baseZhang 1.4.7

mir-feature-tools @ZHANG Xu-long

• ver: 1.4.6 split youZhang

• ver: 1.4.4 fdu-network and update countDays

• ver: 1.4.3 downGUI beta

• ver: 1.4.1 calc combine audio features and extract subFeat from the combine one

• ver: 1.4.0 calc librosa spectral feature

• ver: 1.3.31 downGUI

• ver: 1.3.30 youtubePdfDown

• ver: 1.3.28 spec gammatone and both plot

• ver: 1.3.27 add gammatone spec

• ver: 1.3.25 get spec and graph spec

• ver: 1.3.23 reduce List Filter

• ver: 1.3.21 download youtube link

• ver: 1.3.20 write mat

• ver: 1.3.19 scaler

• ver: 1.3.18 normalize data

• ver: 1.3.17 ./

• ver: 1.3.16 ./

• ver: 1.3.15 /docs

• ver: 1.3.14 del datafile for subdir

• ver: 1.3.13 modify index

• ver: 1.3.12 index.md modify

• ver: 1.3.11 add datafiles

• ver: 1.3.10 add normalization dataset minmax and meanstd

• ver: 1.3.9 just add chang log modify long description

# A python module for audio and music processing

# baseZhang [](https://pypi.python.org/pypi/baseZhang) [](https://pypi.python.org/pypi/baseZhang)

# @windows

1. choose python 2.7.13 and pls use the X86 not the X86-X64 installer package.

2. install scipy by the 32bit installer package of exe.

3. change backend from tensorflow to theano

   search your file system and find the keras.json file. change the contends from tensorflow to theano.

4. download and install ffmpeg from ffmpeg.org

5. use pip install baseZhang

# install_requires

[‘numpy==1.12.1’, ‘pandas==0.19.2’, ‘matplotlib==2.0.0’, ‘h5py==2.7.0’, ‘tqdm==4.11.2’,

‘PyAudio==0.2.11’, ‘pydub==0.18.0’, ‘pyPdf==1.13’, ‘PyYAML==3.12’, ‘six==1.10.0’, ‘SoundFile==0.9.0.post1’, ‘Theano==0.9.0’, ‘scikit-learn==0.18.1’, ‘Keras==1.2.2’],