DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.
☆237May 5, 2023Updated 2 years ago
Alternatives and similar repositories for diffq
Users that are interested in diffq are comparing it to the libraries listed below
Sorting:
- Accompanying code for our paper "Optimizing Short-Time Fourier Transform Parameters via Gradient Descent"☆34Oct 30, 2020Updated 5 years ago
- Fast PyTorch based DSP for audio and 1D signals☆452Feb 17, 2025Updated last year
- logWMSE, an audio quality metric with support for digital silence target. Useful for evaluating audio source separation systems, even whe…☆37Jun 24, 2025Updated 8 months ago
- Code for the paper: Unified Gradient Reweighting for Model Biasing with Applications to Source Separation☆14Nov 16, 2020Updated 5 years ago
- A library for speech data augmentation in time-domain☆683Aug 30, 2021Updated 4 years ago
- A differentiable version of SPTK☆193Feb 26, 2026Updated last week
- MicRank is a Learning to Rank neural channel selection framework where a DNN is trained to rank microphone channels.☆22Apr 8, 2021Updated 4 years ago
- ☆55Jul 6, 2023Updated 2 years ago
- ✨Listen to the jazz created by an algorithm.☆22Dec 30, 2022Updated 3 years ago
- Permutation invariant training in PyTorch☆13Oct 2, 2020Updated 5 years ago
- Comparison of Python audio resampling implementations☆54Jun 30, 2021Updated 4 years ago
- A PyTorch implementation of the paper: "LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation" (ICAS…☆87Nov 13, 2022Updated 3 years ago
- Utilities for resampling and filtering audio data☆47Jan 9, 2020Updated 6 years ago
- ☆18Jul 14, 2018Updated 7 years ago
- Python bindings for minimp3☆16Sep 11, 2023Updated 2 years ago
- Improving Perceptual Quality by Phone-Fortified Perceptual Loss using Wasserstein Distance for Speech Enhancement☆82Jun 28, 2021Updated 4 years ago
- Yin pitch estimator in PyTorch☆117Nov 7, 2022Updated 3 years ago
- Backpropagable pytorch implementation of https://craffel.github.io/mir_eval/.☆35Jul 8, 2024Updated last year
- Pytorch Implementation of WaveNODE☆64Sep 4, 2020Updated 5 years ago
- Fast, differentiable sorting and ranking in PyTorch☆850Jun 9, 2025Updated 8 months ago
- The training code for the 4th place model at MDX 2021 leaderboard A.☆36Sep 1, 2021Updated 4 years ago
- ☆64Aug 14, 2023Updated 2 years ago
- Python bindings for SoX, aiming to replicate a subset of the command line sox utility.☆56Mar 29, 2021Updated 4 years ago
- Official implementation of EfficientLEAF, a learnable audio frontend.☆48Dec 9, 2022Updated 3 years ago
- Pytorch implementation of LearnableUpsamplingLayer (NaturalSpeech, Tan et al., 2022)☆57Mar 12, 2024Updated last year
- ☆53May 15, 2025Updated 9 months ago
- Code for ICASSP 2019 paper☆18Oct 29, 2018Updated 7 years ago
- ☆26Apr 21, 2021Updated 4 years ago
- SDX23 startkit for the Demucs baselines.☆30Mar 3, 2023Updated 3 years ago
- ☆13Aug 23, 2024Updated last year
- An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.☆368Oct 12, 2021Updated 4 years ago
- PyTorch implementation of the paper "NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity." (NeurIPS 2020)☆67Dec 28, 2020Updated 5 years ago
- ☆32Jul 27, 2022Updated 3 years ago
- Big Impulse Response Dataset☆156Oct 19, 2022Updated 3 years ago
- This repository contains data used in the NAACL 2021 Paper - Proteno: Text Normalization with Limited Data for Fast Deployment in Text to…☆45May 25, 2021Updated 4 years ago
- A Python package of the dynamic compressive gammachirp filterbank (dcGC-FB)☆31May 14, 2024Updated last year
- An template that is specifically designed to demonstrate symbolic musical machine learning models on the web. The template comes with a s…☆19Feb 26, 2019Updated 7 years ago
- Epoch-synchronous overlap-add (ESOLA) for time-and pitch-scale modification of speech signals.☆22Jul 24, 2020Updated 5 years ago
- A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.☆366Feb 16, 2026Updated 2 weeks ago