Josh Knapp
67ed69df00
Send each segment to the frontend immediately after transcription via a new pipeline.segment IPC message, then send speaker assignments as a batch pipeline.speaker_update message after diarization completes. This lets the UI display segments progressively instead of waiting for the entire pipeline to finish. Changes: - Add partial_segment_message and speaker_update_message IPC factories - Add on_segment callback parameter to TranscribeService.transcribe() - Emit partial segments and speaker updates from PipelineService.run() - Add send_and_receive_with_progress to SidecarManager (Rust) - Route pipeline.segment/speaker_update events in run_pipeline command - Listen for streaming events in Svelte frontend (+page.svelte) - Add tests for new message types, callback signature, and update logic Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
106 lines
3.5 KiB
Python
106 lines
3.5 KiB
Python
"""Tests for pipeline service data structures and merge logic."""
|
|
|
|
from voice_to_notes.services.diarize import SpeakerSegment
|
|
from voice_to_notes.services.pipeline import (
|
|
PipelineResult,
|
|
PipelineSegment,
|
|
PipelineService,
|
|
pipeline_result_to_payload,
|
|
)
|
|
from voice_to_notes.services.transcribe import (
|
|
SegmentResult,
|
|
TranscriptionResult,
|
|
WordResult,
|
|
)
|
|
|
|
|
|
def test_pipeline_result_to_payload():
|
|
result = PipelineResult(
|
|
segments=[
|
|
PipelineSegment(
|
|
text="Hello world",
|
|
start_ms=0,
|
|
end_ms=2000,
|
|
speaker="SPEAKER_00",
|
|
words=[
|
|
WordResult(word="Hello", start_ms=0, end_ms=800, confidence=0.95),
|
|
WordResult(word="world", start_ms=900, end_ms=2000, confidence=0.88),
|
|
],
|
|
),
|
|
],
|
|
language="en",
|
|
language_probability=0.98,
|
|
duration_ms=10000,
|
|
speakers=["SPEAKER_00", "SPEAKER_01"],
|
|
num_speakers=2,
|
|
)
|
|
payload = pipeline_result_to_payload(result)
|
|
assert payload["language"] == "en"
|
|
assert payload["num_speakers"] == 2
|
|
assert len(payload["segments"]) == 1
|
|
assert payload["segments"][0]["speaker"] == "SPEAKER_00"
|
|
assert len(payload["segments"][0]["words"]) == 2
|
|
|
|
|
|
def test_pipeline_result_to_payload_empty():
|
|
result = PipelineResult()
|
|
payload = pipeline_result_to_payload(result)
|
|
assert payload["segments"] == []
|
|
assert payload["speakers"] == []
|
|
assert payload["num_speakers"] == 0
|
|
|
|
|
|
def test_merge_results_assigns_speakers():
|
|
"""Test that _merge_results correctly assigns speakers based on overlap."""
|
|
service = PipelineService()
|
|
|
|
transcription = TranscriptionResult(
|
|
segments=[
|
|
SegmentResult(text="Hello there", start_ms=0, end_ms=3000, words=[]),
|
|
SegmentResult(text="How are you", start_ms=4000, end_ms=7000, words=[]),
|
|
],
|
|
language="en",
|
|
language_probability=0.99,
|
|
duration_ms=10000,
|
|
)
|
|
|
|
speaker_segments = [
|
|
SpeakerSegment(speaker="SPEAKER_00", start_ms=0, end_ms=3500),
|
|
SpeakerSegment(speaker="SPEAKER_01", start_ms=3500, end_ms=8000),
|
|
]
|
|
|
|
result = service._merge_results(transcription, speaker_segments)
|
|
assert len(result.segments) == 2
|
|
assert result.segments[0].speaker == "SPEAKER_00"
|
|
assert result.segments[1].speaker == "SPEAKER_01"
|
|
|
|
|
|
def test_merge_results_no_speaker_segments():
|
|
"""With no speaker segments, all speakers should be None."""
|
|
service = PipelineService()
|
|
|
|
transcription = TranscriptionResult(
|
|
segments=[SegmentResult(text="Hello", start_ms=0, end_ms=1000, words=[])],
|
|
language="en",
|
|
language_probability=0.99,
|
|
duration_ms=1000,
|
|
)
|
|
|
|
result = service._merge_results(transcription, [])
|
|
assert result.segments[0].speaker is None
|
|
|
|
|
|
def test_speaker_update_generation():
|
|
"""Test that speaker updates are generated after merge."""
|
|
result = PipelineResult(
|
|
segments=[
|
|
PipelineSegment(text="Hello", start_ms=0, end_ms=1000, speaker="SPEAKER_00"),
|
|
PipelineSegment(text="World", start_ms=1000, end_ms=2000, speaker="SPEAKER_01"),
|
|
PipelineSegment(text="Foo", start_ms=2000, end_ms=3000, speaker=None),
|
|
],
|
|
)
|
|
updates = [{"index": i, "speaker": seg.speaker} for i, seg in enumerate(result.segments) if seg.speaker]
|
|
assert len(updates) == 2
|
|
assert updates[0] == {"index": 0, "speaker": "SPEAKER_00"}
|
|
assert updates[1] == {"index": 1, "speaker": "SPEAKER_01"}
|