This is the PyTorch implementation of the Universal Source Separation with Weakly labelled Data.

Collection of Open Source Speech Data

DUSTED: Spoken-Term Discovery using Discrete Speech Units

Official Implementation of TSELM: Target speaker extraction using discrete tokens and language models

ICASSP2025Dynamic Embedding Causal Target Speech Extraction

Target Speaker Extraction Toolkit

SSR-Speech: Towards Stable, Safe and Robust Zero-shot Speech Editing and Synthesis

GANs for time series generation in pytorch

Lightweight wrapper for Silero VAD using internal ONNX Runtime and with no python package dependencies

Focus on prompting and generating

Source code for ACL 2023 paper "End-to-End Simultaneous Speech Translation with Differentiable Segmentation"

ControlSpeech: Towards Simultaneous Zero-shot Speaker Cloning and Zero-shot Language Style Control With Decoupled Codec

StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Official Implementation for "Only a Matter of Style: Age Transformation Using a Style-Based Regression Model" (SIGGRAPH 2021) https://arxiv.org/abs/2102.02754

A deep learning model to age faces in the wild, currently runs at 60+ fps on GPUs

The official pytorch implemention of the Intespeech 2024 paper "Reshape Dimensions Network for Speaker Recognition"

A fast speech-to-any translation model that supports simultaneous decoding and offers 28× speedup.

Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".

Code for ACL 2024 findings paper "CTC-based Non-autoregressive Textless Speech-to-Speech Translation"