Josh Knapp
44480906a4
- Implement DiarizeService with pyannote.audio speaker detection - Build PipelineService combining transcribe → diarize → merge with overlap-based speaker assignment per segment - Add pipeline.start and diarize.start IPC handlers - Add run_pipeline Tauri command for full pipeline execution - Wire frontend to use pipeline: speakers auto-created with colors, segments assigned to detected speakers - Build SpeakerManager with rename support (double-click or edit button) - Add speaker color coding throughout transcript display - Add pyannote.audio dependency - Tests: 24 Python (including merge logic), 6 Rust, 0 Svelte errors Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
139 lines
4.7 KiB
Python
139 lines
4.7 KiB
Python
"""Message handler registry and routing."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from collections.abc import Callable
|
|
|
|
from voice_to_notes.ipc.messages import IPCMessage, error_message
|
|
|
|
# Handler function type: takes a message, returns a response message
|
|
HandlerFunc = Callable[[IPCMessage], IPCMessage | None]
|
|
|
|
|
|
class HandlerRegistry:
|
|
"""Registry mapping message types to handler functions."""
|
|
|
|
def __init__(self) -> None:
|
|
self._handlers: dict[str, HandlerFunc] = {}
|
|
|
|
def register(self, message_type: str, handler: HandlerFunc) -> None:
|
|
"""Register a handler for a message type."""
|
|
self._handlers[message_type] = handler
|
|
|
|
def handle(self, msg: IPCMessage) -> IPCMessage | None:
|
|
"""Route a message to its handler. Returns a response or error."""
|
|
handler = self._handlers.get(msg.type)
|
|
if handler is None:
|
|
print(f"[sidecar] Unknown message type: {msg.type}", file=sys.stderr, flush=True)
|
|
return error_message(msg.id, "unknown_type", f"Unknown message type: {msg.type}")
|
|
try:
|
|
return handler(msg)
|
|
except Exception as e:
|
|
print(f"[sidecar] Handler error for {msg.type}: {e}", file=sys.stderr, flush=True)
|
|
return error_message(msg.id, "handler_error", str(e))
|
|
|
|
|
|
def ping_handler(msg: IPCMessage) -> IPCMessage:
|
|
"""Simple ping handler for testing connectivity."""
|
|
return IPCMessage(id=msg.id, type="pong", payload={"echo": msg.payload})
|
|
|
|
|
|
def make_transcribe_handler() -> HandlerFunc:
|
|
"""Create a transcription handler with a persistent TranscribeService."""
|
|
from voice_to_notes.services.transcribe import TranscribeService, result_to_payload
|
|
|
|
service = TranscribeService()
|
|
|
|
def handler(msg: IPCMessage) -> IPCMessage:
|
|
payload = msg.payload
|
|
result = service.transcribe(
|
|
request_id=msg.id,
|
|
file_path=payload["file"],
|
|
model_name=payload.get("model", "base"),
|
|
device=payload.get("device", "cpu"),
|
|
compute_type=payload.get("compute_type", "int8"),
|
|
language=payload.get("language"),
|
|
)
|
|
return IPCMessage(
|
|
id=msg.id,
|
|
type="transcribe.result",
|
|
payload=result_to_payload(result),
|
|
)
|
|
|
|
return handler
|
|
|
|
|
|
def make_diarize_handler() -> HandlerFunc:
|
|
"""Create a diarization handler with a persistent DiarizeService."""
|
|
from voice_to_notes.services.diarize import DiarizeService, diarization_to_payload
|
|
|
|
service = DiarizeService()
|
|
|
|
def handler(msg: IPCMessage) -> IPCMessage:
|
|
payload = msg.payload
|
|
result = service.diarize(
|
|
request_id=msg.id,
|
|
file_path=payload["file"],
|
|
num_speakers=payload.get("num_speakers"),
|
|
min_speakers=payload.get("min_speakers"),
|
|
max_speakers=payload.get("max_speakers"),
|
|
)
|
|
return IPCMessage(
|
|
id=msg.id,
|
|
type="diarize.result",
|
|
payload=diarization_to_payload(result),
|
|
)
|
|
|
|
return handler
|
|
|
|
|
|
def make_pipeline_handler() -> HandlerFunc:
|
|
"""Create a full pipeline handler (transcribe + diarize + merge)."""
|
|
from voice_to_notes.services.pipeline import PipelineService, pipeline_result_to_payload
|
|
|
|
service = PipelineService()
|
|
|
|
def handler(msg: IPCMessage) -> IPCMessage:
|
|
payload = msg.payload
|
|
result = service.run(
|
|
request_id=msg.id,
|
|
file_path=payload["file"],
|
|
model_name=payload.get("model", "base"),
|
|
device=payload.get("device", "cpu"),
|
|
compute_type=payload.get("compute_type", "int8"),
|
|
language=payload.get("language"),
|
|
num_speakers=payload.get("num_speakers"),
|
|
min_speakers=payload.get("min_speakers"),
|
|
max_speakers=payload.get("max_speakers"),
|
|
skip_diarization=payload.get("skip_diarization", False),
|
|
)
|
|
return IPCMessage(
|
|
id=msg.id,
|
|
type="pipeline.result",
|
|
payload=pipeline_result_to_payload(result),
|
|
)
|
|
|
|
return handler
|
|
|
|
|
|
def hardware_detect_handler(msg: IPCMessage) -> IPCMessage:
|
|
"""Detect hardware capabilities and return recommendations."""
|
|
from voice_to_notes.hardware.detect import detect_hardware
|
|
|
|
info = detect_hardware()
|
|
return IPCMessage(
|
|
id=msg.id,
|
|
type="hardware.info",
|
|
payload={
|
|
"has_cuda": info.has_cuda,
|
|
"cuda_device_name": info.cuda_device_name,
|
|
"vram_mb": info.vram_mb,
|
|
"ram_mb": info.ram_mb,
|
|
"cpu_cores": info.cpu_cores,
|
|
"recommended_model": info.recommended_model,
|
|
"recommended_device": info.recommended_device,
|
|
"recommended_compute_type": info.recommended_compute_type,
|
|
},
|
|
)
|