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

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

Inference code for LLaMA models

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deplo…

llm deploy project based mnn.

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等

PyTorch implementation of the InfoNCE loss for self-supervised learning.

speech enhancement\speech seperation\sound source localization

A enterprise-grade Voice Activity Detector from modelscope and funasr.

达摩fsmn vad c++推理服务

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

语音识别模型pytorch转ONNX转MNN，C++实现部署

KD for wenet

A pytorch wrapper for LF-MMI training and parallel training in Kaldi

📚 Modern C++ Tutorial: C++11/14/17/20 On the Fly | https://changkun.de/modern-cpp/

list of efficient attention modules

Production First and Production Ready End-to-End Speech Recognition Toolkit

kaldi-asr/kaldi is the official location of the Kaldi project.

Towards hot directions in industrial speech recognition

Python开源项目之「自学编程之路」，学习指南+技术干货+大厂面经+资源分享

Kaldi model converter to ONNX

手把手撕LeetCode题目，扒各种算法套路的裤子。English version supported! Crack LeetCode, not only how, but also why.

A Python wrapper for Kaldi

tf 2.0 implementation of Listen, attend and spell

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.