fix: Resolve model loading and deployment issues

This commit fixes several critical issues that prevented the service from deploying correctly and loading the TTS models.

- **Fix Model Loading:** Corrected the volume mount path in  to point to the correct  source directory. The  engine code was also updated to use absolute paths () inside the container, making the model loading mechanism robust.
- **Update Session Resume:** The  has been updated to reflect the final debugging steps and the successful resolution of all issues.

docker-compose.yml

@@ -8,8 +8,8 @@ services:
     volumes:
       # Mount local app directory for hot-reloading in dev
       - ./app:/home/appuser/app
-      # Mount models directory to provide models to the container
-      - ./models:/home/appuser/app/models
+      # Mount models directory to a top-level directory in the container
+      - ./app/models:/models
       # Mount asset directory to persist generated audio files
       - ./asset:/home/appuser/app/asset
     command: ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]