Recherche avancée

Sur d’autres sites (12276)

• ffmpeg - Replace one word audio in video at different specific timeline [duplicate]

  17 décembre 2019, par Siddharth

  This question is an exact duplicate of :

  • Can I extract an audio clip (a single word) from the video and insert at different points/timeline of same video using FFMPEG/libvlcsharp ?

  How can i replace one word (newyork to be replaced by california) throughtout the video where speaker says "Newyork". I want that "Newyork" word to be removed from the audio (while keeping video intact) and insert "california" throughout the video at different places.

  I have an audio file where speaker says "California" which i want to replace with "newyork" word.

  How can i do that using FFMPEG ?

• lavfi/dnn_classify : add filter dnn_classify for classification based on detection...

  17 mars 2021, par Guo, Yejun

  lavfi/dnn_classify : add filter dnn_classify for classification based on detection bounding boxes
  classification is done on every detection bounding box in frame's side data,
  
  which are the results of object detection (filter dnn_detect).
  Please refer to commit log of dnn_detect for the material for detection,
  
  and see below for classification.
   download material for classifcation :
  
  wget https://github.com/guoyejun/ffmpeg_dnn/raw/main/models/openvino/2021.1/emotions-recognition-retail-0003.bin
  
  wget https://github.com/guoyejun/ffmpeg_dnn/raw/main/models/openvino/2021.1/emotions-recognition-retail-0003.xml
  
  wget https://github.com/guoyejun/ffmpeg_dnn/raw/main/models/openvino/2021.1/emotions-recognition-retail-0003.label
   run command as :
  
  ./ffmpeg -i cici.jpg -vf dnn_detect=dnn_backend=openvino:model=face-detection-adas-0001.xml:input=data:output=detection_out:confidence=0.6:labels=face-detection-adas-0001.label,dnn_classify=dnn_backend=openvino:model=emotions-recognition-retail-0003.xml:input=data:output=prob_emotion:confidence=0.3:labels=emotions-recognition-retail-0003.label:target=face,showinfo -f null -
  We'll see the detect&classify result as below :
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0]   side data - detection bounding boxes :
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0] source : face-detection-adas-0001.xml, emotions-recognition-retail-0003.xml
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0] index : 0,  region : (1005, 813) -> (1086, 905), label : face, confidence : 10000/10000.
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0]            classify :  label : happy, confidence : 6757/10000.
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0] index : 1,  region : (888, 839) -> (967, 926), label : face, confidence : 6917/10000.
  
  [Parsed_showinfo_2 @ 0x55b7d25e77c0]            classify :  label : anger, confidence : 4320/10000.
  Signed-off-by : Guo, Yejun <yejun.guo@intel.com>
  

  • [DH] configure
  • [DH] doc/filters.texi
  • [DH] libavfilter/Makefile
  • [DH] libavfilter/allfilters.c
  • [DH] libavfilter/vf_dnn_classify.c

• how to create a radio or video "station" continuous TS stream with ffmpeg

  25 février 2020, par Zibri

  I can’t find any answer to this scenarios :

  Produce a continuous ts file that initially contains silence (or blank video), and as I add files to a text file I wish them to be queued in the output ts stream.
  Think of it as a radio or tv station.
  I found everything on how to stream anything to anything,
  but not a tv/radio broadcast like stream.

  A good start seems to be this :

  ffmpeg -re -y -nostats -nostdin -hide_banner -loglevel quiet -fflags +genpts -f concat -i list.txt -map 0:a? -map 0:v? -map 0:s? -strict -2 -dn -c copy -hls_flags delete_segments -hls_time 10 -hls_list_size 6 /var/www/html/showname_.m3u8

  list.txt example

  file '/mnt/vusolo-tv/show/Season 1/S01E01.mp4'
  
  file '/mnt/vusolo-tv/show/Season 1/S01E02.mp4'

  But i think there can be better ways...

  This is not a good answer either : From multiple video files to single output
  because "All files must have streams with identical encoding. Timebase for streams should be the same. Duration of all streams within a file should be the same, in order to maintain sync."
  And I want to be able to add arbitrary files and produce a TS stream playable by any TV (once broadcasted in dvb).