Merge perf/stream-segments: streaming partial transcript segments and speaker updates

python/voice_to_notes/ipc/messages.py

@@ -34,6 +34,14 @@ def progress_message(request_id: str, percent: int, stage: str, message: str) ->
     )
 
 
+def partial_segment_message(request_id: str, segment_data: dict) -> IPCMessage:
+    return IPCMessage(id=request_id, type="pipeline.segment", payload=segment_data)
+
+
+def speaker_update_message(request_id: str, updates: list[dict]) -> IPCMessage:
+    return IPCMessage(id=request_id, type="pipeline.speaker_update", payload={"updates": updates})
+
+
 def error_message(request_id: str, code: str, message: str) -> IPCMessage:
     return IPCMessage(
         id=request_id,

python/voice_to_notes/services/pipeline.py

@@ -7,7 +7,11 @@ import time
 from dataclasses import dataclass, field
 from typing import Any
 
-from voice_to_notes.ipc.messages import progress_message
+from voice_to_notes.ipc.messages import (
+    partial_segment_message,
+    progress_message,
+    speaker_update_message,
+)
 from voice_to_notes.ipc.protocol import write_message
 from voice_to_notes.services.diarize import DiarizeService, SpeakerSegment
 from voice_to_notes.services.transcribe import (
@@ -83,6 +87,15 @@ class PipelineService:
             progress_message(request_id, 0, "pipeline", "Starting transcription pipeline...")
         )
 
+        def _emit_segment(seg: SegmentResult, index: int) -> None:
+            write_message(partial_segment_message(request_id, {
+                "index": index,
+                "text": seg.text,
+                "start_ms": seg.start_ms,
+                "end_ms": seg.end_ms,
+                "words": [{"word": w.word, "start_ms": w.start_ms, "end_ms": w.end_ms, "confidence": w.confidence} for w in seg.words],
+            }))
+
         transcription = self._transcribe_service.transcribe(
             request_id=request_id,
             file_path=file_path,
@@ -90,6 +103,7 @@ class PipelineService:
             device=device,
             compute_type=compute_type,
             language=language,
+            on_segment=_emit_segment,
         )
 
         if skip_diarization:
@@ -174,6 +188,10 @@ class PipelineService:
             flush=True,
         )
 
+        updates = [{"index": i, "speaker": seg.speaker} for i, seg in enumerate(result.segments) if seg.speaker]
+        if updates:
+            write_message(speaker_update_message(request_id, updates))
+
         write_message(
             progress_message(request_id, 100, "done", "Pipeline complete")
         )

python/voice_to_notes/services/transcribe.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import sys
 import time
+from collections.abc import Callable
 from dataclasses import dataclass, field
 from typing import Any
 
@@ -90,6 +91,7 @@ class TranscribeService:
         device: str = "cpu",
         compute_type: str = "int8",
         language: str | None = None,
+        on_segment: Callable[[SegmentResult, int], None] | None = None,
     ) -> TranscriptionResult:
         """Transcribe an audio file with word-level timestamps.
 
@@ -145,6 +147,9 @@ class TranscribeService:
                 )
             )
 
+            if on_segment:
+                on_segment(result.segments[-1], segment_count - 1)
+
             # Send progress every few segments
             if segment_count % 5 == 0:
                 write_message(