# End-to-end model

YOLOv10 is a real-time end-to-end object detection model proposed by Tsinghua University, with significant improvements in both speed and accuracy.

Paraformer is an innovative non-autoregressive end-to-end speech recognition model with significant advantages over traditional autoregressive models. It can generate entire target sentences in parallel, making it particularly suitable for GPU-accelerated parallel inference.

This is a Japanese automatic speech recognition (ASR) model trained using the ESPnet framework, utilizing the CSJ dataset and based on the Transformer architecture.

Transformer-based end-to-end multilingual speech translation model supporting English-to-multiple language speech translation

Tacotron2 text-to-speech model trained on ESPnet framework using LJSpeech dataset

A pre-trained model for detecting overlapped speech in audio, capable of identifying time segments where two or more speakers are active simultaneously.

Speaker segmentation model based on pyannote.audio, used to detect speaker changes and speech activity in audio

A Transformer-based end-to-end speech translation model, specifically designed for French-to-English speech translation tasks