Pinned Repositories
alfred_workflows
Self-made Alfred workflows
code_examples
DNS_text
Transcripts of the DNS Challenge test sets
espnet
End-to-End Speech Processing Toolkit
MLnotes
Machine learning notes
PlayWithLinux
se-scaling
Model configurations for scaling SE models in the paper "Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement"
torch_conv
Purely PyTorch-based Conv1d and ConvTranspose1d implementations
torch_normalization
PyTorch-based implementations of different normalization layers (e.g., BatchNorm, GroupNorm, InstanceNorm, and LayerNorm)
torch_stft
PyTorch-based implementations of short-time Fourier transform
Emrys365's Repositories
Emrys365/se-scaling
Model configurations for scaling SE models in the paper "Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement"
Emrys365/torch_stft
PyTorch-based implementations of short-time Fourier transform
Emrys365/alfred_workflows
Self-made Alfred workflows
Emrys365/espnet
End-to-End Speech Processing Toolkit
Emrys365/DNS_text
Transcripts of the DNS Challenge test sets
Emrys365/PlayWithLinux
Emrys365/torch_conv
Purely PyTorch-based Conv1d and ConvTranspose1d implementations
Emrys365/torch_normalization
PyTorch-based implementations of different normalization layers (e.g., BatchNorm, GroupNorm, InstanceNorm, and LayerNorm)
Emrys365/code_examples
Emrys365/Emrys365.github.io
Emrys365/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Emrys365/RemarkPortable
Remark made simple and portable
Emrys365/Universal-SE-demo
Demo page of the ASRU 2023 paper "Toward Universal Speech Enhancement for Diverse Input Conditions"
Emrys365/webMUSHRA
a MUSHRA compliant web audio API based experiment software
Emrys365/espnet_model_zoo
ESPnet Model Zoo
Emrys365/graph_pit
Emrys365/hot-reload-c
Emrys365/mdn
Mixture density network implemented in PyTorch.
Emrys365/mir_eval
Evaluation functions for music/audio information retrieval/signal processing algorithms.
Emrys365/norbert
Painless Wiener filters for audio separation
Emrys365/opensmile-python
Python package for openSMILE
Emrys365/pdfplumber
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
Emrys365/PdfTool
pdf转word
Emrys365/personalVAD
An unofficial implementation of the Personal VAD speaker-conditioned voice activity detection method. Bachelor's thesis project.
Emrys365/pytorch_complex
A temporal module for PyTorch-ComplexTensor
Emrys365/RPNSD
PyTorch implementation of RPNSD
Emrys365/shinjiwlab.github.io
Emrys365/sms_wsj
SMS-WSJ: Spatialized Multi-Speaker Wall Street Journal database for multi-channel source separation and recognition
Emrys365/UniSpeech
UniSpeech - Large Scale Self-Supervised Learning for Speech
Emrys365/win-sf
Windows Sysprep Setup Helper