From f2de9f1843b672ad14d61bf8d93b3c4cff8f087d Mon Sep 17 00:00:00 2001 From: henryruhs Date: Mon, 1 Jun 2026 11:41:25 +0200 Subject: [PATCH] rename to video pack and audio pack --- facefusion/apis/stream_helper.py | 12 ++++++------ facefusion/types.py | 4 ++-- tests/test_api_stream_helper.py | 14 +++++++------- 3 files changed, 15 insertions(+), 15 deletions(-) diff --git a/facefusion/apis/stream_helper.py b/facefusion/apis/stream_helper.py index de9a6cf8..bc62669c 100644 --- a/facefusion/apis/stream_helper.py +++ b/facefusion/apis/stream_helper.py @@ -15,7 +15,7 @@ from facefusion import rtc, rtc_store, state_manager, streamer from facefusion.audio import create_empty_audio_frame from facefusion.codecs import aom_decoder, aom_encoder, opus_decoder, opus_encoder, vpx_decoder, vpx_encoder from facefusion.libraries import datachannel as datachannel_module -from facefusion.types import AomDecoder, AomEncoder, AudioCodec, AudioPacket, BitRate, PeerConnection, Resolution, RtcPeer, RtcPeerAudio, SdpAnswer, SdpOffer, SessionId, VideoCodec, VisionFrame, VisionPacket, VpxDecoder, VpxEncoder +from facefusion.types import AomDecoder, AomEncoder, AudioCodec, AudioPack, BitRate, PeerConnection, Resolution, RtcPeer, RtcPeerAudio, SdpAnswer, SdpOffer, SessionId, VideoCodec, VisionFrame, VideoPack, VpxDecoder, VpxEncoder #TODO: remove source_paths guard, process_image should work independent of source_paths since processors decide if they need sources @@ -111,8 +111,8 @@ async def receive_vision_frames(websocket : WebSocket) -> AsyncIterator[VisionFr #TODO: needs review async def run_peer_loop(session_id : SessionId, rtc_peer : RtcPeer) -> None: - video_deque : deque[VisionPacket] = deque(maxlen = 1) - audio_deque : deque[AudioPacket] = deque(maxlen = 10) + video_deque : deque[VideoPack] = deque(maxlen = 1) + audio_deque : deque[AudioPack] = deque(maxlen = 10) video_event = threading.Event() video_codec = rtc_peer.get('video').get('codec') video_track = rtc_peer.get('video').get('receiver_track') @@ -132,7 +132,7 @@ async def run_peer_loop(session_id : SessionId, rtc_peer : RtcPeer) -> None: #TODO: needs review #TODO: method is too complex -def run_encode_loop(rtc_peer : RtcPeer, video_codec : VideoCodec, video_deque : deque[VisionPacket], audio_deque : deque[AudioPacket], video_event : threading.Event) -> None: +def run_encode_loop(rtc_peer : RtcPeer, video_codec : VideoCodec, video_deque : deque[VideoPack], audio_deque : deque[AudioPack], video_event : threading.Event) -> None: video_event.wait() video_event.clear() temp_vision_frame, video_receive_time = video_deque.popleft() @@ -204,7 +204,7 @@ def run_encode_loop(rtc_peer : RtcPeer, video_codec : VideoCodec, video_deque : # TODO: method is too complex -def receive_video_frames(video_track : int, video_codec : VideoCodec, video_deque : deque[VisionPacket], video_event : threading.Event) -> None: +def receive_video_frames(video_track : int, video_codec : VideoCodec, video_deque : deque[VideoPack], video_event : threading.Event) -> None: datachannel_library = datachannel_module.create_static_library() video_decoder = create_video_decoder(video_codec) receive_buffer = ctypes.create_string_buffer(512 * 1024) @@ -238,7 +238,7 @@ def receive_video_frames(video_track : int, video_codec : VideoCodec, video_dequ # TODO: audio_codec is not used but has to, even if there is just one # TODO: method is too complex -def receive_audio_frames(audio_track : int, audio_codec : AudioCodec, audio_deque : deque[AudioPacket]) -> None: +def receive_audio_frames(audio_track : int, audio_codec : AudioCodec, audio_deque : deque[AudioPack]) -> None: datachannel_library = datachannel_module.create_static_library() audio_decoder = opus_decoder.create(48000, 2) receive_buffer = ctypes.create_string_buffer(8 * 1024) diff --git a/facefusion/types.py b/facefusion/types.py index 1c0636d9..ea2c1fe8 100755 --- a/facefusion/types.py +++ b/facefusion/types.py @@ -313,8 +313,8 @@ RtcPeer = TypedDict('RtcPeer', }) RtcStore : TypeAlias = Dict[SessionId, List[RtcPeer]] -VisionPacket : TypeAlias = tuple[VisionFrame, float] -AudioPacket : TypeAlias = tuple[AudioFrame, float] +VideoPack : TypeAlias = tuple[VisionFrame, float] +AudioPack : TypeAlias = tuple[AudioFrame, float] SdpAudioMedia = TypedDict('SdpAudioMedia', { diff --git a/tests/test_api_stream_helper.py b/tests/test_api_stream_helper.py index eb2a608f..3ed5d4c6 100644 --- a/tests/test_api_stream_helper.py +++ b/tests/test_api_stream_helper.py @@ -17,7 +17,7 @@ from facefusion.common_helper import is_linux, is_macos, is_windows from facefusion.download import conditional_download from facefusion.hash_helper import create_hash from facefusion.libraries import aom as aom_module, datachannel as datachannel_module, opus as opus_module, vpx as vpx_module -from facefusion.types import AudioPacket, RtcPeer, VideoCodec, VisionPacket +from facefusion.types import AudioPack, RtcPeer, VideoCodec, VideoPack from facefusion.vision import read_video_frame from .assert_helper import get_test_example_file, get_test_examples_directory @@ -190,8 +190,8 @@ def test_run_encode_loop(video_codec : VideoCodec, payload_type : int) -> None: 'receiver_bitrate': ctypes.c_uint(0) } - video_deque : deque[VisionPacket] = deque() - audio_deque : deque[AudioPacket] = deque() + video_deque : deque[VideoPack] = deque() + audio_deque : deque[AudioPack] = deque() video_event = threading.Event() video_deque.append((source_frame, 0.100)) @@ -229,8 +229,8 @@ def test_run_peer_loop_send_order(video_codec : VideoCodec, payload_type : int) 'receiver_bitrate': ctypes.c_uint(0) } - video_deque : deque[VisionPacket] = deque() - audio_deque : deque[AudioPacket] = deque() + video_deque : deque[VideoPack] = deque() + audio_deque : deque[AudioPack] = deque() video_event = threading.Event() video_deque.append((source_frame, 0.100)) @@ -262,7 +262,7 @@ def test_receive_video_frames() -> None: datachannel_library_mock = MagicMock() datachannel_library_mock.rtcReceiveMessage.side_effect = [ 0, -1 ] vision_frame = read_video_frame(get_test_example_file('target-240p.mp4')) - video_deque : deque[VisionPacket] = deque() + video_deque : deque[VideoPack] = deque() video_event = threading.Event() with patch('facefusion.apis.stream_helper.datachannel_module.create_static_library', return_value = datachannel_library_mock): @@ -282,7 +282,7 @@ def test_receive_audio_frames() -> None: datachannel_library_mock = MagicMock() datachannel_library_mock.rtcReceiveMessage.side_effect = [ 0, -1 ] audio_data = numpy.zeros(960 * 2, dtype = numpy.float32) - audio_deque : deque[AudioPacket] = deque() + audio_deque : deque[AudioPack] = deque() with patch('facefusion.apis.stream_helper.datachannel_module.create_static_library', return_value = datachannel_library_mock): with patch('facefusion.apis.stream_helper.opus_decoder.decode', return_value = audio_data.tobytes()):