End-to-End Speech Processing Toolkit

This github repo is for Neurips 2021 and Interspeech 2022 papers on Non-Matching Reference based estimation of speech quality assessment.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

Vox-Profile Benchmark

Self-Supervised Speech Pre-training and Representation Learning Toolkit.

A song aesthetic evaluation toolkit trained on SongEval.

UTokyo-SaruLab MOS Prediction System

Python implementation of performance metrics in Loizou's Speech Enhancement book

Reference-aware automatic speech evaluation toolkit

Unified automatic quality assessment for speech, music, and sound.

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

A simple library for Fréchet Audio Distance (FAD) calculation

SCOREQ: Speech COntrastive REgression for Quality Assessment (NeurIPS 2024)

Learning audio concepts from natural language supervision

Speech Human Evaluation Estimation Toolkit (SHEET)

This code is to run the WARP-Q speech quality metric.

Python code for Fairseq maintained by ESPnet

Easy-to-Use Speech MOS predictors

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.