add model selection and expanded language support to /transcribe endpoint

Closes #233

backend/backends/__init__.py

@@ -134,6 +134,7 @@ class STTBackend(Protocol):
         self,
         audio_path: str,
         language: Optional[str] = None,
+        model_size: Optional[str] = None,
     ) -> str:
         """
         Transcribe audio to text.

backend/backends/mlx_backend.py

@@ -345,18 +345,20 @@ class MLXSTTBackend:
         self,
         audio_path: str,
         language: Optional[str] = None,
+        model_size: Optional[str] = None,
     ) -> str:
         """
         Transcribe audio to text.
 
         Args:
             audio_path: Path to audio file
-            language: Optional language hint (en or zh)
+            language: Optional language hint
+            model_size: Optional model size override
 
         Returns:
             Transcribed text
         """
-        await self.load_model_async(None)
+        await self.load_model_async(model_size)
 
         def _transcribe_sync():
             """Run synchronous transcription in thread pool."""

backend/backends/pytorch_backend.py

@@ -306,18 +306,20 @@ class PyTorchSTTBackend:
         self,
         audio_path: str,
         language: Optional[str] = None,
+        model_size: Optional[str] = None,
     ) -> str:
         """
         Transcribe audio to text.
 
         Args:
             audio_path: Path to audio file
-            language: Optional language hint (en or zh)
+            language: Optional language hint
+            model_size: Optional model size override
 
         Returns:
             Transcribed text
         """
-        await self.load_model_async(None)
+        await self.load_model_async(model_size)
 
         def _transcribe_sync():
             """Run synchronous transcription in thread pool."""

backend/models.py

@@ -149,7 +149,8 @@ class HistoryListResponse(BaseModel):
 class TranscriptionRequest(BaseModel):
     """Request model for audio transcription."""
 
-    language: Optional[str] = Field(None, pattern="^(en|zh)$")
+    language: Optional[str] = Field(None, pattern="^(en|zh|ja|ko|de|fr|ru|pt|es|it)$")
+    model: Optional[str] = Field(None, pattern="^(base|small|medium|large|turbo)$")
 
 
 class TranscriptionResponse(BaseModel):

backend/routes/transcription.py

@@ -20,6 +20,7 @@ UPLOAD_CHUNK_SIZE = 1024 * 1024  # 1MB
 async def transcribe_audio(
     file: UploadFile = File(...),
     language: str | None = Form(None),
+    model: str | None = Form(None),
 ):
     """Transcribe audio file to text."""
     with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp:
@@ -29,14 +30,23 @@ async def transcribe_audio(
 
     try:
         from ..utils.audio import load_audio
+        from ..backends import WHISPER_HF_REPOS
 
         audio, sr = await asyncio.to_thread(load_audio, tmp_path)
         duration = len(audio) / sr
 
         whisper_model = transcribe.get_whisper_model()
-        model_size = whisper_model.model_size
+        model_size = model if model else whisper_model.model_size
 
-        if not whisper_model.is_loaded() and not whisper_model._is_model_cached(model_size):
+        valid_sizes = list(WHISPER_HF_REPOS.keys())
+        if model_size not in valid_sizes:
+            raise HTTPException(
+                status_code=400,
+                detail=f"Invalid model size '{model_size}'. Must be one of: {', '.join(valid_sizes)}",
+            )
+
+        already_loaded = whisper_model.is_loaded() and whisper_model.model_size == model_size
+        if not already_loaded and not whisper_model._is_model_cached(model_size):
             progress_model_name = f"whisper-{model_size}"
             task_manager = get_task_manager()
 
@@ -59,7 +69,7 @@ async def transcribe_audio(
                 },
             )
 
-        text = await whisper_model.transcribe(tmp_path, language)
+        text = await whisper_model.transcribe(tmp_path, language, model_size)
 
         return models.TranscriptionResponse(
             text=text,