Recherche avancée

Sur d’autres sites (10764)

• finding speed and tone of speech in an audio using python

  1er février 2018, par kRazzy R

  Given an audio , I want to calculate the pace of the speech. i.e how fast or slow is it.

  Currently I am doing the following :
  
   convert speech to text and obtaining a transcript (using a free tool).
  
   count number of words in transcript.
  
   calculate length or duration of file.
  
   finally, pace = (number of words in transcript / duration of file).

  However the accuracy of the pace obtained is dependent purely on transcription , which I think is an unnecessary step.

  Is there any python-library/sox/ffmpeg way that will enable me to

  • to calculate, in a straightforward way,the speed/pace of talk in an audio
  • dominant Pitches/tones of that audio ?

  I referred : I referred : http://sox.sourceforge.net/sox.html and https://digitalcardboard.com/blog/2009/08/25/the-sox-of-silence/

• FFMPEG Speed drops and warnings

  31 juillet 2018, par leo_dragons

  I’ve been trying to stream from a BlackMagic DeckLink Mini Recorder to 4 different outputs using FFMPEG, but i get a huge delay let say more than 60 seconds of delay, it takes a long time to buffer on any player and when i check the terminal i get these warnings :

  [decklink @ 0x4655e40] Decklink input buffer overrun!

  I’ve also noticed that i have a very slow capture speed like 0.5x. Here’s the string i use, i’m currently running on CentOS 7.5 :

  ffmpeg -f decklink -i "DeckLink Mini Recorder" -y -pix_fmt yuv420p -vcodec h264 -preset ultrafast -tune zerolatency -b 900k -g 48 -framerate 30 -movflags +faststart -vf scale=1280:720 -bufsize 400k -maxrate 1200k -benchmark -f flv "rtmp ://10.0.0.172:1935/CAMARAS/live9" -vcodec h264 -preset ultrafast -tune zerolatency -b 700k -g 48 -framerate 30 -movflags +faststart -vf scale=854:480 -bufsize 400k -maxrate 1000k -benchmark -f flv "rtmp ://10.0.0.172:1935/CAMARAS/live10" -vcodec h264 -preset ultrafast -tune zerolatency -b 400k -g 48 -framerate 30 -movflags +faststart -vf scale=854:480 -bufsize 400k -maxrate 500k -benchmark -f flv "rtmp ://10.0.0.172:1935/CAMARAS/live11" -vcodec h264 -preset ultrafast -tune zerolatency -b 200k -g 48 -framerate 30 -movflags +faststart -vf scale=640:360 -bufsize 300k -maxrate 300k -benchmark -f flv "rtmp ://10.0.0.172:1935/CAMARAS/live12" > /dev/null 2>&1 &

  But if i run this string alone i get decent capture speed, but i still have an awful latency 30ish seconds :

  ffmpeg -f decklink -i "DeckLink Mini Recorder" -y -pix_fmt yuv420p -vcodec h264 -preset ultrafast -tune zerolatency -b 900k -g 48 -framerate 30 -movflags +faststart -vf scale=1280:720 -bufsize 400k -maxrate 1200k -benchmark -f flv "rtmp ://10.0.0.172:1935/CAMARAS/live9"

  Any help will be highly appreciated.

  Tahnk you.

• Speed up reading video frames from camera with Opencv

  19 septembre 2020, par Tuyen Vo Quang

  Currently, i have my application implemented in Python to read camera frames via USB. I use Opencv, but for camera with 60fps and 1920x1080 resolution, i could not capture the this speed. I try something : cv2.VideoCapture(0, cv2.CAP_FFMPEG), but i could not the frames (capture read returns False). Could you please suggest any solutions or ways to improve the overall speed or even processing them in GPU.

  


      # Opencv 3.4.9 & Python 3.6.9
    import cv2    
    capture = cv2.VideoCapture(0, cv2.CAP_FFMPEG)

    while True:
        ret, frame = capture.read()
        if ret:
            cv2.imshow('Demo', frame)
            cv2.waitKey(1)


  


  Opencv is built from source :

  


  #!/usr/bin/env bash

set -e

VERSION='3.4.9'
DOWNLOAD_URL="https://github.com/opencv/opencv/archive/${VERSION}.zip"
CONTRIB_DOWNLOAD_URL="https://github.com/opencv/opencv_contrib/archive/${VERSION}.zip"
CURRENT_DIR="$(pwd)"
config_opencv_with_cuda() {
  cmake -D CMAKE_BUILD_TYPE=RELEASE \
        -D CMAKE_INSTALL_PREFIX=/usr/local \
        -D INSTALL_PYTHON_EXAMPLES=OFF \
        -D WITH_CUDA=ON \
        -D ENABLE_FAST_MATH=1 \
        -D CUDA_FAST_MATH=1 \
        -D WITH_CUBLAS=1 \
        -D WITH_V4L=ON \
        -D WITH_FFMPEG=ON \
        -D WITH_GSTREAMER=ON \
        -D BUILD_opencv_cnn_3dobj=OFF \
        -D BUILD_opencv_dnn_modern=OFF \
        -D OPENCV_EXTRA_MODULES_PATH=$CURRENT_DIR/opencv_contrib-$VERSION/modules \
        -D BUILD_DOCS=OFF \
        -D BUILD_PERF_TESTS=OFF \
        -D BUILD_TESTS=OFF \
        -D BUILD_EXAMPLES=OFF ..
}
echo 'Uninstalling pip installation'
pip3 uninstall opencv-python opencv-contrib-python

echo 'Installing dependencies'
apt-get update && apt-get install -y \
  build-essential cmake pkg-config \
  libjpeg-dev libtiff5-dev libpng12-dev \
  libavcodec-dev libavformat-dev libswscale-dev libv4l-dev \
  libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev \
  libxvidcore-dev libx264-dev \
  libgtk2.0-dev libgtk-3-dev \
  gfortran

wget -O opencv.zip "${DOWNLOAD_URL}"
wget -O opencv_contrib.zip "${CONTRIB_DOWNLOAD_URL}"
unzip opencv.zip && unzip opencv_contrib.zip
cd opencv-$VERSION
mkdir build
cd build

if [[ -d /usr/local/cuda ]]; then
  config_opencv_with_cuda
else
  config_opencv_without_cuda
fi

make -j $(nproc)
make install
ldconfig