Initial commit of current state

transcript_repair.py

@@ -0,0 +1,31 @@
+"""Rewrite transcripts before anything downstream reads them.
+
+Sits between the recogniser and the turn aggregator so the substitutions apply
+whichever speech engine is in use, and so the corrected text is what reaches
+Claude, the logs, and any future meeting-notes writer alike.
+"""
+
+from loguru import logger
+
+from pipecat.frames.frames import Frame, TranscriptionFrame
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from vocabulary import Vocabulary
+
+
+class TranscriptRepair(FrameProcessor):
+    """Apply the vocabulary's repair rules to every transcription."""
+
+    def __init__(self, vocabulary: Vocabulary, **kwargs):
+        super().__init__(**kwargs)
+        self._vocabulary = vocabulary
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, TranscriptionFrame):
+            repaired = self._vocabulary.repair(frame.text)
+            if repaired != frame.text:
+                logger.debug(f"Repaired transcript: {frame.text!r} -> {repaired!r}")
+                frame.text = repaired
+
+        await self.push_frame(frame, direction)