Recherche avancée

Sur d’autres sites (9644)

• Improving Google Cloud Speech-to-Text accuracy

  6 juillet 2020, par lr_optim

  I'm working on a project where I need to perform these steps :

  


  

  1. Record a voice call (.webm -file)

  


  2. Split the webm -file into chunks with ffmpeg and convert the file into wav

  


  3. Transcribe the chunks using SpeechRecognition -library and Google Cloud API

  


  


  I've faced problems with the transcription accuracy and wondering if there is something I could do to improve it. At the time I'm splitting the original file into 30s chunks. I thought there might be one problem, that I might be missing words because of splitting so I've tried also with longer chunks under 60s but didn't notice any improve in accuracy.
Reading trough the speechRecognition docs I decided to set r.energy_threshold = 4000, I also tried to set the energy_treshold dynamically like this :

  


  with sr.AudioFile(name) as source:
    r.dynamic_energy_threshold = True
    r.adjust_for_ambient_noise(source, duration = 1)
    audio = r.record(source)


  


  I've also tested en-US and en-GB to see if there's some difference but there isn't as much as I'd want. The program is supposed to work with english language spoken by nordic people. If someone has experience about choosing a right language model for people speaking with accent, please let me know.

  


  This is the ffmpeg command is use to split the webm file into chunks : command = ['ffmpeg', '-i', filename, '-f', 'segment', '-segment_time', '30', parts_dir + outputname + '%09d.wav']

  


  Is there somethig I could do better ? I'm wondering if the quality is not good enough an Google is having hard time because of that ?

  


  The main problem is I'm getting bad results (lots of wrong words) from Google and wondering if there is something I could do about it.

  


• Cannot convert .ogg file to .mp3 or other file formats

  15 août 2020, par mancgain

  I am trying to convert ogg audio file to mp3 or other audio file formats that can be played in ios devices But ogg files are not being converted into other formats like mp3 and caf. I am testing the conversion in android device.

  


  This is my ffmpeg command arguments :

  


  Command: "ffmpeg -y -i $inputFilePath -c:a copy $outputFilePath"
Both input and output filenames were surrounded with quotations

 [-y, -i, /data/user/0/com.musicapp/files/composer_audios/testtt ogg file.ogg, -c:a, copy, /storage/emulated/0/Android/data/com.musicapp/files/ball.mp3]


  


  When I try to convert into mp3 . this error is thrown :

  


   FFmpeg exited with rc: 1
 [mp3 @ 0x73f7b36a00] Invalid audio stream. Exactly one MP3 audio stream is required.
Could not write header for output file #0 (incorrect codec parameters ?): Invalid argument


  


  When I try to convert into .caf file this error is thrown :

  


  
FFmpeg exited with rc: 1
 [caf @ 0x73f7b36a00] unsupported codec
 Could not write header for output file #0 (incorrect codec parameters ?): Invalid data found when processing input



  


  But if I try to convert mp3 file to formats like caf, mkv, mp4, no error is thrown.

  


• How to change or modify pitch of audio file (music etc like .mp3 file)using FFMPEG ?

  18 octobre 2022, par syed kashifullah

  I want to change and modify pitch an .mp3 audio file using FFMPEG.
But I am unable to use FFMPEG to change or modify pitch of that sound.
what command (exact command) should be exactly use for changing pitch of an audio file ?

  


   String outPutPath = new File("/storage/emulated/0/Share it Application/Over_the_HorizonTemp.wav").getPath();
                 
                String[] strFfmpeg  = {"ffmpeg","-i" ,strInputPath,"-af", "rubberband=tempo=1.0:pitch=1.5:pitchq=quality" ,outPutPath};
                execffmpegBinary(strFfmpeg);


  


  execffmpegBinary Function :

  


  public void execffmpegBinary(String[] command) {
    Config.enableLogCallback(new LogCallback() {
        @Override
        public void apply(LogMessage message) {
            Log.e(Config.TAG, message.getText());
            Log.e("TAG", "apply: " +message.getText());
        }
    });
    Config.enableStatisticsCallback(new StatisticsCallback() {
        @Override
        public void apply(Statistics statistics) {

        }
    });

    long executionId = FFmpeg.executeAsync(command, new ExecuteCallback() {
        @Override
        public void apply(long executionId, int returnCode) {
            if (returnCode == RETURN_CODE_SUCCESS) {
                
                Log.e("1TAG", "apply:return code "+returnCode );
                Log.e("1TAG", "apply:execution Id "+executionId );
                Log.e("1TAG", "apply:execution Id "+ new FFmpegExecution(executionId,command));


            } else if (returnCode == RETURN_CODE_CANCEL) {
                Log.e("2TAG", "apply:return code "+returnCode );
                Log.e("2TAG", "apply:execution Id "+executionId );
                Log.e("2TAG", "apply:execution Id "+ new FFmpegExecution(executionId,command));

            } else {
                Log.e("3TAG", "apply: returnCode"+ returnCode);
                Log.e("3TAG", "apply:return code "+returnCode );
                Log.e("3TAG", "apply:execution Id "+executionId );
                Log.e("3TAG", "apply:execution Id "+ new FFmpegExecution(executionId,command));

            }
        }
    });
}