tts-nlp

sofgan

[TOG 2022] SofGAN: A Portrait Image Generator with Dynamic Styling

TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

EGVSR

Efficient & Generic Video Super-Resolution

open_stt

Russian open STT dataset

ppgs_extractor_10ms_sch_lh_aishell1

ppgs_extractor_10ms_sch_lh_librispeech

sofgan

[TOG 2021] SofGAN: A Portrait Image Generator with Dynamic Styling

TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, Korean, Chinese, German and Easy to adapt for other languages)

vadnet

Real-time Voice Activity Detection in Noisy Eniviroments using Deep Neural Networks

tts-nlp/chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M

tts-nlp/EGVSR

Efficient & Generic Video Super-Resolution

tts-nlp/open_stt

Russian open STT dataset

tts-nlp/ppgs_extractor_10ms_sch_lh_aishell1

tts-nlp/ppgs_extractor_10ms_sch_lh_librispeech

tts-nlp/sofgan

[TOG 2021] SofGAN: A Portrait Image Generator with Dynamic Styling

tts-nlp/TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, Korean, Chinese, German and Easy to adapt for other languages)

tts-nlp/vadnet

Real-time Voice Activity Detection in Noisy Eniviroments using Deep Neural Networks