NoneWait

LlamaVoice

LlamaVoice is a llama-based large voice generation model, providing inference and training ability.

Recorder

html5 js 录音 mp3 wav ogg webm amr g711a g711u 格式，支持pc和Android、iOS部分浏览器、Hybrid App（提供Android iOS App源码）、微信，提供ASR语音识别转文字 H5版语音通话聊天示例 DTMF编码解码

kaldiio

A pure python module for reading and writing kaldi ark files

HierSpeechpp

The official implementation of HierSpeech++

metavoice-src

Foundational model for human-like, expressive TTS

vocos

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

ChatTTS

A generative speech model for daily dialogue.

FSQ

Keras implement of Finite Scalar Quantization

SpeechGPT

SpeechGPT Series: Speech Large Language Models

Online-RLHF

A recipe for online RLHF.

UMOE-Scaling-Unified-Multimodal-LLMs

The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"

AnyGPT

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Ditto

A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".

long-context-attention

Sequence Parallel Attention for Long Context LLM Model Training and Inference

LWM

ring-flash-attention

Ring attention implementation with flash attention

langgraph

Build resilient language agents as graphs.

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

nbdev_template

Template for nbdev projects

LongAlign

LongAlign: A Recipe for Long Context Alignment Encompassing Data, Training, and Evaluation

torchtune

A Native-PyTorch Library for LLM Fine-tuning

Skywork

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Awesome-RAG

NeMo-Aligner

Scalable toolkit for efficient model alignment

CRUD_RAG

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.