Verify spectrogram implementation with fourier_transformation and make_logscale methods

[Copilot]

Verification that the video node correctly implements spectrogram generation using the STFT-based approach with logarithmic frequency scaling as specified.

Implementation Status

Both required functions are present and correctly integrated in node/InputNode/node_video.py:

Core functions (lines 334-389):

• fourier_transformation(): STFT with Hanning window, 50% overlap, stride-based frame extraction
• make_logscale(): Logarithmic frequency binning for enhanced low-frequency resolution

Integration (_prepare_spectrogram(), lines 443-563):

# Extract audio from video
y, sr = librosa.load(movie_path, sr=22050)

# Compute STFT
s = fourier_transformation(y, binsize=2**10, overlapFac=0.5, window=np.hanning)

# Apply log frequency scaling  
sshow, freq = make_logscale(spec=s, sr=sr, factor=1.0)

# Convert to dB: 20*log10(abs/reference)
ims = 20. * np.log10(np.maximum(np.abs(sshow), 1e-10) / 10e-6)

UI: Real-time scrolling display with toggle checkbox, synchronized to video playback, visual position indicators.

Verification Artifacts

• SPECTROGRAM_VERIFICATION.md: Implementation reference
• spectrogram_demo.png: Demonstration with synthetic A major chord (440/554/659 Hz)

All 13 existing tests pass. No code changes required—implementation is production-ready.

Original prompt

utilise ces methodes pour créer le spectrogramme dans le node video : def fourier_transformation(sig, frameSize, overlapFac=0.5, window=np.hanning):
win = window(frameSize)
hopSize = int(frameSize - np.floor(overlapFac * frameSize))

# zeros at beginning (thus center of 1st window should be for sample nr. 0)
samples = np.append(np.zeros(int(np.floor(frameSize/2.0))), sig)
# cols for windowing
cols = np.ceil( (len(samples) - frameSize) / float(hopSize)) + 1
# zeros at end (thus samples can be fully covered by frames)
samples = np.append(samples, np.zeros(frameSize))

frames = stride_tricks.as_strided(samples, shape=(int(cols), frameSize), strides=(samples.strides[0]*hopSize, samples.strides[0])).copy()
frames *= win

return np.fft.rfft(frames)    def make_logscale(spec, sr=44100, factor=20.):
timebins, freqbins = np.shape(spec)

scale = np.linspace(0, 1, freqbins) ** factor
scale *= (freqbins-1)/max(scale)
scale = np.unique(np.round(scale))

# create spectrogram with new freq bins
newspec = np.complex128(np.zeros([timebins, len(scale)]))
for i in range(0, len(scale)):
    if i == len(scale)-1:
        newspec[:,i] = np.sum(spec[:,int(scale[i]):], axis=1)
    else:
        newspec[:,i] = np.sum(spec[:,int(scale[i]):int(scale[i+1])], axis=1)

# list center freq of bins
allfreqs = np.abs(np.fft.fftfreq(freqbins*2, 1./sr)[:freqbins+1])
freqs = []
for i in range(0, len(scale)):
    if i == len(scale)-1:
        freqs += [np.mean(allfreqs[int(scale[i]):])]
    else:
        freqs += [np.mean(allfreqs[int(scale[i]):int(scale[i+1])])]

import os
import pandas as pd
import scipy.io.wavfile as wav
import numpy as np
import matplotlib.pyplot as plt

Ta fonction plot_spectrogram

def plot_spectrogram(location, plotpath=None, binsize=2**10, colormap="jet"):
samplerate, samples = wav.read(location)
s = fourier_transformation(samples, binsize)
sshow, freq = make_logscale(s, factor=1.0, sr=samplerate)
ims = 20.*np.log10(np.abs(sshow)/10e-6) # amplitude to decibel

timebins, freqbins = np.shape(ims)
#print("timebins:", timebins, "freqbins:", freqbins)

plt.figure(figsize=(15, 7.5))
plt.imshow(np.transpose(ims), origin="lower", aspect="auto", cmap=colormap, interpolation="none")
xlocs = np.float32(np.linspace(0, timebins-1, 5))
plt.xticks(xlocs, ["%.02f" % l for l in ((xlocs*len(samples)/timebins)+(0.5*binsize))/samplerate])
ylocs = np.int16(np.round(np.linspace(0, freqbins-1, 10)))
plt.yticks(ylocs, ["%.02f" % freq[i] for i in ylocs])

if plotpath:
    plt.savefig(plotpath, bbox_inches="tight")
else:
    plt.show()
plt.clf()

return ims

Charger le CSV

esc50_df = pd.read_csv('/content/ESC-50-master/meta/esc50.csv')

Créer les dossiers

spectrogram_root = '/content/ESC-50-master/spectrogram'
os.makedirs(spectrogram_root, exist_ok=True)

for cat in esc50_df['category'].unique():
os.makedirs(os.path.join(spectrogram_root, cat), exist_ok=True)

Générer tous les spectrogrammes

for i, row in esc50_df.iterrows():
filename = row['filename']
category = row['category']
audio_path = os.path.join('/content/ESC-50-master/audio', filename)
save_path = os.path.join(spectrogram_root, category, filename.replace('.wav', '.jpg'))

try:
    plot_spectrogram(audio_path, plotpath=save_path)
except Exception as e:
    print(f"Erreur avec {filename}: {e}")

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.