update

poetry.lock

-# This file is automatically @generated by Poetry and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.4.0 and should not be changed by hand.
 
 [[package]]
 name = "alabaster"
@@ -1033,6 +1033,21 @@ typing-extensions = ">=4.2.0"
 dotenv = ["python-dotenv (>=0.10.4)"]
 email = ["email-validator (>=1.0.3)"]
 
+[[package]]
+name = "pyee"
+version = "9.0.4"
+description = "A port of node.js's EventEmitter to python."
+category = "main"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pyee-9.0.4-py2.py3-none-any.whl", hash = "sha256:9f066570130c554e9cc12de5a9d86f57c7ee47fece163bbdaa3e9c933cfbdfa5"},
+    {file = "pyee-9.0.4.tar.gz", hash = "sha256:2770c4928abc721f46b705e6a72b0c59480c4a69c9a83ca0b00bb994f1ea4b32"},
+]
+
+[package.dependencies]
+typing-extensions = "*"
+
 [[package]]
 name = "pygments"
 version = "2.15.0"
@@ -1107,6 +1122,22 @@ files = [
 [package.dependencies]
 six = ">=1.5"
 
+[[package]]
+name = "python-ffmpeg"
+version = "2.0.4"
+description = "A python binding for FFmpeg which provides sync and async APIs"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "python-ffmpeg-2.0.4.tar.gz", hash = "sha256:4d5275a58da2a82fb550acbf496ff86e76d677e06b781baeefbe05a4cd47ab50"},
+    {file = "python_ffmpeg-2.0.4-py3-none-any.whl", hash = "sha256:89aa9a0a6232a4fda58a9153af7d6c73b4d80d52b08dcde2b3c4ddcceb392b95"},
+]
+
+[package.dependencies]
+pyee = "*"
+typing-extensions = "*"
+
 [[package]]
 name = "pytz"
 version = "2023.3"
@@ -1371,6 +1402,7 @@ files = [
     {file = "soundfile-0.12.1-py2.py3-none-any.whl", hash = "sha256:828a79c2e75abab5359f780c81dccd4953c45a2c4cd4f05ba3e233ddf984b882"},
     {file = "soundfile-0.12.1-py2.py3-none-macosx_10_9_x86_64.whl", hash = "sha256:d922be1563ce17a69582a352a86f28ed8c9f6a8bc951df63476ffc310c064bfa"},
     {file = "soundfile-0.12.1-py2.py3-none-macosx_11_0_arm64.whl", hash = "sha256:bceaab5c4febb11ea0554566784bcf4bc2e3977b53946dda2b12804b4fe524a8"},
+    {file = "soundfile-0.12.1-py2.py3-none-manylinux_2_17_x86_64.whl", hash = "sha256:2dc3685bed7187c072a46ab4ffddd38cef7de9ae5eb05c03df2ad569cf4dacbc"},
     {file = "soundfile-0.12.1-py2.py3-none-manylinux_2_31_x86_64.whl", hash = "sha256:074247b771a181859d2bc1f98b5ebf6d5153d2c397b86ee9e29ba602a8dfe2a6"},
     {file = "soundfile-0.12.1-py2.py3-none-win32.whl", hash = "sha256:59dfd88c79b48f441bbf6994142a19ab1de3b9bb7c12863402c2bc621e49091a"},
     {file = "soundfile-0.12.1-py2.py3-none-win_amd64.whl", hash = "sha256:0d86924c00b62552b650ddd28af426e3ff2d4dc2e9047dae5b3d8452e0a49a77"},
@@ -1626,4 +1658,4 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "9b3bd7a53c5793a67b2f2cc96573d8eaf01c644bf000510d3d4e29e356f6c40a"
+content-hash = "ca35a4cda1d1842a6fae117b5805bf43e963330173bbd66780c666b4ae903aba"

pyproject.toml

@@ -14,6 +14,7 @@ pandas = "^2.0.0"
 scikit-learn = "^1.2.2"
 grpcio-tools = "^1.53.0"
 mpai-cae-arp = "^0.3.0"
+python-ffmpeg = "^2.0.4"
 
 
 [tool.poetry.group.docs.dependencies]

src/segment_finder.py

@@ -2,13 +2,15 @@ import os
 import tempfile
 from uuid import uuid4
 
+import numpy as np
+from ffmpeg import FFmpeg
+
 from mpai_cae_arp.audio import AudioWave, Noise
 from mpai_cae_arp.files import File, FileType
 from mpai_cae_arp.types.irregularity import Irregularity, IrregularityFile, Source
 from mpai_cae_arp.time import frames_to_seconds, seconds_to_frames, seconds_to_string, time_to_seconds
 
-temp_dir = tempfile.gettempdir()
-TMP_CHANNELS_MAP = os.path.join(temp_dir, "channels_map.json")
+TMP_CHANNELS_MAP = os.path.join(tempfile.gettempdir(), "mpai", "channels_map.json")
 
 def calculate_offset(audio: AudioWave, video: AudioWave) -> float:
     """
@@ -26,12 +28,24 @@ def calculate_offset(audio: AudioWave, video: AudioWave) -> float:
     float
     """
 
-    # corr = np.correlate(audio.array, video.array, mode="full")
-    # lags = np.arange(-len(audio.array) + 1, len(video.array))
-    # lag_idx = np.argmax(np.abs(corr))
+    corr = np.correlate(audio.array, video.array, mode="full")
+    lags = np.arange(-len(audio.array) + 1, len(video.array))
+    lag_idx = np.argmax(np.abs(corr))
+
+    return lags[lag_idx] / audio.samplerate
+
 
-    # return lags[lag_idx] / audio.samplerate
-    return 150
+def get_audio_from_video(video_src: str):
+    # calculate offset with ffmpeg
+    # ffmpeg -i video.mov -acodec pcm_s16le -ac 2 audio.wav
+    ffmpeg = (
+        FFmpeg()
+        .input(video_src)
+        .output(
+            "out.wav",
+            {""}
+        )
+    )
 
 
 def get_irregularities_from_audio(audio_src: AudioWave) -> list[Irregularity]:
@@ -72,6 +86,8 @@ def create_irreg_file(audio_src: str, video_src: str) -> IrregularityFile:
 
     audio = AudioWave.from_file(audio_src, bufferize=True)
     
+
+
     offset = calculate_offset(audio, video_src)
     irregularities = get_irregularities_from_audio(audio)
 

src/server.py

@@ -38,6 +38,10 @@ class AudioAnalyserServicer(arp_pb2_grpc.AudioAnalyserServicer):
         )
 
     def analyse(self, request: ComputationRequest, context):
+
+        working_dir: str = request.working_dir
+        files_name: str = request.files_name
+
         self.console.log('Received request for computation')
         for x in range(10):
             yield ComputationResult(