MUS 15 Project 2: Audio Transcription¶
Test¶
Gino Prasad, Saba Heydari Seradj, Ashish Dalvi¶
05/27/2023¶
For our MUS 15 project, our group created an audio transcriber from scratch. All of the code was made from scratch by us using python.
We have uploaded this code to https://github.com/GinoP123/MusicTranscription
In [11]:
import torch
import torchaudio
from IPython.display import Audio
import numpy as np
import matplotlib.pyplot as plt
from scipy.fft import fft, ifft
import scipy.ndimage
import pandas as pd
import tqdm
print(torch.__version__)
print(torchaudio.__version__)
2.0.0.dev20221214 0.14.0.dev20221214
Loading Example Audio¶
In [12]:
audio_path = 'wav_files/audio1623001661.wav'
In [13]:
bruyeres_wav, sample_rate = torchaudio.load(audio_path)
bruyeres_wav = bruyeres_wav[0][19*sample_rate:-7*sample_rate]
In [14]:
Audio(bruyeres_wav, rate=sample_rate)
Out[14]: