Next-Token Prediction is All You Need

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

An Open-Sourced LLM-empowered Foundation TTS System

[ICASSP 2024] This is the official code for "VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching"

[Official Implementation] Acoustic Autoregressive Modeling 🔥

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Ultra-low bitrate neural audio codec (0.31~1.40 kbps) with a better semantic in the latent space.

LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning

Pytorch implementation of SoundCTM

PyTorch Implementation of AudioLCM (ACM-MM'24): a efficient and high-quality text-to-audio generation with latent consistency model.

a text-conditional diffusion probabilistic model capable of generating high fidelity audio.

Open-Sora: Democratizing Efficient Video Production for All

*BeaqleJS* provides a framework to create browser based listening tests and is purely based on open web standards like HTML5 and Javascript.

A generative speech model for daily dialogue.

Speech, Language, Audio, Music Processing with Large Language Model

Lumina-T2X is a unified framework for Text to Any Modality Generation

Word alignments generated by the Montreal Forced Aligner for the Librispeech dataset

Lumina-T2X is a unified framework for Text to Any Modality Generation

Official repo for WavCraft, an AI agent for audio creation and editing

PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model

This reporsitory contains metadata of WavCaps dataset and codes for downstream tasks.

An Open Source text-to-speech system built by inverting Whisper.

A unified dataset of multilingual emotional human utterances

Unofficial implementation of NVIDIA P-Flow TTS paper

A family of diffusion models for text-to-audio generation.

🔊 Repository for our NAACL-HLT 2019 paper: AudioCaps

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

Inference and training library for high-quality TTS models.