Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

zero-shot voice conversion & singing voice conversion with in context learning

An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement

Easily train a good VC model with voice data <= 10 mins!

XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)

in preparation...

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

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

Examples and recipes for Llama 2 model

End-to-End Speech Processing Toolkit

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Inference code for LLaMA models

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…

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

An unofficial PyTorch implementation of the audio LM VALL-E