dqqcasia's starred repositories

youtube-dl

Command-line program to download videos from YouTube.com and other video sites

Language:PythonLicense:UnlicenseStargazers:130215Issues:2200Issues:26562

langchain

🦜🔗 Build context-aware reasoning applications

Language:Jupyter NotebookLicense:MITStargazers:89710Issues:675Issues:7257

DragGAN

Official Code for DragGAN (SIGGRAPH 2023)

Language:PythonLicense:NOASSERTIONStargazers:35601Issues:1003Issues:187

whisper.cpp

Port of OpenAI's Whisper model in C/C++

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Language:PythonLicense:MITStargazers:20293Issues:197Issues:367

codellama

Inference code for CodeLlama models

Language:PythonLicense:NOASSERTIONStargazers:15637Issues:177Issues:192

Awesome-Chinese-LLM

整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。

Llama-Chinese

Llama中文社区,Llama3在线体验和微调模型已开放,实时汇总最新Llama3学习资料,已将所有代码更新适配Llama3,构建最好的中文Llama大模型,完全开源可商用

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:10755Issues:88Issues:297

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:10586Issues:141Issues:338

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Language:PythonLicense:Apache-2.0Stargazers:8150Issues:73Issues:398

vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Language:PythonLicense:MITStargazers:6529Issues:56Issues:199

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Language:PythonLicense:MITStargazers:5951Issues:36Issues:954

Baichuan-7B

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

Language:PythonLicense:Apache-2.0Stargazers:5662Issues:66Issues:127

whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Language:PythonLicense:AGPL-3.0Stargazers:1740Issues:26Issues:133

whisper_streaming

Whisper realtime streaming for long speech-to-text transcription and translation

Language:PythonLicense:MITStargazers:1515Issues:33Issues:81

deep_learning_curriculum

Language model alignment-focused deep learning curriculum

SDEdit

PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations

Language:PythonLicense:MITStargazers:946Issues:23Issues:28

llm-hallucination-survey

Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

bigcode-evaluation-harness

A framework for the evaluation of autoregressive code generation language models.

Language:PythonLicense:Apache-2.0Stargazers:718Issues:12Issues:129

fairseq2

FAIR Sequence Modeling Toolkit 2

Language:PythonLicense:MITStargazers:634Issues:19Issues:93

NISQA

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

Language:PythonLicense:MITStargazers:629Issues:24Issues:46

MEGABYTE-pytorch

Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch

Language:PythonLicense:MITStargazers:604Issues:11Issues:13

jiwer

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

Language:PythonLicense:Apache-2.0Stargazers:576Issues:15Issues:44

Speech-Resources

语音方向实验室/公司/资源/实习等,欢迎推荐或自荐

BIG-Bench-Hard

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

sft_datasets

开源SFT数据集整理,随时补充

FunCodec

FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.

Language:PythonLicense:MITStargazers:319Issues:16Issues:48