Lumotia/docs/architecture-map/03-audio-transcription/transcription-parakeet.md

name, type, slice, last_verified

name	type	slice	last_verified
Parakeet backend (transcribe-rs ONNX)	architecture-map-page	03-audio-transcription	2026/05/09

Parakeet backend (transcribe-rs ONNX)

Where you are: Architecture map → Audio + Transcription → Parakeet backend

Plain English summary. Parakeet is loaded via transcribe-rs 0.3 with the onnx feature. The model itself is wrapped in a thin ParakeetWordGranularity shim that overrides the trait method to request word-level timestamps (instead of the default per-subword "T Est Ing" output). The shim is then wrapped in SpeechModelAdapter so the rest of the engine sees a uniform Transcriber. There is no Cargo feature for Parakeet today: the dep is unconditional.

At a glance

• Crate: lumotia-transcription
• Path: crates/transcription/src/local_engine.rs:167 (the ParakeetWordGranularity shim) and :197 (load_parakeet).
• LOC (Parakeet-specific code): ~40.
• External deps: transcribe-rs 0.3 with default-features = false, features = ["onnx"].
• Internal callers (best effort, slice 2 reconciles): src-tauri/src/commands/models.rs calls load_parakeet from the model-load command path.

Public surface:

• pub fn load_parakeet(model_dir: &Path) -> Result<Box<dyn Transcriber + Send>> — crates/transcription/src/local_engine.rs:197.
• pub use transcribe_rs::SpeechModel — re-exported in lib.rs:18 for any caller that wants to hold a raw SpeechModel.

What's in here

ParakeetWordGranularity (private struct)

local_engine.rs:167. Wraps transcribe_rs::onnx::parakeet::ParakeetModel. Implements transcribe_rs::SpeechModel by forwarding capabilities(), default_leading_silence_ms(), default_trailing_silence_ms() to the inner model, but overriding transcribe_raw:

fn transcribe_raw(&mut self, samples, options) -> ...TranscriptionResult... {
    use transcribe_rs::onnx::parakeet::{ParakeetParams, TimestampGranularity};
    let params = ParakeetParams {
        language: options.language.clone(),
        timestamp_granularity: Some(TimestampGranularity::Word),
    };
    self.0.transcribe_with(samples, &params)
}

Why this exists: transcribe-rs 0.3's blanket SpeechModel impl for ParakeetModel::transcribe_raw ignores TranscribeOptions and uses TimestampGranularity::Token (per-subword), which surfaces in Lumotia as T Est Ing . One , Two , Three output. The concrete-type method ParakeetModel::transcribe_with accepts ParakeetParams with an explicit granularity. The shim exposes that to the trait object.

load_parakeet

local_engine.rs:197. ParakeetModel::load(model_dir, &Quantization::Int8) then wraps:

SpeechModelAdapter(Box::new(ParakeetWordGranularity(model)))

Hardcodes Quantization::Int8. No feature flag; no caller-side override.

Data flow

samples (f32, 16 kHz mono)
options: TranscriptionOptions { language, initial_prompt }  // initial_prompt discarded
   └─ SpeechModelAdapter::transcribe_sync
       └─ TranscribeOptions {
              language,
              translate: false,
              leading_silence_ms: None,
              trailing_silence_ms: None,
          }
       └─ ParakeetWordGranularity::transcribe_raw
           └─ ParakeetParams { language, timestamp_granularity: Word }
           └─ ParakeetModel::transcribe_with
       └─ TranscriptionResult { segments: Option<Vec<...>> }
   → Vec<Segment> (start_secs, end_secs as f64; text)

Watch-outs

• initial_prompt is silently discarded. SpeechModelAdapter::transcribe_sync does not look at it. The capability flag on TranscriberCapabilities { supports_initial_prompt: false } is what tells the UI to hide the field. Don't let a UI refactor accidentally show it.
• Quantisation is locked to Int8. No way to pick FP16 or FP32 today without editing load_parakeet. May matter for accuracy / VRAM trade-offs on bigger Parakeet variants.
• Segment timestamps already come back in seconds. Unlike whisper-rs's centiseconds, transcribe-rs returns floats already in seconds. The as f64 casts in SpeechModelAdapter are widening, not unit conversion.
• No Cargo feature gate. transcribe-rs is always pulled in. Disabling Parakeet would require either a new feature in this crate, or editing lib.rs re-exports. Brief item #13 hints a future cloud-only ASR config might want to drop both backends; today only Whisper is gateable.
• ParakeetParams differ between transcribe-rs versions. If you bump transcribe-rs, transcribe_with and ParakeetParams are the API surface to re-verify. The shim is the only file that constructs ParakeetParams directly.
• ort version conflict is the reason Silero VAD is blocked. Parakeet (transcribe-rs) requires ort 2.0.0-rc.12; the Silero crates pin 2.0.0-rc.10. Documented in audio-vad.md.

See also

• Transcription engines overview — the Transcriber / SpeechModelAdapter plumbing.
• Audio VAD — the ort version conflict introduced by this dep.
• Cargo features — note Parakeet has no feature flag today.
• transcribe_rs::SpeechModel re-export at crates/transcription/src/lib.rs:18.