Use official HuggingFace documentation approach to override model detection

v2.0.3 - DOCUMENTED APPROACH: Based on official HF Spaces config reference
1. Added models: [] to explicitly override automatic model detection
2. Added app_file: app.py to specify our Docker entrypoint
3. Removed unofficial .hf_config.json (not in HF docs)
4. Cleaned up .space_config.yaml to use only documented parameters
5. Per HF docs: 'Models will be parsed automatically from code if not specified'
6. Empty models: [] should prevent auto-detection of Moshi models

Following official HuggingFace Spaces documentation instead of guessing!

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

.hf_config.json

@@ -1,7 +0,0 @@
-{
-  "sdk": "docker",
-  "app_port": 7860,
-  "hardware": "l4",
-  "disable_auto_inference": true,
-  "force_docker": true
-}

.space_config.yaml

@@ -6,7 +6,7 @@ sdk: docker
 app_port: 7860
 hardware: l4
 sleep_time_timeout: 1800
-suggested_storage: standard
-disable_embedding: true
-custom_headers:
-  x-space-config: docker-only
+suggested_storage: small
+app_file: app.py
+models: []
+datasets: []

README.md

@@ -9,6 +9,9 @@ hardware: l4
 sleep_time_timeout: 1800
 suggested_storage: small
 pinned: false
+app_file: app.py
+models: []
+datasets: []
 ---
 
 # STT GPU Service Python v4

app.py

@@ -21,7 +21,7 @@ from fastapi.responses import JSONResponse, HTMLResponse
 import uvicorn
 
 # Version tracking
-VERSION = "2.0.2"
+VERSION = "2.0.3"
 COMMIT_SHA = "TBD"
 
 # Configure logging