Recherche avancée

Sur d’autres sites (9771)

• Using PyAV to encode mono audio to file, params match docs, but still causes Errno 22

  20 février 2023, par andrew8088

  While trying to use PyAV to encode live mono audio from a microphone to a compressed audio stream (using mp2 or flac as encoder), the program kept raising an exception ValueError: [Errno 22] Invalid argument.

  


  To remove the live microphone source as a cause of the problem, and to make the problematic code easier for others to run/test, I have removed the mic source and now just generate a pure tone as a sequence of input buffers.

  


  All attempts to figure out the missing or mismatched or incorrect argument have just resulted in seeing documentation and examples that are the same as my code.

  


  I would like to know from someone who has used PyAV successfully for mono audio what the correct method and parameters are for encoding mono frames into the mono stream.

  


  The package used is av 10.0.0 installed with
pip3 install av --no-binary av
so it uses my package-manager provided ffmpeg library, which is version 4.2.7.

  


  The problematic python code is :

  


  #!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Recreating an error 22 when encoding sound with PyAV.

Created on Sun Feb 19 08:10:29 2023
@author: andrewm
"""
import typing
import sys
import math
import fractions

import av
from av import AudioFrame

""" Ensure some PyAudio constants are still defined without changing 
    the PyAudio recording callback function and without depending 
    on PyAudio simply for reproducing the PyAV bug [Errno 22] thrown in 
    File "av/filter/context.pyx", line 89, in av.filter.context.FilterContext.push
"""
class PA_Stub():
    paContinue = True
    paComplete= False

pyaudio = PA_Stub()


"""Generate pure tone at given frequency with amplitude 0...1.0 at 
   sampling frewuency fs and beginning at phase offset 'phase'.
   Returns the new phase after the sinusoid has cycled over the 
   sampling window length.
"""
def generate_tone(
        freq:int, phase:float, amp:float, fs, samp_fmt, buffer:bytearray
) -> float:
    assert samp_fmt == "s16", "Only s16 supported atm"
    samp_size_bytes = 2
    n_samples = int(len(buffer)/samp_size_bytes)
    window = [int(0) for i in range(n_samples)]
    theta = phase
    phase_inc = 2*math.pi * freq / fs
    for i in range(n_samples):
        v = amp * math.sin(theta)
        theta += phase_inc
        s = int((2**15-1)*v)
        window[i] = s
    for sample_i in range(len(window)):
        byte_i = sample_i * samp_size_bytes
        enc = window[sample_i].to_bytes(
                2, byteorder=sys.byteorder, signed=True
        )
        buffer[byte_i] = enc[0]
        buffer[byte_i+1] = enc[1]
    return theta


channels = 1
fs = 44100  # Record at 44100 samples per second
fft_size_samps = 256
chunk_samps = fft_size_samps * 10  # Record in chunks that are multiples of fft windows.

# print(f"fft_size_samps={fft_size_samps}\nchunk_samps={chunk_samps}")

seconds = 3.0
out_filename = "testoutput.wav"

# Store data in chunks for 3 seconds
sample_limit = int(fs * seconds)
sample_len = 0
frames = []  # Initialize array to store frames

ffmpeg_codec_name = 'mp2'  # flac, mp3, or libvorbis make same error.

sample_size_bytes = 2
buffer = bytearray(int(chunk_samps*sample_size_bytes))
chunkperiod = chunk_samps / fs
total_chunks = int(math.ceil(seconds / chunkperiod))
phase = 0.0

### uncomment if you want to see the synthetic data being used as a mic input.
# with open("test.raw","wb") as raw_out:
#     for ci in range(total_chunks):
#         phase = generate_tone(2600, phase, 0.8, fs, "s16", buffer)
#         raw_out.write(buffer)
# print("finished gen test")
# sys.exit(0)
# #---- 

# Using mp2 or mkv as the container format gets the same error.
with av.open(out_filename+'.mp2', "w", format="mp2") as output_con:
    output_con.metadata["title"] = "My title"
    output_con.metadata["key"] = "value"
    channel_layout = "mono"
    sample_fmt = "s16p"

    ostream = output_con.add_stream(ffmpeg_codec_name, fs, layout=channel_layout)
    assert ostream is not None, "No stream!"
    cctx = ostream.codec_context
    cctx.sample_rate = fs
    cctx.time_base = fractions.Fraction(numerator=1,denominator=fs)
    cctx.format = sample_fmt
    cctx.channels = channels
    cctx.layout = channel_layout
    print(cctx, f"layout#{cctx.channel_layout}")
    
    # Define PyAudio-style callback for recording plus PyAV transcoding.
    def rec_callback(in_data, frame_count, time_info, status):
        global sample_len
        global ostream
        frames.append(in_data)
        nsamples = int(len(in_data) / (channels*sample_size_bytes))
        
        frame = AudioFrame(format=sample_fmt, layout=channel_layout, samples=nsamples)
        frame.sample_rate = fs
        frame.time_base = fractions.Fraction(numerator=1,denominator=fs)
        frame.pts = sample_len
        frame.planes[0].update(in_data)
        print(frame, len(in_data))
        
        for out_packet in ostream.encode(frame):
            output_con.mux(out_packet)
        for out_packet in ostream.encode(None):
            output_con.mux(out_packet)
        
        sample_len += nsamples
        retflag = pyaudio.paContinue if sample_lencode>

  


  If you uncomment the RAW output part you will find the generated data can be imported as PCM s16 Mono 44100Hz into Audacity and plays the expected tone, so the generated audio data does not seem to be the problem.

  


  The normal program console output up until the exception is :

  


  mp2 at 0x7f8e38202cf0> layout#4
Beginning
 5120
. 5120


  


  The stack trace is :

  


  Traceback (most recent call last):&#xA;&#xA;  File "Dev/multichan_recording/av_encode.py", line 147, in <module>&#xA;    ret_data, ret_flag = rec_callback(buffer, ci, {}, 1)&#xA;&#xA;  File "Dev/multichan_recording/av_encode.py", line 121, in rec_callback&#xA;    for out_packet in ostream.encode(frame):&#xA;&#xA;  File "av/stream.pyx", line 153, in av.stream.Stream.encode&#xA;&#xA;  File "av/codec/context.pyx", line 484, in av.codec.context.CodecContext.encode&#xA;&#xA;  File "av/audio/codeccontext.pyx", line 42, in av.audio.codeccontext.AudioCodecContext._prepare_frames_for_encode&#xA;&#xA;  File "av/audio/resampler.pyx", line 101, in av.audio.resampler.AudioResampler.resample&#xA;&#xA;  File "av/filter/graph.pyx", line 211, in av.filter.graph.Graph.push&#xA;&#xA;  File "av/filter/context.pyx", line 89, in av.filter.context.FilterContext.push&#xA;&#xA;  File "av/error.pyx", line 336, in av.error.err_check&#xA;&#xA;ValueError: [Errno 22] Invalid argument&#xA;&#xA;</module>

  


  edit : It's interesting that the error happens on the 2nd AudioFrame, as apparently the first one was encoded okay, because they are given the same attribute values aside from the Presentation Time Stamp (pts), but leaving this out and letting PyAV/ffmpeg generate the PTS by itself does not fix the error, so an incorrect PTS does not seem the cause.

  


  After a brief glance in av/filter/context.pyx the exception must come from a bad return value from res = lib.av_buffersrc_write_frame(self.ptr, frame.ptr)
  
Trying to dig into av_buffersrc_write_frame from the ffmpeg source it is not clear what could be causing this error. The only obvious one is a mismatch between channel layouts, but my code is setting the layout the same in the Stream and the Frame. That problem had been found by an old question pyav - cannot save stream as mono and their answer (that one parameter required is undocumented) is the only reason the code now has the layout='mono' argument when making the stream.

  


  The program output shows layout #4 is being used, and from https://github.com/FFmpeg/FFmpeg/blob/release/4.2/libavutil/channel_layout.h you can see this is the value for symbol AV_CH_FRONT_CENTER which is the only channel in the MONO layout.

  


  The mismatch is surely some other object property or an undocumented parameter requirement.

  


  How do you encode mono audio to a compressed stream with PyAV ?

  


• Are there any examples on how to create RTMP video streaming using FFMPEG (C++) ? [on hold]

  17 décembre 2017, par JavaRunner

  Are there any examples on how to create RTMP video streaming using FFMPEG (C++) ?
  I know FFMPEG can work with RTMP protocol but I don’t know how to use it for creating my own C++ application to make a rtmp stream.

• ffmpeg ffplay udp streaming quality and error [closed]

  1er janvier 2023, par SangEun Shin

  I am receiving udp streaming through ffmpeg ffplay, but there is a problem that the video is broken.
I'm using a Gopro Hero 11 camera, but I can't receive more than three camera streams because the streaming is fixed with the udp 8554 port.

  


  So using Raspberry pie 4 and nginx reverse proxy for each camera, multi camera streaming succesfully received on another raspberry pie.

  


  In conclusion, gopro camera udp streaming -> raspberrypi received. use nginx reverse proxy -> another raspberry pi received.

  


  However, there is an issue that streaming video quality is broken.
  
I used ffplay :
ffplay udp://@:23002

  


  and the following error also appears :

  


  [h264 @ 0x91cb4ed0] reference picture missing during reorderf=0/0   
[h264 @ 0x91cb4ed0] Missing reference picture, default is 65559
[h264 @ 0x91d234d0] reference picture missing during reorder
[h264 @ 0x91d234d0] Missing reference picture, default is 65559
[h264 @ 0x93028ba0] reference picture missing during reorderf=0/0   
[h264 @ 0x93028ba0] Missing reference picture, default is 65560
[h264 @ 0x9302d6d0] mmco: unref short failure 0KB sq=    0B f=0/0   
[h264 @ 0x9302d6d0] number of reference frames (0+3) exceeds max (2; probably corrupt input), discarding one
[mpegts @ 0x93000630] Packet corrupt (stream = 0, dts = 73156083)
[mpegts @ 0x93000630] Packet corrupt (stream = 0, dts = 73159086)
[mpegts @ 0x93000630] Packet corrupt (stream = 0, dts = 73165092)
[h264 @ 0x9302d6d0] reference picture missing during reorderf=0/0   
[h264 @ 0x9302d6d0] Missing reference picture, default is 65540
[h264 @ 0x930e08e0] reference picture missing during reorderf=0/0   
[h264 @ 0x930e08e0] Missing reference picture, default is 65541


  


  so i use ffplay option -fflag +discardcorrupt. and
use -vf "setpts=N/60/TB".

  


  conclusion : ffplay udp://@:23002 -fflag +discardcorrupt -vf "setpts=N/60/TB"

  


  img

  


  It's better than before, but is still breaks when the change in streaming video is large.

  


  and The packet corrupt still remains, I don't know how to set the pts value that fits the streaming video.

  


  Or is there an issue that I didn't find ?

  


  I'm looking for a way to match the pts.

  


  But I wonder if this is the right way.

  


  I'd appreciate your help to the lost.