swarm-stt: the speech-to-text core (hash cache, shared runs, ffmpeg and whisper-cli engine)

swarm-stt/src/lib.rs

@@ -0,0 +1,20 @@
+//! The speech-to-text core of the swarm's `swarm-stt` service.
+//!
+//! [`Service::transcribe`] takes the bytes of a voice memo and answers its
+//! text. Three things stand between the bytes and the engine:
+//!
+//! - a size cap, so one oversized file cannot occupy the engine;
+//! - a cache keyed by the SHA-256 of the bytes, so the same memo sent to
+//!   several agents is transcribed once ([`cache`]); and
+//! - an in-flight map, so two requests for one memo that arrive together share
+//!   one engine run instead of starting two.
+//!
+//! The engine is behind the [`Engine`] trait. [`engine::Whisper`] decodes with
+//! `ffmpeg` and transcribes with `whisper-cli`; the tests use a fake.
+
+pub mod cache;
+pub mod engine;
+mod service;
+
+pub use engine::Engine;
+pub use service::{Config, Error, Reply, Service};