zyser's repositories
golf
A DDSP-based neural vocoder.
annotated_deep_learning_paper_implementations
๐งโ๐ซ 59 Implementations/tutorials of deep learning papers with side-by-side notes ๐; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), ๐ฎ reinforcement learning (ppo, dqn), capsnet, distillation, ... ๐ง
AudioSep
Official implementation of "Separate Anything You Describe"
basic-pitch
A lightweight yet powerful audio-to-MIDI converter with pitch bend detection
BigVGAN-NVIDIA
Official implementation of BigVGAN in PyTorch
diffsptk
A differential version of SPTK
e2-tts-pytorch
Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch
GeneFace
Official Pytorch Implementation of GeneFace (ICLR 2023)
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
LAVISH
Vision Transformers are Parameter-Efficient Audio-Visual Learners
LlamaVoice
LlamaVoice is a llama-based large voice generation model, providing inference and training ability.
log-wmse-audio-quality
logWMSE, an audio quality metric with support for digital silence target. Useful for evaluating audio source separation systems, even when there are many audio tracks or stems.
MagVITS
VITS with phoneme-level prosody modeling based on MaskGIT
Matcha-TTS
๐ต Matcha-TTS: A fast TTS architecture with conditional flow matching
nano-llama31
nanoGPT style version of Llama 3.1
normalizing-flows
PyTorch implementation of normalizing flow models
PeriodWave
The official Implementation of PeriodWave and PeriodWave-Turbo
pipecat_framework-for-voice-and-multimodal-conversational-AI
Open Source framework for voice and multimodal conversational AI
podcast-summarizer
OpenAI Whisper + davinci for podcast summarization
polymath_music_separation
Convert any music library into a music production sample-library with ML
praat
Praat: Doing Phonetics By Computer
taylor-series-linear-attention
Explorations into the recently proposed Taylor Series Linear Attention
TriAAN-VC
TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion
voice_datasets
๐ A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).
xlstm_fork
Pytorch implementation of the xLSTM model by Beck et al. (2024)
yt-dlp
A youtube-dl fork with additional features and fixes