Skip to main content

​
Overview

StreamingEouAsrManager provides real-time streaming ASR with End-of-Utterance detection using the Parakeet EOU 120M model.

​
Quick Start

let manager = StreamingEouAsrManager(chunkSize: .ms160, eouDebounceMs: 1280)
try await manager.loadModels(modelDir: modelsURL)

// Process audio incrementally
_ = try await manager.process(audioBuffer: buffer1)
_ = try await manager.process(audioBuffer: buffer2)

// Get final transcript
let transcript = try await manager.finish()

// Reset for next utterance
await manager.reset()

​
Configuration

let manager = StreamingEouAsrManager(
    chunkSize: .ms320,        // .ms160, .ms320, or .ms1600
    eouDebounceMs: 1280       // Minimum silence before EOU triggers
)

​
EOU Callback

manager.setEouCallback { transcript in
    print("End of utterance: \(transcript)")
}

​
API

MethodDescription
loadModels(modelDir:)Load CoreML models from directory
process(audioBuffer:)Process audio incrementally
finish()Finalize and return transcript
reset()Reset state for next utterance
appendAudio(_:)Append audio without processing (VAD integration)

​
Benchmarks

LibriSpeech test-clean (2,620 files, 5.4h audio):
Chunk SizeLatencyWERRTFx
160msLowest~8%~5x
320msBalanced~5%~12x
1600msHighest throughput——
320ms is the recommended default — best accuracy/latency tradeoff.

​
CLI

# Transcribe a file
swift run fluidaudio parakeet-eou --input audio.wav --use-cache

# Benchmark
swift run fluidaudio parakeet-eou --benchmark --chunk-size 160 --max-files 100 --use-cache