Takaaki-Saeki

pflowtts_pytorch

Unofficial implementation of NVIDIA P-Flow TTS paper

TTS-arxiv-daily

Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)

PAM

PAM is a no-reference audio quality metric for audio generation tasks

LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

pflow-encodec

Implementation of TTS model based on NVIDIA P-Flow TTS Paper

DDDM-VC

Official Pytorch Implementation for "DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion" (AAAI 2024)

Codec-SUPERB

Audio Codec Speech processing Universal PERformance Benchmark

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

SpeechGPT

SpeechGPT Series: Speech Large Language Models

mamba

Mamba SSM architecture

DiscreteSpeechMetrics

Reference-aware automatic speech evaluation toolkit

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

ssl_speech_restoration_v2

AcademiCodec

AcademiCodec: An Open Source Audio Codec Model for Academic Research

ai-audio-startups

Community list of startups working with AI in audio and music technology

PLMpapers

Must-read Papers on pre-trained language models.

Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

voicebox-pytorch

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

contentvec

speech self-supervised representations

CML-TTS-Dataset

CML-TTS: A Multilingual Dataset for Speech Synthesis

uroman-python

Python wrapper around uroman tokenizer

miipher

Unofficial implementation of miipher

vits2_pytorch

unofficial vits2-TTS implementation in pytorch

SpeechMOS

Easy-to-Use Speech MOS predictors

codellama

Inference code for CodeLlama models

randomized_positional_encodings

Randomized Positional Encodings Boost Length Generalization of Transformers

descript-audio-codec

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

Speech-Prompts-Adapters

This Repository surveys the paper focusing on Prompting and Adapters for Speech Processing.

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

zm-text-tts

[IJCAI'23] Learning to Speak from Text for Low-Resource TTS