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>

Cargo.toml

@@ -0,0 +1,52 @@
+[package]
+name    = "whisper-server"
+version = "0.1.0"
+edition = "2021"
+
+[[bin]]
+name = "whisper-server"
+path = "src/main.rs"
+
+[dependencies]
+# Web framework
+axum            = { version = "0.7", features = ["multipart"] }
+axum-extra      = { version = "0.9", features = ["typed-header"] }
+tokio           = { version = "1",   features = ["full"] }
+tokio-stream    = { version = "0.1", features = ["sync"] }
+tower           = { version = "0.4" }
+tower-http      = { version = "0.5", features = ["cors", "trace", "limit"] }
+
+# Whisper inference
+whisper-rs      = { version = "0.13", features = ["cuda"] }
+
+# Serialisation
+serde           = { version = "1", features = ["derive"] }
+serde_json      = "1"
+
+# OpenAPI / Swagger
+utoipa          = { version = "4", features = ["axum_extras", "uuid"] }
+utoipa-swagger-ui = { version = "7", features = ["axum"] }
+
+# HTTP client (webhooks)
+reqwest         = { version = "0.12", default-features = false, features = ["json", "rustls-tls"] }
+
+# Utilities
+uuid            = { version = "1", features = ["v4", "serde"] }
+tracing         = "0.1"
+tracing-subscriber = { version = "0.3", features = ["env-filter", "json"] }
+anyhow          = "1"
+thiserror       = "1"
+tempfile        = "3"
+num_cpus        = "1"
+chrono          = { version = "0.4", features = ["serde"] }
+tokio-util      = { version = "0.7", features = ["io"] }
+futures         = "0.3"
+async-stream    = "0.3"
+bytes           = "1"
+dashmap         = "6"
+
+[profile.release]
+opt-level     = 3
+lto           = "thin"
+codegen-units = 1
+strip         = "symbols"