lifeiteng

vall-e

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

naturalspeech3_facodec

FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3

SoundStorm

NaturalSpeech2

TTS-TextAnalyzer

TTS Text Analyzer

VoiceBox

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

Optimizers

Tensorflow Optimizers

audio-ai-timeline

A timeline of the latest AI models for audio generation, starting in 2023!

kaldifeat

Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API

lhotse

Tools for handling speech data in machine learning projects.

reverb

Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

SpeechTokenizer

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

warp-ctc

Fast parallel CTC.

cpp-taskflow

Fast Parallel Tasking Programming Library using Modern C++

fairseq2

FAIR Sequence Modeling Toolkit 2

FBGEMM

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

google-research

Google AI Research

io

Dataset, streaming, and file system extensions maintained by TensorFlow SIG-IO

kaldi

This is now the official location of the Kaldi project.

kaldialign

Python wrappers for Kaldi Levenshtein's distance and alignment code.

lifeiteng.github.com

demos page

Montreal-Forced-Aligner

Command line utility for forced alignment using Kaldi

open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

REAPER

RL101

My implementations of reinforcement learning algorithms

sonic

Simple library to speed up or slow down speech

spektral

Graph Neural Networks with Keras and Tensorflow 2.

text

Making text a first-class citizen in TensorFlow.

THULAC

An Efficient Lexical Analyzer for Chinese