On Tue, Dec 29, 2020, at 6:41 AM, Lynne wrote: > Dec 28, 2020, 19:03 by j...@jonb.org: > > >> Actually its not impossible to create extradata from raw Opus streams. > >> The extradata only contains a magic, #channes, padding, a sample rate and > >> a channel_family. > >> > >> We know the magic, the #channels can be found out via the packet's > >> contents and whether it contains multiple packets, the padding would > >> be 0 because its a stream, the sample rate is always 48000 (we purpusefully > >> disrespect the container's sample rate in case of Opus, which this is), > >> and the mapping family can be set to 255 to just let the decoder decide > >> on the number of channels. > >> > >> > >> > The RTP demuxer should start exporting extradata instead, if possible. > >> > Either generated from available stream information, or taken verbatim if > >> > present. Not sure how the RTP encapsulation for Opus is defined in this > >> > regard. > >> > > >> > >> Yes, I think that's the best solution. Just follow the steps I described > >> above, and > >> to write it out you can check out the opus_write_extradata() function in > >> libavcodec/opusenc.c. > >> > > > > Thank you for the feedback everyone. I agree, the RTP demuxer is the best > > place for this. I will resubmit the patch as such. > >
Thank you for all the feedback everyone. I've updated the patch to build the opus header inside of ff_rtp_parse_open in libavformat/rtpdec.c. I set the mapping_family to 0, since I believe Opus/RTP only supports 2 channels. I set the input sample rate to 0, which the spec considers "unspecified". Let me know what you think of this approach for these values. Happy to switch them to 255/48000 if you prefer. I copied the bytestream code from opusenc.c. There's now 3 or 4 different places in the codebase where opus headers are getting built. Let me know if you'd like me to refactor this a bit. I didn't want to touch too many components with my first patch.
0001-ff_rtp_parse_open-builds-Opus-head-in-extradata.patch
Description: Binary data
_______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
