Audio Python Packages

transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

sounddevice

:sound: Play and Record Sound with Python :snake:

torchaudio

Data manipulation and transformation for audio signal processing, powered by PyTorch

librosa

Python library for audio and music analysis

audioread

cross-library (GStreamer + Core Audio + MAD + FFmpeg) audio decoding for Python

speechrecognition

Speech recognition module for Python, supporting several engines and APIs, online and offline.

resampy

Efficient sample rate conversion in python

tinytag

Python library for reading audio file metadata

asteroid-filterbanks

Asteroid's filterbanks :rocket:

torch-audiomentations

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

descript-audio-codec

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

conformer

Implementation of the convolutional module from the Conformer paper, for use in Transformers

auraloss

Collection of audio-focused loss functions in PyTorch

audiomentations

A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

snac

Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate

python-stretch

Simple python library for pitch shifting and time stretching. Wrapper of Signalsmith Stretch C++ Library

voxcpm

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

hume

Python client for Hume AI

ntgcalls

A Native Implementation of Telegram Calls in a seamless way.

silk-python

stream encoder/decoder for silk and pcm

stftpitchshift

STFT based real-time pitch and timbre shifting in C++ and Python

pytorch-pretrained-bert

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

audiofile

Handling audio files in Python

pyacoustid

Python bindings for Chromaprint acoustic fingerprinting and the Acoustid Web service