Spectra Extraction based on PyTorch
Considering the pytorch-kalda is presented, so it is more practical to use it. Also, SpeechBrain, A PyTorch-based Speech Toolkit, is coming. I am looking forward to a nice step on speech. To conclude, this package is used to learn spectra of a signal, so it is valuable at all.
This library provides common spectra features from an audio signal including MFCCs and filter bank energies. This library mimics the library
python_speech_features but PyTorch-style.
This library provides voice activity detection (VAD) based on energy. This library mimics the library
VAD-python but PyTorch-style.
Use: Rui Wang. (2020, March 14). mechanicalsea/spectra: release v0.4.0 (Version 0.4.0).
This library is avaliable on pypi.org
To install from Pypi:
pip install --upgrade spectra-torch
- python: 3.7.3
- torch: 1.4.0
- torchaudio: 0.4.0
- Mel Frequency Cepstral Coefficients (MFCC)
- Filterbank Energies
- Log Filterbank Energies
- Voice Activity Detection (VAD)
Here are examples.
# Ensure cuda is available. import spectra_torch.base as mm import torchaudio as ta sig, sr = ta.load_wav('piece_20_32k.wav') sig = sig.cuda() mfcc = mm.mfcc(sig, sr) # MFCC starts, detection = mm.is_speech(sig, sr, speechlen=0.5) # VAD
Tutorials of MFCC and VAD is provided at notebooks.
Step-by-step description is presented. Welcome to enjoy it.
The difference between
- Precision bais: 1e-4
- Speed up: 0.1s/mfcc
def mfcc(signal, samplerate=16000, winlen=0.025, hoplen=0.01, numcep=13, nfilt=26, nfft=None, lowfreq=0, highfreq=None, preemph=0.97, ceplifter=22, plusEnergy=True)
def fbank(signal, samplerate=16000, winlen=0.025, hoplen=0.01, nfilt=26, nfft=512, lowfreq=0, highfreq=None, preemph=0.97)
def is_speech(signal, samplerate=16000, winlen=0.02, hoplen=0.01, thresEnergy=0.6, speechlen=0.5, lowfreq=300, highfreq=3000, preemph=0.97)
Thanks for you attention.
Free for question to my email (firstname.lastname@example.org).
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Hashes for spectra_torch-0.4.0-py2.py3-none-any.whl