feat: GPU-accelerated Whisper API for RTX 2080 (sm_75)

- Pure Rust: Axum 0.7 + whisper-rs 0.13 (CUDA FFI)
- Async job queue with SSE progress streaming
- Webhook delivery with 5x exponential backoff
- Disk-persisted job state (survives restarts)
- Anti-hallucination params: no_speech_thold, entropy_thold, suppress_blank
- CUDA sm_75 flags: GGML_CUDA_FORCE_MMQ, GGML_CUDA_GRAPHS, GGML_CUDA_FA_ALL_QUANTS
- Configurable via env: CUDA_DEVICE, WHISPER_MODEL_PATH, PORT, DATA_DIR
- Gitea Actions CI: build + push to git.sal.giize.com registry
- Multi-stage Dockerfile with customizable CUDA_VERSION ARG

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

.gitea/workflows/docker-build.yml

@@ -0,0 +1,69 @@
+name: Build & Push Docker Image
+
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - "v*"
+  pull_request:
+    branches:
+      - main
+
+env:
+  REGISTRY: git.sal.giize.com
+  IMAGE_NAME: mozempk/whisper-rtx2080
+  # Customizable CUDA version (override with repo variable CUDA_VERSION)
+  CUDA_VERSION: ${{ vars.CUDA_VERSION || '12.4.1' }}
+  UBUNTU_VERSION: ${{ vars.UBUNTU_VERSION || '22.04' }}
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Gitea Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ secrets.REGISTRY_USERNAME }}
+          password: ${{ secrets.REGISTRY_TOKEN }}
+
+      - name: Extract metadata (tags, labels)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            # tag with git sha on every push to main
+            type=sha,prefix=sha-,format=short,event=branch
+            # semver tags from git tags: v1.2.3 → 1.2.3, 1.2, 1, latest
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=semver,pattern={{major}}
+            # latest on main branch
+            type=raw,value=latest,enable=${{ github.ref == 'refs/heads/main' }}
+            # pr-N on pull requests
+            type=ref,event=pr
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          build-args: |
+            CUDA_VERSION=${{ env.CUDA_VERSION }}
+            UBUNTU_VERSION=${{ env.UBUNTU_VERSION }}
+          # Cache layers in the Gitea registry for faster rebuilds
+          cache-from: type=registry,ref=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:buildcache
+          cache-to: type=registry,ref=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:buildcache,mode=max
+          platforms: linux/amd64