Recherche avancée

Sur d’autres sites (4648)

• Dynamically record parts of a video stream using ffmpeg based on incoming events

  12 septembre 2023, par ganjim

  Say I have a RTSP stream running on some server.

  


  I want to record parts of this video stream based on some events that will come up on my machine.
My goal is to record 10 seconds before up to 10 seconds after the PTS in any received event. Consider that I have a way to synchronize the PTS between the sender and the receiver, but by the time I receive the events, its already streamed and is in the past.
So I either need to have the ffmpeg command running already, or to have buffered streaming video in my memory.

  


  I just added some code with comments as a way to simulate the situation, it is not complete as I still don't have a working solution. But I'm looking to understand if ffmpeg has capabilities for dealing with rtsp streams suitable for this situation.

  


  const { spawn } = require('child_process');

function processEvent(event){
  
  let startTime = event.pts - 10
  let endTime = event.pts + 10

  const ffmpegArgs = [
    '-i', "rtspUrl",
    '-ss', startTime.toString(),
    '-to', endTime.toString(),
    '-c', 'copy',
    '-f', 'mp4',
    `output_${startTime}_${endTime}.mp4` // Output filename
  ];
  // Here it is obviously not possible to give ffmpeg a negative startTime.
  // We either have to have spawned the ffmpeg command and somehow give it a starting time for recording on demand or have a buffering system in place.
  // Having a buffer to store every raw frame and then attach them after endTime is also considerably CPU and memory intensive.
  // Looking for alternative ways to achieve the same output.

  const ffmpegProcess = spawn('ffmpeg', ffmpegArgs, {
    stdio: 'inherit'
  });
}

// Code to simulate the events:
// imagine these pts to be relative to Date.now(), so using negative PTS to show the events are going to be in the past by the time we receive them.
setTimeout(() => {
  const event1= { pts: -30 };
  processEvent(event1);
}, 1000);

setTimeout(() => {
  const event2 = { pts: -20 };
  processEvent(event2);
}, 5000);


  


• Detect volume via mic, start recording, end on silence, transcribe and sent to endpoint

  15 juin 2023, par alphadmon

  I have been attempting to get this to work in many ways but I can't seem to get it right. Most of the time I get a part of it to work and then when I try to make other parts work, I generally break other things.

  


  I am intercepting the volume coming from the mic and if it is louder than 50, I start a recording. I then keep recording until there is a silence, if the silence is equal to 5 seconds I then stop the recording.

  


  I then send the recording to be transcribed by whisper using OpenAI API.

  


  Once that is returned, I then want to send it to the open ai chat end point and get the response.

  


  After that, I would like to start listening again.

  


  Here is what I have that is sort of working so far, but the recording is an empty file always :

  


  // DETECT SPEECH
const recorder = require('node-record-lpcm16');

// TRANSCRIBE
const fs = require("fs");
const ffmpeg = require("fluent-ffmpeg");
const mic = require("mic");
const { Readable } = require("stream");
const ffmpegPath = require("@ffmpeg-installer/ffmpeg").path;
require('dotenv').config();

// CHAT
const { Configuration, OpenAIApi } = require("openai");

// OPEN AI
const configuration = new Configuration({
    organization: process.env.OPENAI_ORG,
    apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);

// SETUP
ffmpeg.setFfmpegPath(ffmpegPath);

// VARS
let isRecording = false;
const audioFilename = 'recorded_audio.wav';
const micInstance = mic({
    rate: '16000',
    channels: '1',
    fileType: 'wav',
});

// DETECT SPEECH
const file = fs.createWriteStream('determine_speech.wav', { encoding: 'binary' });
const recording = recorder.record();
recording.stream().pipe(file);


recording.stream().on('data', async (data) => {
    let volume = parseInt(calculateVolume(data));
    if (volume > 50 && !isRecording) {
        console.log('You are talking.');
        await recordAudio(audioFilename);
    } else {
        setTimeout(async () => {
            console.log('You are quiet.');
            micInstance.stop();
            console.log('Finished recording');
            const transcription = await transcribeAudio(audioFilename);
            console.log('Transcription:', transcription);
            setTimeout(async () => {
                await askAI(transcription);
            }, 5000);
        }, 5000);
    }
});

function calculateVolume(data) {
    let sum = 0;

    for (let i = 0; i < data.length; i += 2) {
        const sample = data.readInt16LE(i);
        sum += sample * sample;
    }

    const rms = Math.sqrt(sum / (data.length / 2));

    return rms;
}

// TRANSCRIBE
function recordAudio(filename) {
    const micInputStream = micInstance.getAudioStream();
    const output = fs.createWriteStream(filename);
    const writable = new Readable().wrap(micInputStream);

    console.log('Listening...');

    writable.pipe(output);

    micInstance.start();

    micInputStream.on('error', (err) => {
        console.error(err);
    });
}

// Transcribe audio
async function transcribeAudio(filename) {
    const transcript = await openai.createTranscription(
        fs.createReadStream(filename),
        "whisper-1",
    );
    return transcript.data.text;
}

// CHAT
async function askAI(text) {
    let completion = await openai.createChatCompletion({
        model: "gpt-4",
        temperature: 0.2,
        stream: false,
        messages: [
            { role: "user", content: text },
            { role: "system", content: "Act like you are a rude person." }
        ],
    });

    completion = JSON.stringify(completion.data, null, 2);
    console.log(completion);
}


  


• How to save variables at start of script for use later if script needs to be re-run due to errors or bad user input

  28 novembre 2023, par slyfox1186

  I have a script that uses GitHub's API to get the latest version number of the repositories that I am trying to download and then compile.

  


  Due to the fact that without using a specialized token from GitHub you are only allowed 50 API calls a day vs the 5000 a day with the API user token.

  


  I want to be able to parse all of the repositories and grab the version numbers that my script will then import into the code up front so in case someone who accidentally cancels the build in the middle of it (for who knows what reasons) wont have to eat up their 50 day API call allowance.

  


  Essentially, store each repo's version number, if the user then needs to rerun the script and version numbers that have been saved so far will be skipped (thus eliminating an API call) and any numbers that are still needing to be sourced will be called and then stored for used in the script.

  


  I am kinda of lost for a method on how to go about this.

  


  Maybe some sort of external file can be generated ?

  


  So what my script does is it builds FFmpeg from source code and all of the external libraries that you can link to it are also built from their latest source code.

  


  The code calls the function git_ver_fn and passes arguments to it which are parsed inside the function and directed to another functions git_1_fn or git_2_fn which passed those parsed arguments that have been passed on to the CURL command which changes the URL based on the arguments passed. It uses the jq command to capture the GitHub version number and download link for the tar.gz file.

  


  It is the version number I am and trying to figure out the best way to store in case the script fails and has to be rerun, which will eat up all of the 50 APT limit that GitHub imposes without a token. I can't post my token in the script because GitHub deactivates it and thus the users will be SOL if they need to run the script more than once.

  


  curl_timeout='5'

git_1_fn()
{
    # SCRAPE GITHUB WEBSITE FOR LATEST REPO VERSION
    github_repo="$1"
    github_url="$2"

    if curl_cmd="$(curl -m "$curl_timeout" -sSL "https://api.github.com/repos/$github_repo/$github_url")"; then
        g_ver="$(echo "$curl_cmd" | jq -r '.[0].name')"
        g_ver="${g_ver#v}"
        g_ssl="$(echo "$curl_cmd" | jq -r '.[0].name')"
        g_ssl="${g_ssl#OpenSSL }"
        g_pkg="$(echo "$curl_cmd" | jq -r '.[0].name')"
        g_pkg="${g_pkg#pkg-config-}"
        g_url="$(echo "$curl_cmd" | jq -r '.[0].tarball_url')"
    fi
}

git_2_fn()
{
    videolan_repo="$1"
    videolan_url="$2"
    if curl_cmd="$(curl -m "$curl_timeout" -sSL "https://code.videolan.org/api/v4/projects/$videolan_repo/repository/$videolan_url")"; then
        g_ver="$(echo "$curl_cmd" | jq -r '.[0].commit.id')"
        g_sver="$(echo "$curl_cmd" | jq -r '.[0].commit.short_id')"
        g_ver1="$(echo "$curl_cmd" | jq -r '.[0].name')"
        g_ver1="${g_ver1#v}"
    fi
}

git_ver_fn()
{
    local v_flag v_tag url_tag

    v_url="$1"
    v_tag="$2"

    if [ -n "$3" ]; then v_flag="$3"; fi

    if [ "$v_flag" = 'B' ] && [  "$v_tag" = '2' ]; then
        url_tag='git_2_fn' gv_url='branches'
    fi

    if [ "$v_flag" = 'X' ] && [  "$v_tag" = '5' ]; then
        url_tag='git_5_fn'
    fi

    if [ "$v_flag" = 'T' ] && [  "$v_tag" = '1' ]; then
        url_tag='git_1_fn' gv_url='tags'
    elif [ "$v_flag" = 'T' ] && [  "$v_tag" = '2' ]; then
        url_tag='git_2_fn' gv_url='tags'
    fi

    if [ "$v_flag" = 'R' ] && [  "$v_tag" = '1' ]; then
        url_tag='git_1_fn'; gv_url='releases'
    elif [ "$v_flag" = 'R' ] && [  "$v_tag" = '2' ]; then
        url_tag='git_2_fn'; gv_url='releases'
    fi

    case "$v_tag" in
        2)          url_tag='git_2_fn';;
    esac

    "$url_tag" "$v_url" "$gv_url" 2>/dev/null
}

# begin source code building
git_ver_fn 'freedesktop/pkg-config' '1' 'T'
if build 'pkg-config' "$g_pkg"; then
    download "https://pkgconfig.freedesktop.org/releases/$g_ver.tar.gz" "$g_ver.tar.gz"
    execute ./configure --silent --prefix="$workspace" --with-pc-path="$workspace"/lib/pkgconfig/ --with-internal-glib
    execute make -j "$cpu_threads"
    execute make install
    build_done 'pkg-config' "$g_pkg"
fi

git_ver_fn 'yasm/yasm' '1' 'T'
if build 'yasm' "$g_ver"; then
    download "https://github.com/yasm/yasm/releases/download/v$g_ver/yasm-$g_ver.tar.gz" "yasm-$g_ver.tar.gz"
    execute ./configure --prefix="$workspace"
    execute make -j "$cpu_threads"
    execute make install
    build_done 'yasm' "$g_ver"
fi