
Recherche avancée
Médias (1)
-
Rennes Emotion Map 2010-11
19 octobre 2011, par
Mis à jour : Juillet 2013
Langue : français
Type : Texte
Autres articles (82)
-
MediaSPIP 0.1 Beta version
25 avril 2011, parMediaSPIP 0.1 beta is the first version of MediaSPIP proclaimed as "usable".
The zip file provided here only contains the sources of MediaSPIP in its standalone version.
To get a working installation, you must manually install all-software dependencies on the server.
If you want to use this archive for an installation in "farm mode", you will also need to proceed to other manual (...) -
MediaSPIP version 0.1 Beta
16 avril 2011, parMediaSPIP 0.1 beta est la première version de MediaSPIP décrétée comme "utilisable".
Le fichier zip ici présent contient uniquement les sources de MediaSPIP en version standalone.
Pour avoir une installation fonctionnelle, il est nécessaire d’installer manuellement l’ensemble des dépendances logicielles sur le serveur.
Si vous souhaitez utiliser cette archive pour une installation en mode ferme, il vous faudra également procéder à d’autres modifications (...) -
Le profil des utilisateurs
12 avril 2011, parChaque utilisateur dispose d’une page de profil lui permettant de modifier ses informations personnelle. Dans le menu de haut de page par défaut, un élément de menu est automatiquement créé à l’initialisation de MediaSPIP, visible uniquement si le visiteur est identifié sur le site.
L’utilisateur a accès à la modification de profil depuis sa page auteur, un lien dans la navigation "Modifier votre profil" est (...)
Sur d’autres sites (10768)
-
ffmpeg failed to load audio file
14 avril 2024, par Vaishnav GhengeFailed to load audio: ffmpeg version 5.1.4-0+deb12u1 Copyright (c) Failed to load audio: ffmpeg version 5.1.4-0+deb12u1 Copyright (c) 2000-2023 the FFmpeg developers
 built with gcc 12 (Debian 12.2.0-14)
 configuration: --prefix=/usr --extra-version=0+deb12u1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librist --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --disable-sndio --enable-libjxl --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-libplacebo --enable-librav1e --enable-shared
 libavutil 57. 28.100 / 57. 28.100
 libavcodec 59. 37.100 / 59. 37.100
 libavformat 59. 27.100 / 59. 27.100
 libavdevice 59. 7.100 / 59. 7.100
 libavfilter 8. 44.100 / 8. 44.100
 libswscale 6. 7.100 / 6. 7.100
 libswresample 4. 7.100 / 4. 7.100
 libpostproc 56. 6.100 / 56. 6.100
/tmp/tmpjlchcpdm.wav: Invalid data found when processing input



backend :



@app.route("/transcribe", methods=["POST"])
def transcribe():
 # Check if audio file is present in the request
 if 'audio_file' not in request.files:
 return jsonify({"error": "No file part"}), 400
 
 audio_file = request.files.get('audio_file')

 # Check if audio_file is sent in files
 if not audio_file:
 return jsonify({"error": "`audio_file` is missing in request.files"}), 400

 # Check if the file is present
 if audio_file.filename == '':
 return jsonify({"error": "No selected file"}), 400

 # Save the file with a unique name
 filename = secure_filename(audio_file.filename)
 unique_filename = os.path.join("uploads", str(uuid.uuid4()) + '_' + filename)
 # audio_file.save(unique_filename)
 
 # Read the contents of the audio file
 contents = audio_file.read()

 max_file_size = 500 * 1024 * 1024
 if len(contents) > max_file_size:
 return jsonify({"error": "File is too large"}), 400

 # Check if the file extension suggests it's a WAV file
 if not filename.lower().endswith('.wav'):
 # Delete the file if it's not a WAV file
 os.remove(unique_filename)
 return jsonify({"error": "Only WAV files are supported"}), 400

 print(f"\033[92m{filename}\033[0m")

 # Call Celery task asynchronously
 result = transcribe_audio.delay(contents)

 return jsonify({
 "task_id": result.id,
 "status": "pending"
 })


@celery_app.task
def transcribe_audio(contents):
 # Transcribe the audio
 try:
 # Create a temporary file to save the audio data
 with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_audio:
 temp_path = temp_audio.name
 temp_audio.write(contents)

 print(f"\033[92mFile temporary path: {temp_path}\033[0m")
 transcribe_start_time = time.time()

 # Transcribe the audio
 transcription = transcribe_with_whisper(temp_path)
 
 transcribe_end_time = time.time()
 print(f"\033[92mTranscripted text: {transcription}\033[0m")

 return transcription, transcribe_end_time - transcribe_start_time

 except Exception as e:
 print(f"\033[92mError: {e}\033[0m")
 return str(e)



frontend :


useEffect(() => {
 const init = () => {
 navigator.mediaDevices.getUserMedia({audio: true})
 .then((audioStream) => {
 const recorder = new MediaRecorder(audioStream);

 recorder.ondataavailable = e => {
 if (e.data.size > 0) {
 setChunks(prevChunks => [...prevChunks, e.data]);
 }
 };

 recorder.onerror = (e) => {
 console.log("error: ", e);
 }

 recorder.onstart = () => {
 console.log("started");
 }

 recorder.start();

 setStream(audioStream);
 setRecorder(recorder);
 });
 }

 init();

 return () => {
 if (recorder && recorder.state === 'recording') {
 recorder.stop();
 }

 if (stream) {
 stream.getTracks().forEach(track => track.stop());
 }
 }
 }, []);

 useEffect(() => {
 // Send chunks of audio data to the backend at regular intervals
 const intervalId = setInterval(() => {
 if (recorder && recorder.state === 'recording') {
 recorder.requestData(); // Trigger data available event
 }
 }, 8000); // Adjust the interval as needed


 return () => {
 if (intervalId) {
 console.log("Interval cleared");
 clearInterval(intervalId);
 }
 };
 }, [recorder]);

 useEffect(() => {
 const processAudio = async () => {
 if (chunks.length > 0) {
 // Send the latest chunk to the server for transcription
 const latestChunk = chunks[chunks.length - 1];

 const audioBlob = new Blob([latestChunk]);
 convertBlobToAudioFile(audioBlob);
 }
 };

 void processAudio();
 }, [chunks]);

 const convertBlobToAudioFile = useCallback((blob: Blob) => {
 // Convert Blob to audio file (e.g., WAV)
 // This conversion may require using a third-party library or service
 // For example, you can use the MediaRecorder API to record audio in WAV format directly
 // Alternatively, you can use a library like recorderjs to perform the conversion
 // Here's a simplified example using recorderjs:

 const reader = new FileReader();
 reader.onload = () => {
 const audioBuffer = reader.result; // ArrayBuffer containing audio data

 // Send audioBuffer to Flask server or perform further processing
 sendAudioToFlask(audioBuffer as ArrayBuffer);
 };

 reader.readAsArrayBuffer(blob);
 }, []);

 const sendAudioToFlask = useCallback((audioBuffer: ArrayBuffer) => {
 const formData = new FormData();
 formData.append('audio_file', new Blob([audioBuffer]), `speech_audio.wav`);

 console.log(formData.get("audio_file"));

 fetch('http://34.87.75.138:8000/transcribe', {
 method: 'POST',
 body: formData
 })
 .then(response => response.json())
 .then((data: { task_id: string, status: string }) => {
 pendingTaskIdsRef.current.push(data.task_id);
 })
 .catch(error => {
 console.error('Error sending audio to Flask server:', error);
 });
 }, []);



I was trying to pass the audio from frontend to whisper model which is in flask app


-
How to improve web camera streaming latency to v4l2loopback device with ffmpeg ?
11 mars, par Made by MosesI'm trying to stream my iPhone camera to my PC on LAN.


What I've done :


- 

-
HTTP server with html page and streaming script :


I use WebSockets here and maybe WebRTC is better choice but it seems like network latency is good enough






async function beginCameraStream() {
 const mediaStream = await navigator.mediaDevices.getUserMedia({
 video: { facingMode: "user" },
 });

 websocket = new WebSocket(SERVER_URL);

 websocket.onopen = () => {
 console.log("WS connected");

 const options = { mimeType: "video/mp4", videoBitsPerSecond: 1_000_000 };
 mediaRecorder = new MediaRecorder(mediaStream, options);

 mediaRecorder.ondataavailable = async (event) => {
 // to measure latency I prepend timestamp to the actual video bytes chunk
 const timestamp = Date.now();
 const timestampBuffer = new ArrayBuffer(8);
 const dataView = new DataView(timestampBuffer);
 dataView.setBigUint64(0, BigInt(timestamp), true);
 const data = await event.data.bytes();

 const result = new Uint8Array(data.byteLength + 8);
 result.set(new Uint8Array(timestampBuffer), 0);
 result.set(data, 8);

 websocket.send(result);
 };

 mediaRecorder.start(100); // Collect 100ms chunks
 };
}



- 

-
Server to process video chunks






import { serve } from "bun";
import { Readable } from "stream";

const V4L2LOOPBACK_DEVICE = "/dev/video10";

export const setupFFmpeg = (v4l2device) => {
 // prettier-ignore
 return spawn("ffmpeg", [
 '-i', 'pipe:0', // Read from stdin
 '-pix_fmt', 'yuv420p', // Pixel format
 '-r', '30', // Target 30 fps
 '-f', 'v4l2', // Output format
 v4l2device, // Output to v4l2loopback device
 ]);
};

export class FfmpegStream extends Readable {
 _read() {
 // This is called when the stream wants more data
 // We push data when we get chunks
 }
}

function main() {
 const ffmpeg = setupFFmpeg(V4L2LOOPBACK_DEVICE);
 serve({
 port: 8000,
 fetch(req, server) {
 if (server.upgrade(req)) {
 return; // Upgraded to WebSocket
 }
 },
 websocket: {
 open(ws) {
 console.log("Client connected");
 const stream = new FfmpegStream();
 stream.pipe(ffmpeg?.stdin);

 ws.data = {
 stream,
 received: 0,
 };
 },
 async message(ws, message) {
 const view = new DataView(message.buffer, 0, 8);
 const ts = Number(view.getBigUint64(0, true));
 ws.data.received += message.byteLength;
 const chunk = new Uint8Array(message.buffer, 8, message.byteLength - 8);

 ws.data.stream.push(chunk);

 console.log(
 [
 `latency: ${Date.now() - ts} ms`,
 `chunk: ${message.byteLength}`,
 `total: ${ws.data.received}`,
 ].join(" | "),
 );
 },
 },
 });
}

main();



After I try to open the v4l2loopback device


cvlc v4l2:///dev/video10



picture is delayed for at least 1.5 sec which is unacceptable for my project.


Thoughts :


- 

- Problem doesn't seems to be with network latency




latency: 140 ms | chunk: 661 Bytes | total: 661 Bytes
latency: 206 ms | chunk: 16.76 KB | total: 17.41 KB
latency: 141 ms | chunk: 11.28 KB | total: 28.68 KB
latency: 141 ms | chunk: 13.05 KB | total: 41.74 KB
latency: 199 ms | chunk: 11.39 KB | total: 53.13 KB
latency: 141 ms | chunk: 16.94 KB | total: 70.07 KB
latency: 139 ms | chunk: 12.67 KB | total: 82.74 KB
latency: 142 ms | chunk: 13.14 KB | total: 95.88 KB



150ms is actually too much for 15KB on LAN but there can some issue with my router


- 

- As far as I can tell it neither ties to ffmpeg throughput :




Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'pipe:0':
 Metadata:
 major_brand : iso5
 minor_version : 1
 compatible_brands: isomiso5hlsf
 creation_time : 2025-03-09T17:16:49.000000Z
 Duration: 00:00:01.38, start:
0.000000, bitrate: N/A
 Stream #0:0(und): Video: h264 (Baseline) (avc1 / 0x31637661), yuvj420p(pc), 1280x720, 4012 kb/s, 57.14 fps, 29.83 tbr, 600 tbn, 1200 tbc (default)
 Metadata:
 rotate : 90
 creation_time : 2025-03-09T17:16:49.000000Z
 handler_name : Core Media Video
 Side data:
 displaymatrix: rotation of -90.00 degrees

Stream mapping:
 Stream #0:0 -> #0:0 (h264 (native) -> rawvideo (native))

[swscaler @ 0x55d8d0b83100] deprecated pixel format used, make sure you did set range correctly

Output #0, video4linux2,v4l2, to '/dev/video10':
 Metadata:
 major_brand : iso5
 minor_version : 1
 compatible_brands: isomiso5hlsf
 encoder : Lavf58.45.100

Stream #0:0(und): Video: rawvideo (I420 / 0x30323449), yuv420p, 720x1280, q=2-31, 663552 kb/s, 60 fps, 60 tbn, 60 tbc (default)
 Metadata:
 encoder : Lavc58.91.100 rawvideo
 creation_time : 2025-03-09T17:16:49.000000Z
 handler_name : Core Media Video
 Side data:
 displaymatrix: rotation of -0.00 degrees

frame= 99 fps=0.0 q=-0.0 size=N/A time=00:00:01.65 bitrate=N/A dup=50 drop=0 speed=2.77x
frame= 137 fps=114 q=-0.0 size=N/A time=00:00:02.28 bitrate=N/A dup=69 drop=0 speed=1.89x
frame= 173 fps= 98 q=-0.0 size=N/A time=00:00:02.88 bitrate=N/A dup=87 drop=0 speed=1.63x
frame= 210 fps= 86 q=-0.0 size=N/A time=00:00:03.50 bitrate=N/A dup=105 drop=0 speed=1.44x
frame= 249 fps= 81 q=-0.0 size=N/A time=00:00:04.15 bitrate=N/A dup=125 drop=0 speed=1.36
frame= 279 fps= 78 q=-0.0 size=N/A time=00:00:04.65 bitrate=N/A dup=139 drop=0 speed=1.31x



- 

-
I also tried to write the video stream directly to
video.mp4
file and immediately open it withvlc
but it only can be successfully opened after 1.5 sec.

-
I've tried to use OBS v4l2 input source instead of vlc but the latency is the same








Update №1


When i try to stream actual
.mp4
file toffmpeg
it works almost immediately with 0.2sec delay to spin up the ffmpeg itself :

cat video.mp4 | ffmpeg -re -i pipe:0 -pix_fmt yuv420p -f v4l2 /dev/video10 & ; sleep 0.2 && cvlc v4l2:///dev/video10



So the problem is apparently with streaming process


-
-
how to add audio using ffmpeg when recording video from browser and streaming to Youtube/Twitch ?
26 juillet 2021, par Tosh VelagaI have a web application I am working on that allows the user to stream video from their browser and simultaneously livestream to both Youtube and Twitch using ffmpeg. The application works fine when I don't need to send any of the audio. Currently I am getting the error below when I try to record video and audio. I am new to using ffmpeg and so any help would be greatly appreciated. Here is also my repo if needed : https://github.com/toshvelaga/livestream


Here is my node.js server with ffmpeg


const child_process = require('child_process') // To be used later for running FFmpeg
const express = require('express')
const http = require('http')
const WebSocketServer = require('ws').Server
const NodeMediaServer = require('node-media-server')
const app = express()
const cors = require('cors')
const path = require('path')
const logger = require('morgan')
require('dotenv').config()

app.use(logger('dev'))
app.use(cors())

app.use(express.json({ limit: '200mb', extended: true }))
app.use(
 express.urlencoded({ limit: '200mb', extended: true, parameterLimit: 50000 })
)

var authRouter = require('./routes/auth')
var compareCodeRouter = require('./routes/compareCode')

app.use('/', authRouter)
app.use('/', compareCodeRouter)

if (process.env.NODE_ENV === 'production') {
 // serve static content
 // npm run build
 app.use(express.static(path.join(__dirname, 'client/build')))

 app.get('*', (req, res) => {
 res.sendFile(path.join(__dirname, 'client/build', 'index.html'))
 })
}

const PORT = process.env.PORT || 8080

app.listen(PORT, () => {
 console.log(`Server is starting on port ${PORT}`)
})

const server = http.createServer(app).listen(3000, () => {
 console.log('Listening on PORT 3000...')
})


const wss = new WebSocketServer({
 server: server,
})

wss.on('connection', (ws, req) => {
 const ffmpeg = child_process.spawn('ffmpeg', [
 // works fine when I use this but when I need audio problems arise
 // '-f',
 // 'lavfi',
 // '-i',
 // 'anullsrc',

 '-i',
 '-',

 '-f',
 'flv',
 '-c',
 'copy',
 `${process.env.TWITCH_STREAM_ADDRESS}`,
 '-f',
 'flv',
 '-c',
 'copy',
 `${process.env.YOUTUBE_STREAM_ADDRESS}`,
 // '-f',
 // 'flv',
 // '-c',
 // 'copy',
 // `${process.env.FACEBOOK_STREAM_ADDRESS}`,
 ])

 ffmpeg.on('close', (code, signal) => {
 console.log(
 'FFmpeg child process closed, code ' + code + ', signal ' + signal
 )
 ws.terminate()
 })

 ffmpeg.stdin.on('error', (e) => {
 console.log('FFmpeg STDIN Error', e)
 })

 ffmpeg.stderr.on('data', (data) => {
 console.log('FFmpeg STDERR:', data.toString())
 })

 ws.on('message', (msg) => {
 console.log('DATA', msg)
 ffmpeg.stdin.write(msg)
 })

 ws.on('close', (e) => {
 console.log('kill: SIGINT')
 ffmpeg.kill('SIGINT')
 })
})

const config = {
 rtmp: {
 port: 1935,
 chunk_size: 60000,
 gop_cache: true,
 ping: 30,
 ping_timeout: 60,
 },
 http: {
 port: 8000,
 allow_origin: '*',
 },
}

var nms = new NodeMediaServer(config)
nms.run()



Here is my frontend code that records the video/audio and sends to server :


import React, { useState, useEffect, useRef } from 'react'
import Navbar from '../../components/Navbar/Navbar'
import './Dashboard.css'

const CAPTURE_OPTIONS = {
 audio: true,
 video: true,
}

function Dashboard() {
 const [mute, setMute] = useState(false)
 const videoRef = useRef()
 const ws = useRef()
 const mediaStream = useUserMedia(CAPTURE_OPTIONS)

 let liveStream
 let liveStreamRecorder

 if (mediaStream && videoRef.current && !videoRef.current.srcObject) {
 videoRef.current.srcObject = mediaStream
 }

 const handleCanPlay = () => {
 videoRef.current.play()
 }

 useEffect(() => {
 ws.current = new WebSocket(
 window.location.protocol.replace('http', 'ws') +
 '//' + // http: -> ws:, https: -> wss:
 'localhost:3000'
 )

 ws.current.onopen = () => {
 console.log('WebSocket Open')
 }

 return () => {
 ws.current.close()
 }
 }, [])

 const startStream = () => {
 liveStream = videoRef.current.captureStream(30) // 30 FPS
 liveStreamRecorder = new MediaRecorder(liveStream, {
 mimeType: 'video/webm;codecs=h264',
 videoBitsPerSecond: 3 * 1024 * 1024,
 })
 liveStreamRecorder.ondataavailable = (e) => {
 ws.current.send(e.data)
 console.log('send data', e.data)
 }
 // Start recording, and dump data every second
 liveStreamRecorder.start(1000)
 }

 const stopStream = () => {
 liveStreamRecorder.stop()
 ws.current.close()
 }

 const toggleMute = () => {
 setMute(!mute)
 }

 return (
 <>
 <navbar></navbar>
 <div style="{{" classname="'main'">
 <div>
 
 </div>
 <div classname="'button-container'">
 <button>Go Live</button>
 <button>Stop Recording</button>
 <button>Share Screen</button>
 <button>Mute</button>
 </div>
 </div>
 >
 )
}

const useUserMedia = (requestedMedia) => {
 const [mediaStream, setMediaStream] = useState(null)

 useEffect(() => {
 async function enableStream() {
 try {
 const stream = await navigator.mediaDevices.getUserMedia(requestedMedia)
 setMediaStream(stream)
 } catch (err) {
 console.log(err)
 }
 }

 if (!mediaStream) {
 enableStream()
 } else {
 return function cleanup() {
 mediaStream.getVideoTracks().forEach((track) => {
 track.stop()
 })
 }
 }
 }, [mediaStream, requestedMedia])

 return mediaStream
}

export default Dashboard