private void ResetSpectrogram()
{
int sampleRate = audioControl1.SampleRate;
int fftSize = 1 << 14;
int samplesInTenMinutes = sampleRate * 60 * 10;
int targetWidth = settings.targetWidth;
int stepSize = samplesInTenMinutes / targetWidth;
spec = new Spectrogram.Spectrogram(sampleRate, fftSize, stepSize, fixedWidth: targetWidth);
spec.SetColormap(cmaps.Where(x => x.Name == settings.colormap).First());
// reset the spectrogram based on where we are in the 10 minute block
ResetSpectrogramPosition();
// resize the image based on the spectrogram dimensions
bmpSpectrogram = new Bitmap(
width: spec.Width + verticalScaleWidth,
height: spec.Height / settings.verticalReduction,
format: PixelFormat.Format32bppPArgb);
pictureBox1.Image = bmpSpectrogram;
pictureBox1.Size = pictureBox1.Image.Size;
Width = pictureBox1.Width + 33;
UpdateVerticalScale();
Status($"Spectrogram reset");
}
public SuccessViewModel CalculateSuccess(SongViewModel song)
{
try
{
SongBE entity;
entity = Mapper.Map <SongViewModel, SongBE>(song);
SongDAL songDAL = new SongDAL();
SuccessViewModel successViewModel = new SuccessViewModel();
var listSongs = songDAL.GetSongsToCalculate(entity.Category);
(int sampleRate, double[] audio) = WavFile.ReadMono(FileUtils.GetRepoMusicPath(song.SongKey));
var spec = new Spectrogram.Spectrogram(sampleRate / 2, fftSize: (16384 / 8), stepSize: (2500 * 5), maxFreq: 2200);
spec.Add(audio);
var tempPath = Path.GetTempPath();
spec.SaveImage(tempPath + "/" + song.SongKey + ".jpg", intensity: 5, dB: true);
var file = FileUtils.GetImageBytes(tempPath + "/" + song.SongKey + ".jpg");
successViewModel.ImageBase64 = "data:image/jpg;base64," + Convert.ToBase64String(file);
var bmHash = this.GetHash(spec.GetBitmap());
List <Spectrogram.Spectrogram> spectrograms = new List <Spectrogram.Spectrogram>();
foreach (var son in listSongs)
{
(int sampleRateSong, double[] audioSong) = WavFile.ReadMono(FileUtils.GetRepoMusicPath(son.SongKey));
var specSong = new Spectrogram.Spectrogram(sampleRateSong / 2, fftSize: (16384 / 8), stepSize: (2500 * 5), maxFreq: 2200);
specSong.Add(audioSong);
spectrograms.Add(specSong);
}
int equalElements = 0;
foreach (var sp in spectrograms)
{
equalElements += bmHash.Zip(this.GetHash(sp.GetBitmap()), (i, j) => i == j).Count(eq => eq);
}
var con = Convert.ToInt32(equalElements / spectrograms.Count);
successViewModel.Percentage = Convert.ToInt32((con * 100) / bmHash.Count);
return(successViewModel);
}
catch (Exception ex)
{
throw new Exception(Messages.Generic_Error);
}
}
public SFF(Spectrogram spec, int melBinCount = 0)
{
SampleRate = spec.SampleRate;
StepSize = spec.StepSize;
Width = spec.Width;
FftSize = spec.FftSize;
FftFirstIndex = spec.NextColumnIndex;
Height = spec.Height;
OffsetHz = spec.OffsetHz;
MelBinCount = melBinCount;
Ffts = (melBinCount > 0) ? spec.GetMelFFTs(melBinCount) : spec.GetFFTs();
CalculateTimes();
CalculateFrequencies();
}
//Sets up a listener for the selected microphone and initializes a spectrogram display
public void StartListening()
{
int sampleRate = Int32.Parse(sampleRates[cbSampleRate.SelectedIndex]);
int fftSize = 1 << (9 + cbFFTsize.SelectedIndex);
int stepSize = fftSize - (int)(fftSize * overlap);
listener?.Dispose();
listener = new Listener(cbMicInput.SelectedIndex, sampleRate);
spec = new Spectrogram.Spectrogram(sampleRate, fftSize, stepSize);
if (cmaps != null)
{
spec.SetColormap(cmaps[cbCmaps.SelectedIndex]); //todo this is a hack for this running before SpecInit
}
stft = new FFTs(spec.GetFFTs(), spec.SampleRate, spec.StepSize, spec.GetWindow());
}
private void btnConectionPort_Click(object sender, EventArgs e)
{
//if (this.logger is null)
//{
// string comPort = this.cmbComPort.SelectedItem.ToString();
// this.logger = new SerialDataLogger(comPort, channelCount: 1);
// this.btnConectionPort.Text = "Close";
//}
//else
//{
// this.logger.Dispose();
// this.logger = null;
// this.cmbComPort.Text = "Open";
//}
#if DEBUG
if (this.btnConectionPort.Text == "Open")
{
string comPort = this.cmbComPort.SelectedItem.ToString();
this.ssd = new SerialSignalData(comPort, baudRate: 115200);
this.btnConectionPort.Text = "Close";
this.tmrTimeSeriesGraphRender.Enabled = true;
this.tmrSpectrogramGraphRender.Enabled = true;
this.Notch50 = new IIRFilter(int.Parse(this.cmbSampleRate.SelectedItem.ToString()), 50, 5);
this.spectrogram = new Spectrogram.Spectrogram(128, 128, 25);
this.pbSpectrogram.Height = this.spectrogram.Height;
this.pbScaleVert.Image?.Dispose();
this.pbScaleVert.Image = this.spectrogram.GetVerticalScale(this.pbScaleVert.Width);
this.pbScaleVert.Height = this.spectrogram.Height;
}
else
{
this.btnConectionPort.Text = "Open";
this.tmrTimeSeriesGraphRender.Enabled = false;
this.tmrSpectrogramGraphRender.Enabled = false;
}
#else
Console.WriteLine("Mode=Other");
#endif
}
public void Start(int deviceIndex = 0, int fftPower = 14, string preLoadWavFile = null)
{
int sampleRate = 8000;
int fftSize = (int)(Math.Pow(2, fftPower));
int tenMinutePixelWidth = 1000;
int samplesInTenMinutes = sampleRate * 10 * 60;
int segmentSize = samplesInTenMinutes / tenMinutePixelWidth;
spec = new Spectrogram.Spectrogram(sampleRate, fftSize, segmentSize);
spec.displaySettings.brightness = 5;
spec.displaySettings.freqLow = 1000;
spec.displaySettings.freqHigh = 1500;
spec.displaySettings.tickSpacingHz = 50;
spec.displaySettings.tickSpacingSec = 30;
formBrightness = new FormBrightness(spec);
formFreqRange = new FormFreqRange(spec);
formFFT = new FormFFT(spec);
pbSpec.Width = tenMinutePixelWidth;
pbSpec.Height = spec.displaySettings.height;
if (preLoadWavFile != null)
{
spec.AddExtend(Tools.ReadWav(preLoadWavFile));
}
else
{
int bitRate = 16;
int channels = 1;
int bufferMilliseconds = 20;
wvin = new NAudio.Wave.WaveInEvent();
wvin.DeviceNumber = deviceIndex;
wvin.WaveFormat = new NAudio.Wave.WaveFormat(sampleRate, bitRate, channels);
wvin.DataAvailable += OnDataAvailable;
wvin.BufferMilliseconds = bufferMilliseconds;
wvin.StartRecording();
}
}
private void StartListening()
{
try
{
int sampleRate = 6000;
int fftSize = SelectedFftSize;
int stepSize = fftSize / 20;
SpectrogamImageSource = null;
listener?.Dispose();
listener = new Listener(DeviceCapabilities.IndexOf(selectedDevice), sampleRate);
spec = new Spectrogram.Spectrogram(sampleRate, fftSize, stepSize);
spec.SetWindow(FftSharp.Window.Rectangular(fftSize));
SpectrogramHeight = spec.Height;
VerticalScaleImageSource = null;
VerticalScaleImageSource = ImageHelpers.BitmapToImageSource(spec.GetVerticalScale(LEGEND_WIDTH));
}
catch (Exception ex)
{
Console.WriteLine("Exeption when attempting to start to listen: " + ex.Message);
}
}
private async Task audio2spectrum_saveVideoAsync(string path)
{
var progressHandler = new Progress <string>(value =>
{
status_txt.Text = value;
});
var progress = progressHandler as IProgress <string>;
await Task.Run(() =>
{
long frameCount;
try
{
double samplesPerFrame = ((double)audio2spectrum_sampleRate) * frameRate.Denominator / frameRate.Numerator;
double totalFrameCount = Math.Ceiling(audio2spectrum_samples.Length / samplesPerFrame);
int roundedSamplesPerFrame = (int)Math.Ceiling(samplesPerFrame);
int outputWidth = 50;
int outputHeight = 50;
double samplesPerPixel = samplesPerFrame / outputWidth;
// Now find closest fft size (take next highest)
int fftSize = (int)Math.Pow(2, Math.Ceiling(Math.Log(samplesPerPixel, 2.0)));
progress.Report("Audio2Spectrum: Loading spectrogram library");
Spectrogram.Spectrogram spec = new Spectrogram.Spectrogram(audio2spectrum_sampleRate, fftSize: 2048, stepSize: 50);
spec.SetFixedWidth(outputWidth);
//outputWidth = spec.Width;
progress.Report("Audio2Spectrum: Initializing video writer");
VideoFileWriter writer = new VideoFileWriter();
writer.Open(path, outputWidth, outputHeight, frameRate, VideoCodec.FFV1);
/*
* Console.WriteLine("width: " + reader.Width);
* Console.WriteLine("height: " + reader.Height);
* Console.WriteLine("fps: " + reader.FrameRate);
* Console.WriteLine("codec: " + reader.CodecName);
* Console.WriteLine("length: " + reader.FrameCount);
*/
frameCount = (long)totalFrameCount;
// Enlarge the array to make sure we don't end up accessing nonexisting samples. We make it a tiny bit bigger than maybe necessary, just to be safe. (To be honest, I am just too lazy to calculate the precise number we need)
/*if((long)Math.Ceiling(frameCount * samplesPerFrame) > audio2spectrum_samples.Length)
* {
* progress.Report("Audio2Spectrum: Resizing array");
* Array.Resize<double>(ref audio2spectrum_samples, (int)Math.Ceiling(frameCount * samplesPerFrame));
* }*/
double[] frameSampleBuffer = new double[roundedSamplesPerFrame];
int currentFrame = 0;
long currentStartSample = 0;
progress.Report("Audio2Spectrum: Starting video generation");
Bitmap tmp;
for (int i = 0; i < frameCount; i++)
{
currentStartSample = (long)Math.Floor(i *samplesPerFrame);
// Doing this branching here now because the resizing the array first was just way way too slow and memory hungry
if (currentStartSample >= audio2spectrum_samples.Length) // Even the first sample is already outside the bounds, just make empty array.
{
frameSampleBuffer = new double[roundedSamplesPerFrame];
}
else if ((currentStartSample + (roundedSamplesPerFrame - 1)) > (audio2spectrum_samples.Length - 1)) // Copy as many samples as possible
{
long difference = (currentStartSample + (roundedSamplesPerFrame - 1)) - (audio2spectrum_samples.Length - 1);
frameSampleBuffer = new double[roundedSamplesPerFrame];
Array.Copy(audio2spectrum_samples, currentStartSample, frameSampleBuffer, 0, roundedSamplesPerFrame - difference);
}
else
{
Array.Copy(audio2spectrum_samples, currentStartSample, frameSampleBuffer, 0, roundedSamplesPerFrame);
}
spec.Add(frameSampleBuffer);
tmp = spec.GetBitmapMel(dB: true, melBinCount: outputHeight);
#if DEBUG
Console.WriteLine(tmp.Width + "x" + tmp.Height);
#endif
writer.WriteVideoFrame(tmp);
if (currentFrame % 1000 == 0)
{
progress.Report("Audio2Spectrum: Saving video: " + i + "/" + frameCount + " frames");
}
}
writer.Close();
}
catch (Exception e)
{
MessageBox.Show(e.Message);
}
});
status_txt.Text = "Audio2Spectrum: Completed saving video.";
videoIsLoaded = true;
}
public async Task <ActionResult> GetPredictionAsync([FromForm] string page, [FromForm] IFormFile audioFile)
{
try
{
var modelPath = "";
if (page == "Login")
{
modelPath = Path.Combine(_env.ContentRootPath, "Models", "MLModelLogin.zip");
}
else if (page == "Language")
{
modelPath = Path.Combine(_env.ContentRootPath, "Models", "MLModelLanguage.zip");
}
else if (page == "Home")
{
modelPath = Path.Combine(_env.ContentRootPath, "Models", "MLModelHome.zip");
}
else if (page == "cart")
{
modelPath = Path.Combine(_env.ContentRootPath, "Models", "MLModelCartPage.zip");
}
else if (page == "singleItem")
{
modelPath = Path.Combine(_env.ContentRootPath, "Models", "MLModelSingleItemPage.zip");
}
else if (page == "category")
{
modelPath = Path.Combine(_env.ContentRootPath, "Models", "MLModelCategory.zip");
}
else if (page == "pay")
{
//var v = @"C:\Users\Frank\source\repos\YorubaModelML\YorubaPredictionAPI\Models\MLModelPayPage.zip";
modelPath = Path.Combine(_env.ContentRootPath, "Models", "MLModelPayPage.zip");
}
var model = new ConsumeModel(modelPath);
var uploadPath = Path.Combine(_env.ContentRootPath, "uploads");
Directory.CreateDirectory(uploadPath);
if (audioFile.Length > 0)
{
var audioFilePath = Path.Combine(uploadPath, audioFile.FileName);
using (var fs = new FileStream(audioFilePath, FileMode.Create))
{
await audioFile.CopyToAsync(fs);
}
double[] audio;
int sampleRate;
using (var audioFileReader = new AudioFileReader(audioFilePath))
{
sampleRate = audioFileReader.WaveFormat.SampleRate;
var wholeFile = new List <float>((int)(audioFileReader.Length / 4));
var readBuffer = new float[audioFileReader.WaveFormat.SampleRate * audioFileReader.WaveFormat.Channels];
int samplesRead = 0;
while ((samplesRead = audioFileReader.Read(readBuffer, 0, readBuffer.Length)) > 0)
{
wholeFile.AddRange(readBuffer.Take(samplesRead));
}
audio = Array.ConvertAll(wholeFile.ToArray(), x => (double)x);
}
int fftSize = 8192;
var spec = new Spectrogram.Spectrogram(sampleRate, 4096, stepSize: 500, maxFreq: 3000, fixedWidth: 250);
spec.Add(audio);
var info = new FileInfo(audioFilePath);
var imagepath = Path.Combine(uploadPath, info.Name + ".png");
spec.SaveImage(imagepath, intensity: 20_000);
var md = new ModelInput {
ImageSource = imagepath
};
var result = model.Predict(md);
Directory.Delete(uploadPath, true);
return(Ok(new { class_id = result.Prediction, probability = result.Score.Max() }));
//return Ok(_env.ContentRootPath);
}
_logger.LogError("File is Null");
return(BadRequest("File is null"));
}
catch (Exception ex)
{
_logger.LogError(ex.Message);
return(BadRequest(ex.Message));
}
}
