6588130e36
- Value objects: ModelId, EngineName, Megabytes, AudioSamples, Segment, Transcript - KonError enum with thiserror - Constants centralised: audio pipeline, VAD, RAM thresholds, inference threading - SpeechToText and TextProcessor provider traits with ProviderRegistry - Unified model registry (Whisper tiny/base/small/medium + Parakeet CTC int8) - Hardware detection: probe_ram, probe_cpu, probe_gpu (stub), probe_os - Recommendation engine: score_model (pure function), rank_recommendations (sorted) - 5 tests passing, clippy clean Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
50 lines
1.7 KiB
Rust
50 lines
1.7 KiB
Rust
/// Audio pipeline constants.
|
|
pub const WHISPER_SAMPLE_RATE: u32 = 16_000;
|
|
pub const WHISPER_CHANNELS: u16 = 1;
|
|
|
|
/// Parakeet mel spectrogram constants.
|
|
pub const PARAKEET_N_FFT: usize = 512;
|
|
pub const PARAKEET_HOP_LENGTH: usize = 160;
|
|
pub const PARAKEET_WIN_LENGTH: usize = 400;
|
|
pub const PARAKEET_N_MELS: usize = 80;
|
|
pub const PARAKEET_PRE_EMPHASIS: f32 = 0.97;
|
|
pub const PARAKEET_BLANK_TOKEN: usize = 1024;
|
|
pub const PARAKEET_LOG_GUARD: f32 = 5.960_464_5e-8; // 2^-24
|
|
|
|
/// Chunk timing for live transcription.
|
|
pub const CHUNK_INTERVAL_MS: u64 = 3000;
|
|
pub const MIN_CHUNK_SAMPLES: usize = 8000;
|
|
|
|
/// Post-processing thresholds.
|
|
pub const SMART_PARAGRAPH_GAP_SECS: f64 = 2.0;
|
|
|
|
/// Thread count for inference. Leaves headroom for the UI thread.
|
|
pub const MIN_INFERENCE_THREADS: usize = 4;
|
|
|
|
/// History limits.
|
|
pub const HISTORY_MAX_ENTRIES: usize = 100;
|
|
|
|
/// RAM thresholds for model recommendations (in GB).
|
|
pub const RAM_MINIMUM_FOR_LOCAL_STT: f64 = 2.0;
|
|
pub const RAM_THRESHOLD_LIGHTWEIGHT: f64 = 4.0;
|
|
pub const RAM_THRESHOLD_STANDARD: f64 = 8.0;
|
|
pub const RAM_THRESHOLD_COMFORTABLE: f64 = 16.0;
|
|
|
|
/// VAD configuration defaults.
|
|
pub const VAD_SPEECH_THRESHOLD: f64 = 0.5;
|
|
pub const VAD_MIN_SPEECH_DURATION_MS: u32 = 250;
|
|
pub const VAD_MAX_SPEECH_DURATION_S: u32 = 30;
|
|
pub const VAD_MIN_SILENCE_DURATION_MS: u32 = 300;
|
|
pub const VAD_SPEECH_PAD_MS: u32 = 100;
|
|
|
|
/// Model download chunk size for progress reporting.
|
|
pub const DOWNLOAD_CHUNK_BYTES: usize = 65_536;
|
|
|
|
/// Inference thread count based on available parallelism.
|
|
pub fn inference_thread_count() -> usize {
|
|
std::thread::available_parallelism()
|
|
.map(|p| p.get().saturating_sub(1))
|
|
.unwrap_or(MIN_INFERENCE_THREADS)
|
|
.max(MIN_INFERENCE_THREADS)
|
|
}
|