Recherche avancée

Sur d’autres sites (17733)

• Detect audio silence in AVFrame using AutoGen in C# for FFmpeg

  16 novembre 2016, par williamtroup

  I’m currently reading audio frames as follows :

  AVFrame* frame = ffmpeg.av_frame_alloc();
  
  
  
  while (ffmpeg.av_read_frame(formatContext, &packet) >= 0)
  
  {
  
      if (packet.stream_index == streamIndex)
  
      {
  
          while (packet.size > 0)
  
          {
  
              int frameDecoded;
  
              int frameDecodedResult = ffmpeg.avcodec_decode_audio4(codecContext, frame, &frameDecoded, packet);
  
  
  
              if (frameDecoded > 0 && frameDecodedResult >= 0)
  
              {
  
                  packet.data += totalBytesDecoded;
  
                  packet.size -= totalBytesDecoded;
  
              }
  
          }
  
  
  
          frameIndex++;
  
      }
  
  
  
      Avcodec.av_free_packet(&packet);
  
  }

  In this loop, I want to be able to detect if "frame" contains silent audio before doing anything with it. Is there a filter to do this ? Been struggling with this for a few days.

  Many thanks in advance.

• 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);
}


  


• aacsbr : silence message for SBR extension "padding".

  9 avril 2012, par Reimar Döffinger

  aacsbr : silence message for SBR extension "padding".
  Some files contain a few additional, all-0 bits.
  
  Check for that case and don’t print incorrect "not supported"
  
  message.
  Signed-off-by : Reimar Döffinger <Reimar.Doeffinger@gmx.de>
  
  Signed-off-by : Alex Converse <alex.converse@gmail.com>
  

  • [DBH] libavcodec/aacsbr.c