Jake
8b49d0fe9c
New crates/transcription/src/transcriber.rs defines a Transcriber trait (Send supertrait for spawn_blocking travel) with TranscriberCapabilities (sample_rate, channels, supports_initial_prompt). TranscriberCapabilities.sample_rate is load-bearing for the upcoming progressive WAV writer (#19). Concrete impls: - SpeechModelAdapter wraps Box<dyn transcribe_rs::SpeechModel + Send> for Parakeet (and any future transcribe-rs-backed engine). - WhisperRsBackend moves its transcribe_sync body into the impl, widening the signature from &self to &mut self so per-call WhisperState can be created cleanly through the trait object. LocalEngine now holds Box<dyn Transcriber + Send>; dispatch in transcribe_sync collapses from a match to a direct call. Adds LocalEngine::capabilities() for the WAV-writer. Cargo feature flag "whisper" (default on) makes whisper-rs, num_cpus, and the whole whisper_rs_backend module optional. cargo check --no-default-features -p kon-transcription now builds without pulling whisper-rs-sys — the escape hatch brief item #6 / #13 called for on Windows / non-AVX2 / cloud-only builds. load_whisper is cfg-gated behind the same feature. src-tauri/src/commands/models.rs load_model_from_disk returns Box<dyn Transcriber + Send> instead of SpeechBackend; caller chain (ensure_model_loaded, prewarm_default_model) is unchanged. transcriber_trait_is_object_safe test lands alongside the trait as a compile-time witness against future Self-returning / generic-method additions.
52 lines
1.8 KiB
TOML
52 lines
1.8 KiB
TOML
[package]
|
|
name = "kon-transcription"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
description = "Speech-to-text engine wrappers, model management, and inference concurrency for Kon"
|
|
build = "build.rs"
|
|
|
|
[features]
|
|
# Whisper backend (direct whisper-rs, vulkan-accelerated). Default on —
|
|
# gating it exists so a future Windows non-AVX2 build, or a cloud-only
|
|
# ASR configuration, can drop whisper-rs-sys entirely per brief item
|
|
# #13. Disabling this feature also drops the WhisperRsBackend module
|
|
# and the load_whisper entry point.
|
|
default = ["whisper"]
|
|
whisper = ["dep:whisper-rs", "dep:num_cpus"]
|
|
|
|
[dependencies]
|
|
kon-core = { path = "../core" }
|
|
|
|
# Parakeet via ONNX. Whisper is handled directly via whisper-rs below.
|
|
transcribe-rs = { version = "0.3", default-features = false, features = ["onnx"] }
|
|
|
|
# Async runtime for spawn_blocking
|
|
tokio = { version = "1", features = ["rt", "sync"] }
|
|
|
|
# Model downloads
|
|
reqwest = { version = "0.12", features = ["stream"] }
|
|
futures-util = "0.3"
|
|
|
|
# Download integrity verification
|
|
sha2 = "0.10"
|
|
|
|
# Gated behind the `whisper` feature (see [features] above).
|
|
whisper-rs = { version = "0.16", default-features = false, features = ["vulkan"], optional = true }
|
|
|
|
# Direct whisper-rs backend (WhisperRsBackend): thread pool sizing.
|
|
# Gated alongside whisper-rs since no other code in this crate needs it.
|
|
num_cpus = { version = "1", optional = true }
|
|
|
|
# Typed error enum used by WhisperRsBackend + elsewhere. Kept
|
|
# unconditional because it is a derive-macro crate with negligible
|
|
# build cost.
|
|
thiserror = "2"
|
|
|
|
# Structured logging at backend boundaries (observability for initial_prompt flow).
|
|
tracing = "0.1"
|
|
|
|
[dev-dependencies]
|
|
# TcpListener fixture for the download resume tests (mirrors kon-llm).
|
|
tokio = { version = "1", features = ["rt", "sync", "net", "io-util", "macros"] }
|
|
tempfile = "3"
|