Stack Overflow
Stack Overflow

Questions tagged [librosa]

librosa is a python package for music and audio analysis.

Following are some of the features of librosa

  • Load audio input
  • Compute mel-spectrogram, MFCC, delta features, chroma
  • Invert mel-spectrogram, MFCC or chroma back to waveform
  • Locate beat events
  • Compute beat-synchronous features
  • Display features
  • Save beat tracker output to a CSV file

For detailed information and examples, visit the librosa documentation.

See also the official Github page.

750 questions
0
votes
1 answer

Python cannot import name 'NUMPY_MKL'

I am trying to run a wavenet implementation (which uses tensorflow + librosa). However, I keep running into the error "cannot import name 'NUMPY_MKL'". I have already installed tensorflow, numpy+mk1, scipy and librosa. Tensorflow itself is loading…
Lincoln
  • 11
  • 2
0
votes
0 answers

Librosa on jython

I installed Jython 2.7.1 and want to get librosa to work to get theier mfcc transformations to work. I have issues installing it as it seems to rely on numpy which uses C but Jpython does not do C. I found JyNi as some layer in-between to get this…
jonas.hartwig
  • 857
  • 3
  • 8
  • 19
0
votes
1 answer

how to normalize fft values for neural networks

I calculate the fft for a given soundfile and get an array of the shape e.g. (100,257) with 100 rows and 257 frequency bins. I want to use this as an input vector for a neural network but before I want to normalize with librosa lib…
KyleReemoN-
  • 504
  • 2
  • 8
  • 16
0
votes
1 answer

librosa write_wav in mono?

I want to resample a mono recording recordered in 40.000 Hz to 44100 Hz. The code below works but librosa seems to save in stereo, making the file twice the size which is not needed and I have a lot of samples to process. So I need to save the…
Hugo Koopmans
  • 1,349
  • 1
  • 15
  • 27
0
votes
1 answer

Why is the image stored and show different?

I am having some problems saving the image I am displaying as numpy ndarays. Example: This code: librosa.display.specshow(static.T,sr=16000,x_axis='frames',y_axis='mel',hop_length=160,cmap=cm.jet) plt.title("log mel power spectrum of " +…
Fixining_ranges
  • 223
  • 1
  • 13
0
votes
1 answer

Slicing audio signal to detect pitch

I am using Librosa to transcribe monophonic guitar audio signals. I thought that, it would be a good start to "slice" the signal depending on the onset times, to detect note changes at the correct time. Librosa provides a function that detects the…
pavlos163
  • 2,730
  • 4
  • 38
  • 82
0
votes
1 answer

Why is image stored different than the one imshowed?

I am currently not able to understand why I am not able to recreate the plot after I store the data.. import os import sys from os import listdir from os.path import isfile, join import numpy as np import matplotlib.pyplot as plt from…
Fixining_ranges
  • 223
  • 1
  • 13
0
votes
1 answer

Applying a window function to a frame in librosa

I am currently working on an ASR system, and I've forgotten to apply a window function to each frame. I am extracting, which could be the cause to why I am receiving bad results. But is that possible in librosa? I can't find this option in librosa…
Carlton Banks
  • 395
  • 1
  • 6
  • 25
0
votes
0 answers

Why I am not able to output or store the full list?

I am currently trying to sample an audio file, such that i can use the samples to train a neural network. The problem is that i am not able to view all the samples, or store them in a file such that I don't need to do the sampling everytime i test…
J.Down
  • 700
  • 1
  • 9
  • 32
-1
votes
0 answers

Splitting an audio file into different plots and datasets when a sound plays

I am learning some python audio processing and was wondering how I could split an audio file into different amplitude time plots when a sound plays. For example if the audio file is a guitar that plays four notes and different times I would like to…
LostSocks
  • 17
  • 5
-1
votes
1 answer

Couldn't install librosa on windows

i tried to install librosa on Pycharm (windows)but i had this error: ERROR: Could not build wheels for soxr, which is required to install pyproject.toml-based projects I used all three following commands and no one worked: pip innstall librosa pip…
Alchask
  • 1
  • 1
-1
votes
1 answer

How to use flask to receive wav file and load it with librosa?

I received a wav file from the front end and got a FileStorage object with request.files.get('file'). How can I load it in librosa? audio = request.files.get('file') data, sampling_rate = librosa.load(audio) and the error below showed TypeError:…
Sheyh
  • 13
  • 1
-1
votes
1 answer

Audio frequency analysis - Python

I generated this spectrogram (hann window, logaritmic scale) with Audacity. I need to generate similar data with Python basing on .wav file. Does anyone know, which libraries/functions should I use?
pablo99
  • 21
  • 1
  • 5
-1
votes
1 answer

How to install librosa on virtuualenv?

I'm trying to install librosa inside virtualenv using python version 3.10.0 and this is what I get. The error is much longer as it keeps trying to install scikit-learn more than once before exiting with error status 1. I'm not also sure why it's…
Shaheen
  • 31
  • 6
-1
votes
1 answer

Is there any way to convert spectrogram into MFCCs directly?

Is there any way to convert spectrogram into MFCCs directly? If yes, kindly provide python script for that. Thanks
Priyazeet257
  • 9
  • 2
1 2 3
…
49
50