SmileGoat

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

tiny-dnn

header only, dependency-free deep learning framework in C++14

SoundStorm

The reproduced code for Google's SoundStorm

paper-reading

深度学习经典、新论文逐段精读

sherpa-ncnn

Real-time speech recognition using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Raspberry Pi, VisionFive2, LicheePi4A etc.

sherpa-onnx

Speech-to-text, text-to-speech, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift, Dart, JavaScript, Flutter

icefall

lingvo

Lingvo

so-vits-svc

SoftVC VITS Singing Voice Conversion

Search-for-Typos

Search for typos in code or text, automatically fix some typos. 查找文本或代码中的拼写错误/打字错误，自动修改部分 typos。【The typos lib is extensible and customizable, and supports regular expressions. typos 库可扩展和定制，支持正则表达式】

SpeechRecognizer

sherpa

Speech-to-text server framework with next-gen Kaldi

kaldi-native-fbank

Kaldi-compatible online fbank extractor without external dependencies

TTSAndroid

TTS Android demo of PaddleSpeech, merged into https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/demos

vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

PaddleSlim

PaddleSlim is an open-source library for deep model compression and architecture search.

paddlespeech_tts_cpp

PaddleSpeech TTS cpp

rasr

The RWTH ASR Toolkit.

TensorflowASR

一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目，CPU上的实时率(RTF)小于0.1

ASR-decoder

it's ASR decoder and make graph project

PaddleHub

Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)

paddle_build

FastDeploy

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support.

Paddle3D

A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.

PaddleRS

Awesome Remote Sensing Toolkit based on PaddlePaddle.

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

pybind11

Seamless operability between C++11 and Python

PaddleSpeech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

ivy

Convert Machine Learning Code Between Frameworks

SymphonyNet

Symphony Generation with Permutation Invariant Language Model