A simple, performant re-implementation of AutoVC

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

A PyTorch-based Speech Toolkit

PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.

PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques …

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer

Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

CMU multilingual speech repository

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Graph4nlp is the library for the easy use of Graph Neural Networks for NLP. Welcome to visit our DLG4NLP website (https://dlg4nlp.github.io/index.html) for various learning resources!

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

g2pC: A Context-aware Grapheme-to-Phoneme Conversion module for Chinese

A set of tools to use in Microsoft Azure Form Recognizer and OCR services.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

LaNMT: Latent-variable Non-autoregressive Neural Machine Translation with Deterministic Inference

End-to-End Speech Processing Toolkit

JP puncuator

VS Code in the browser

Microsoft.Recognizers.Text provides recognition and resolution of numbers, units, date/time, etc. in multiple languages (ZH, EN, FR, ES, PT, DE, IT, TR, HI, NL. Partial support for JA, KO, AR, SV).…

A Python wrapper for Kaldi

A header-only C++ library for deep neural networks

Speech Recognition using DeepSpeech2.

汉字转拼音(pypinyin)