awesome-python-audio
Awesome Python resources related to audio and music
https://github.com/andreimatveyeu/awesome-python-audio
Last synced: 17 days ago
JSON representation
Analysis & Feature Extraction
Audio Embeddings & Representations
- CLAP (LAION) - Audio Pretraining for zero-shot audio classification
- CLAP (Microsoft)
- OpenL3 - source deep audio and image embeddings
- panns-inference
- wav2vec2 - supervised speech representations from Facebook AI
Audio Processing & I/O
- numpy & scipy.io.wavfile
- wave
- audiomentations
- audioread - library audio decoding (GStreamer + Core Audio + MAD + FFmpeg)
- babycat
- matchering
- Matchering-cli
- noisereduce
- pedalboard
- pyAudioProcessing
- PyDub
- torchaudio
- SoundDevice
- torch-audiomentations
- soundfile
Datasets
Audio
- AudioSet - scale dataset of manually annotated audio events
- Birdsong
- TIDIGITS
- UrbanSound8K
- VCTK
- ESC-50
- Free Spoken Digit Dataset
- Freesound Dataset
- RAVDESS - visual dataset of emotional speech and song
- Common Voice
- LibriSpeech
- Speech Commands
- VoxCeleb - scale speaker identification dataset
Music
- DEAM
- IRMAS
- MAESTRO
- MedleyDB - track mixing research
- Musdb18
- NSynth - scale dataset of annotated musical notes
- RWC Music Database
- DALI
- FMA
- hsmusic
- Jamendo Audio Tagging - label audio tagging dataset
- symbolic-music-datasets
- The Million Song Dataset
- Beatport EDM Key
- MagnaTagATune
- GiantMIDI-Piano - scale MIDI dataset of classical piano music
- LAION-Audio-630K - text pairs for CLAP training
- MusicCaps
- MusicNet
- Open MIC
Music Generation & AI
Text-to-Speech
- NSynth
- Magenta
- musicautobot
- AudioCraft
- Stable Audio Tools
- Riffusion - time music generation using stable diffusion on spectrograms
Music Theory & Composition
Text-to-Speech
Music Transcription & Pitch
Text-to-Speech
- basic-pitch
- CREPE
- torchcrepe
- MT3 - instrument automatic music transcription from Google Magenta
- piano_transcription_inference - resolution piano transcription with pedal detection
Playback & Services
Text-to-Speech
- freesound-python
- audiostream
- beets
- discord.py
- Mopidy
- Mopidy-YouTube
- mpv
- MusicBot
- pygame.mixer
- pyglet - platform windowing and multimedia library
- pyradio
- miniaudio
- pyAV
- Spotipy
Source Separation
Text-to-Speech
- Spleeter
- pydsm
- Demucs - of-the-art music source separation from Meta
- audio-separator - Net VR Arch and Demucs models
- Asteroid - based audio source separation toolkit for researchers
Speech Processing
Speech-to-Text
- Whisper
- faster-whisper
- WhisperX - level timestamps and speaker diarization
- SpeechRecognition
- Vosk
- SpeechBrain
- pyannote-audio