Implement basic webrtc stream (#1054)

* implement basic webrtc_stream

* add aiortc to requirements.txt

* update aiortc version

* rename variables with rtc_ prefix

* changes

* changes

* change helper to assert_helper and stream_helper

* rename variables with rtc_ prefix

* add error handling

* return whole connection

* remove monkey patch and some cleaning

* cleanup

* tiny adjustments

* tiny adjustments

* proper typing and naming for rtc offer set

* - remove async from on_video_track method
- rename source -> target
- add audio

* audio always before video

---------

Co-authored-by: henryruhs <info@henryruhs.com>

facefusion/apis/stream_helper.py

@@ -0,0 +1,31 @@
+import asyncio
+from typing import cast
+
+from aiortc import MediaStreamTrack, RTCPeerConnection, VideoStreamTrack
+from av import VideoFrame
+
+from facefusion.streamer import process_stream_frame
+
+
+def create_output_track(target_track : MediaStreamTrack) -> VideoStreamTrack:
+	output_track = VideoStreamTrack()
+
+	async def read_stream_frame() -> VideoFrame:
+		target_stream_frame = cast(VideoFrame, await target_track.recv())
+		output_vision_frame = await asyncio.get_running_loop().run_in_executor(None, process_stream_frame, target_stream_frame.to_ndarray(format = 'bgr24'))
+		output_stream_frame = VideoFrame.from_ndarray(output_vision_frame, format = 'bgr24')
+		output_stream_frame.pts = target_stream_frame.pts
+		output_stream_frame.time_base = target_stream_frame.time_base
+		return output_stream_frame
+
+	output_track.recv = read_stream_frame
+	return output_track
+
+
+def on_video_track(rtc_connection : RTCPeerConnection, target_track : MediaStreamTrack) -> None:
+	if target_track.kind == 'audio':
+		rtc_connection.addTrack(target_track)
+
+	if target_track.kind == 'video':
+		output_track = create_output_track(target_track)
+		rtc_connection.addTrack(output_track)