Pinned Repositories
2022-AdaIN-pytorch-hf_streamlit_space
Create a Huggingface space using streamlit for the project
2022-U-Net
fixing dependencies
actions_test
AVSpeechDownloader
Simple python script for downloading AVSpeech Dataset
custom_hf_trainer
A custom Huggingface trainer which supports logging auxiliary losses returned by your model
eval-wavs
iSeparate-SDX
iSeparate library for the SDX2023 challenge
istft-torch
Quick and naive translation of torch.istft() to python with option to skip NOLA check.
RNN-Handwriting-Generation-Pytorch
sequence generation using RNN using pytorch
stempeg
Python I/O for STEM audio files
naba89's Repositories
naba89/AVSpeechDownloader
Simple python script for downloading AVSpeech Dataset
naba89/iSeparate-SDX
iSeparate library for the SDX2023 challenge
naba89/RNN-Handwriting-Generation-Pytorch
sequence generation using RNN using pytorch
naba89/custom_hf_trainer
A custom Huggingface trainer which supports logging auxiliary losses returned by your model
naba89/eval-wavs
naba89/istft-torch
Quick and naive translation of torch.istft() to python with option to skip NOLA check.
naba89/2022-AdaIN-pytorch-hf_streamlit_space
Create a Huggingface space using streamlit for the project
naba89/2022-U-Net
fixing dependencies
naba89/actions_test
naba89/DDDM-VC
Official Pytorch Implementation for "DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion" (AAAI 2024)
naba89/deep-learning-project-template
Pytorch Lightning code guideline for conferences
naba89/media-comp-test-repo
Demo repository
naba89/P.808
This is an open-source implementation of the ITU P.808 standard for "Subjective evaluation of speech quality with a crowdsourcing approach" (see https://www.itu.int/rec/T-REC-P.808/en). It uses Amazon Mechanical Turk as the crowdsourcing platform. It includes implementations for Absolute Category Rating (ACR), Degradation Category Rating (DCR), and Comparison Category Rating (CCR).
naba89/stempeg
Python I/O for STEM audio files
naba89/VideoDenoising
A novel video denoising algorithm based on wavelet and walsh-hadamard transform
naba89/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"
naba89/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
naba89/flame_feature_extractor
naba89/HierSpeechpp
The official implementation of HierSpeech++
naba89/project-CURRENNT-scripts
This repository contains the scripts to use CURRENNT
naba89/pub-SiSEC2018
Paper for SiSEC 2018, published at LVA/ICA
naba89/PyTorch-Wavelet-Toolbox
Differentiable fast wavelet transforms in PyTorch with GPU support.
naba89/PyTorchWavelets
PyTorch implementation of the wavelet analysis from Torrence & Compo (1998)
naba89/sdx-submissions
Sound Demixing Challenge Submission Repo
naba89/srt-parse
Segments a .mp3 file into several smaller audio clips using an accompanying .srt closed captioning file.
naba89/ssqueezepy
Synchrosqueezing, wavelet transforms, and time-frequency analysis in Python
naba89/StableTTS
Next-generation TTS model using flow-matching and DiT, inspired by Stable Diffusion 3
naba89/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
naba89/tts-asr-eval-suite
A suite of various automatic evaluation metrics for TTS and VC
naba89/webMUSHRA
a MUSHRA compliant web audio API based experiment software