 
-# Available models for reference
+# Available models for Lightning Whisper MLX
 AVAILABLE_MODELS = [
     "tiny",
-    "tiny.en",
-    "base",
-    "base.en",
     "small",
-    "small.en",
+    "base",
     "medium",
-    "medium.en",
     "large",
     "large-v2",
-    "large-v3",
-    "large-v3-turbo",  # Recommended for Mac Mini
+    "large-v3",  # Recommended for Mac Mini
     "distil-small.en",
     "distil-medium.en",
     "distil-large-v2",

services/mana-stt/setup.sh

@@ -89,13 +89,13 @@ python -c "import mlx; print(f'   MLX installed')" 2>/dev/null || echo "   MLX n
 python -c "import fastapi; print(f'   FastAPI {fastapi.__version__}')"
 
 echo ""
-echo "6. Downloading Whisper model (large-v3-turbo)..."
-echo "   This will download ~1.6 GB on first run..."
+echo "6. Downloading Whisper model (large-v3)..."
+echo "   This will download ~2.9 GB on first run..."
 # Pre-download the model
 python -c "
 from lightning_whisper_mlx import LightningWhisperMLX
 print('   Initializing Whisper model...')
-whisper = LightningWhisperMLX(model='large-v3-turbo', batch_size=12)
+whisper = LightningWhisperMLX(model='large-v3', batch_size=12)
 print('   Whisper model ready!')
 " || echo "   Note: Model will be downloaded on first transcription request"