A simple library for Fréchet Audio Distance (FAD) calculation
☆246Aug 22, 2025Updated 6 months ago
Alternatives and similar repositories for fadtk
Users that are interested in fadtk are comparing it to the libraries listed below
Sorting:
- A lightweight library for Frechet Audio Distance calculation.☆309Feb 11, 2026Updated 2 weeks ago
- A standardized toolkit of Kernel Audio Distance (KAD)—a distribution-free, unbiased, and computationally efficient metric for evaluating …☆95Jun 12, 2025Updated 8 months ago
- Metrics for evaluating music and audio generative models – with a focus on long-form, full-band, and stereo generations.☆283Jan 30, 2026Updated 3 weeks ago
- ☆117Feb 14, 2026Updated 2 weeks ago
- Encode and decode audio samples to/from compressed latent representations!☆247Sep 19, 2025Updated 5 months ago
- GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch☆135Feb 3, 2025Updated last year
- ☆251Feb 14, 2024Updated 2 years ago
- Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'☆101Jul 24, 2024Updated last year
- Inference codebase for "Cacophony: An Improved Contrastive Audio-Text Model". Preprint: https://arxiv.org/abs/2402.06986☆48Jan 19, 2026Updated last month
- Official repo for DisCoder: High-Fidelity Music Vocoder using Neural Audio Codecs presented at ICASSP 2025☆38Feb 24, 2025Updated last year
- Unified automatic quality assessment for speech, music, and sound.☆675Jun 5, 2025Updated 8 months ago
- Collection of audio-focused loss functions in PyTorch☆851Jul 30, 2024Updated last year
- State-of-the-art pretrained music models for training, evaluation, inference☆163Jan 20, 2026Updated last month
- Official implementation of the paper "Acoustic Music Understanding Model with Large-Scale Self-supervised Training".☆434May 25, 2025Updated 9 months ago
- ☆62Nov 6, 2023Updated 2 years ago
- AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model☆291Oct 12, 2025Updated 4 months ago
- Differentiable audio signal processors in PyTorch☆283Dec 4, 2023Updated 2 years ago
- A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation☆144Nov 30, 2025Updated 3 months ago
- MiRA (Music Replication Assessment) tool is a model-independent open evaluation method based on four diverse audio music similarity metri…☆34Nov 14, 2025Updated 3 months ago
- Compute distribution-based quality metrics for audio data using embeddings, with a focus on music.☆43Jan 15, 2026Updated last month
- a list of demo websites for automatic music generation research☆772Feb 9, 2026Updated 2 weeks ago
- All-In-One Music Structure Analyzer☆721May 9, 2024Updated last year
- The MIR-MLPop dataset and the official implementation of the paper "MIR-MLPop: A Multilingual Pop Music Dataset with Time-Aligned Lyrics …☆33Apr 22, 2024Updated last year
- Models and code for RepCodec: A Speech Representation Codec for Speech Tokenization☆192Jul 12, 2024Updated last year
- The official implementation of TokenSynth (ICASSP 2025)☆79Oct 27, 2025Updated 4 months ago
- PAM is a no-reference audio quality metric for audio generation tasks☆77Jul 19, 2024Updated last year
- applying audio FX with text descriptors☆33Nov 12, 2025Updated 3 months ago
- Project for MIDI to Audio Synthesis☆27Mar 13, 2023Updated 2 years ago
- Official Implementation of EnCLAP (ICASSP 2024)☆94Jun 2, 2024Updated last year
- Audio Codec Speech processing Universal PERformance Benchmark☆297Jan 8, 2026Updated last month
- Expressive Anechoic Recordings of Speech (EARS)☆209Jun 25, 2024Updated last year
- open soundstream-ish VAE codecs for downstream neural audio synthesis☆121Jun 12, 2023Updated 2 years ago
- ☆38Jun 16, 2024Updated last year
- AQUA-Tk = Audio QUality Assessment-Toolkit. (In development)☆102Dec 8, 2025Updated 2 months ago
- PyTorch implementation of the ICASSP-24 paper: "Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Superv…☆38Jan 6, 2024Updated 2 years ago
- Contrastive Language-Audio Pretraining☆2,033May 15, 2025Updated 9 months ago
- [ICASSP 2025] "FLowHigh: Towards efficient and high-quality audio super-resolution with single-step flow matching"☆108Jan 17, 2025Updated last year
- Official implementation of SawSing (ISMIR'22)☆272Aug 28, 2022Updated 3 years ago
- music generation with masked transformers!☆350May 16, 2025Updated 9 months ago