🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A high-throughput and memory-efficient inference and serving engine for LLMs

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

Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Andr…

📣 商用级开源语音自动识别程序库，开箱即用，全平台支持，中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide a set of easier APIs to call ASR models.

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

The Noise Contrastive Estimation for softmax output written in Pytorch

Data augmentation for NLP, presented at EMNLP 2019

One has no future if one couldn't teach themself.

[ICLR'19] Trellis Networks for Sequence Modeling

Sequence modeling benchmarks and temporal convolutional networks

A clone of Darts (Double-ARray Trie System)

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。