zyser's repositories
MB-iSTFT-VITS2
Application of MB-iSTFT-VITS components to vits2_pytorch
Codec-SUPERB
Audio Codec Speech processing Universal PERformance Benchmark
conditional-flow-matching
TorchCFM: a Conditional Flow Matching library
DDSP-SVC
End-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)
Diff-HierVC
Official Pytorch Implementation of "Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation"
edm2
Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)
FAcodec
Training code for FAcodec presented in NaturalSpeech3
gemma_pytorch
The official PyTorch implementation of Google's Gemma models
Grad-TTS
Implementation of the 'Grad-TTS' with Multilingual Cleaners
LLaMA-Factory
Unify Efficient Fine-tuning of 100+ LLMs
llama.cpp
Port of Facebook's LLaMA model in C/C++
llama2.c
Inference Llama 2 in one file of pure C
megatts2
Unoffical implementation of Megatts2
ml-4m
4M: Massively Multimodal Masked Modeling
NeMo-text-processing
NeMo text processing for ASR and TTS
OpenPhonemizer
Permissively licensed, open sourced, local IPA Phonemizer (G2P) powered by deep learning.
Phi-3CookBook
This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks.
PitchSqueezer
A robust pitch tracker using synchro-squeezed fft and frequency domain autocorrelation
stable-speech
Reproduction of Stability AI's Text-to-Speech model.
supervoice-gpt
GPT-style network for phonemization with durations of text
tts-arabic-pytorch
TTS models for Arabic (Tacotron2, FastPitch)
utmos
A toolkit to calculate speech audio quality. Not affiliated with the original authors
vitsgpt-vits
the code for vits in the vitsGPT project
VoRAS_VC
VoRAS: Vocos Retrieval and self-Augmentation for Speech
WavCraft
Official repo for WavCraft, an AI agent for audio creation and editing