ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

A lightweight network for body/hand action recognition

PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

A fully working pytorch implementation of NaturalSpeech (Tan et al., 2022)

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

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]