Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

A python package to build AI-powered real-time audio applications

Speaker embedding (d-vector) trained with GE2E loss

Keras implementation of ‘’Deep Speaker: an End-to-End Neural Speaker Embedding System‘’ (speaker recognition)

Fine-tuning toolkit for Chatterbox TTS & Chatterbox TURBO models. Supports 23 languages with smart vocabulary extension. Features offline preprocessing, automatic VAD trimming, and voice cloning capabilities. Train custom TTS models with your own dataset in LJSpeech and file-based format.

Speaker diarization for Python — "who spoke when?" CPU-only, no API keys, Apache 2.0. ~10.8% DER on VoxConverse, 8x faster than real-time.

A pipeline to read lips and generate speech for the read content, i.e Lip to Speech Synthesis.

PyTorch implementation of Densely Connected Time Delay Neural Network

Companion repository for the paper "A Comparison of Metric Learning Loss Functions for End-to-End Speaker Verification" published at SLSP 2020

On-device speaker recognition engine powered by deep learning

A curated list of speaker-embedding speaker-verification, speaker-identification resources.

Voxceleb1 i-vector based speaker recognition system

Luigi pipeline to download VoxCeleb(2) audio from YouTube and extract speaker segments

Train voice styles for Supertone/supertonic-3 model.

Trained speaker embedding deep learning models and evaluation pipelines in pytorch and tesorflow for speaker recognition.

PyTorch implementation of the 1D-Triplet-CNN neural network model described in Fusing MFCC and LPC Features using 1D Triplet CNN for Speaker Recognition in Severely Degraded Audio Signals by A. Chowdhury, and A. Ross.

Speaker embedding for VI-SVC and VI-SVS, alse for VITS; Use this to replace the ID to implement voice clone.

Awesome Speech Dataset, including download links and a brief explanation for each resource. These datasets provide diverse and high-quality speech data covering various domains such as conversational, academic, political, and more.

DropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020