pull from main

server/reflector/processors/__init__.py

@@ -1,5 +1,6 @@
 from .base import Processor, ThreadedProcessor, Pipeline  # noqa: F401
 from .types import AudioFile, Transcript, Word, TitleSummary, FinalSummary  # noqa: F401
+from .audio_file_writer import AudioFileWriterProcessor  # noqa: F401
 from .audio_chunker import AudioChunkerProcessor  # noqa: F401
 from .audio_merge import AudioMergeProcessor  # noqa: F401
 from .audio_transcript import AudioTranscriptProcessor  # noqa: F401

server/reflector/processors/audio_file_writer.py

@@ -0,0 +1,39 @@
+from reflector.processors.base import Processor
+import av
+from pathlib import Path
+
+
+class AudioFileWriterProcessor(Processor):
+    """
+    Write audio frames to a file.
+    """
+
+    INPUT_TYPE = av.AudioFrame
+    OUTPUT_TYPE = av.AudioFrame
+
+    def __init__(self, path: Path | str):
+        super().__init__()
+        if isinstance(path, str):
+            path = Path(path)
+        self.path = path
+        self.out_container = None
+        self.out_stream = None
+
+    async def _push(self, data: av.AudioFrame):
+        if not self.out_container:
+            self.path.parent.mkdir(parents=True, exist_ok=True)
+            self.out_container = av.open(self.path.as_posix(), "w", format="wav")
+            self.out_stream = self.out_container.add_stream(
+                "pcm_s16le", rate=data.sample_rate
+            )
+            for packet in self.out_stream.encode(data):
+                self.out_container.mux(packet)
+        await self.emit(data)
+
+    async def _flush(self):
+        if self.out_container:
+            for packet in self.out_stream.encode(None):
+                self.out_container.mux(packet)
+            self.out_container.close()
+            self.out_container = None
+            self.out_stream = None

server/reflector/processors/audio_merge.py

@@ -3,7 +3,6 @@ from reflector.processors.types import AudioFile
 from time import monotonic_ns
 from uuid import uuid4
 import io
-import wave
 import av
 
 
@@ -28,12 +27,16 @@ class AudioMergeProcessor(Processor):
         # create audio file
         uu = uuid4().hex
         fd = io.BytesIO()
-        with wave.open(fd, "wb") as wf:
-            wf.setnchannels(channels)
-            wf.setsampwidth(sample_width)
-            wf.setframerate(sample_rate)
-            for frame in data:
-                wf.writeframes(frame.to_ndarray().tobytes())
+
+        out_container = av.open(fd, "w", format="wav")
+        out_stream = out_container.add_stream("pcm_s16le", rate=sample_rate)
+        for frame in data:
+            for packet in out_stream.encode(frame):
+                out_container.mux(packet)
+        for packet in out_stream.encode(None):
+            out_container.mux(packet)
+        out_container.close()
+        fd.seek(0)
 
         # emit audio file
         audiofile = AudioFile(
@@ -44,4 +47,5 @@ class AudioMergeProcessor(Processor):
             sample_width=sample_width,
             timestamp=data[0].pts * data[0].time_base,
         )
+
         await self.emit(audiofile)