Add OpenAI-compatible API and Docker deployment

- Add FastAPI-based API in whisperx/api/
- Implement transcription endpoint compatible with OpenAI
- Added Dockerfile and docker-compose.yml for easy deployment
- Updated README with Docker instructions
- Added new script whisperx-serve for running the API

docker-compose.yml

@@ -0,0 +1,28 @@
+version: '3.8'
+
+services:
+  whisperx-api:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - "8000:8000"
+    environment:
+      - WHISPERX_MODEL=turbo
+      - WHISPERX_DEVICE=cuda
+      - WHISPERX_COMPUTE_TYPE=float16
+    volumes:
+      # Mount Hugging Face cache if needed
+      - hf_cache:/app/.cache/huggingface
+    devices:
+      # Allow access to all GPUs
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    cap_add:
+      - SYS_ADMIN
+    security_opt:
+      - seccomp:unconfined
+    # For AMD ROCm GPUs, use device passthrough
+
+volumes:
+  hf_cache: