OpenS2S : Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model

[EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

"Cyberpunk style" for matplotlib plots

Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS

Whisper realtime streaming for long speech-to-text transcription and translation

Generating Talking Face Landmarks from Speech

Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Flower: A Friendly Federated AI Framework

Source code for LCN submission for ADReSS-M challenge (formerly called MADReSS).

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

😸 💬 A module to compute textual lexical richness (aka lexical diversity).

A Python wrapper for the high-quality vocoder "World"

This is a pytorch implementation of the paper: StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

Single shot neural network pruning before training the model, based on connection sensitivity

Low-level Python library used to interact with a Substra network

Papr Readr Bot

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

an editor for spoken-word audio with automatic transcription

Robust Speech Recognition via Large-Scale Weak Supervision

A collection of utilities for handling IPA phones.

Automatic classification of the Big-Five personality traits from texts using embeddings and Long short-term memory network.

Dr.VOT is an a software package for automatic measurement of voice onset time (VOT).

add statistical significance annotations on seaborn plots. Further development of statannot, with bugfixes, new features, and a different API.