SoftVC VITS Singing Voice Conversion

[ACL 2025 Oral] Language-Codec: Reducing the Gaps Between Discrete Codec Representation and Speech Language Models

Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

Vector (and Scalar) Quantization, in Pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

speech self-supervised representations

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

Recurrent neural network for audio noise reduction

Simple and Efficient Tensorflow implementations of NER models with tf.estimator and tf.data

Facebook AI Research's Automatic Speech Recognition Toolkit

End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)

End-to-end ASR/LM implementation with PyTorch

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…

Pytorch Bindings for warp-ctc

Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.

A PyTorch Implementation of End-to-End Models for Speech-to-Text

The RWTH extensible training framework for universal recurrent neural networks

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow

Speech Recognition using DeepSpeech2.

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

Reference implementations of MLPerf® training benchmarks

Models and examples built with TensorFlow

End-to-End Speech Processing Toolkit