tatsu1020 Goto Github PK

audio_feature_extraction

This repository contains implementations of audio feature extractions inlcluding spectrogram, mel-scale spectrogram, mel-frequency cepstrum coefficients (MFCC) with numpy.

deepfilternet

Noise supression using deep filtering

fastspeech2

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

megatron-deepspeed-mistral

Ongoing research training transformer language models at scale, including: BERT & GPT-2

mnist-fashion

This repo contains implementations of logistic regression, multi-layer perceptron, and convolutional neural networks for MNIST fashion dataset.

nobelium

A static blog build on top of Notion and NextJS, deployed on Vercel.

self-supervised-dutch-dysarthria-asr

This is a repository presenting the outcome of my thesis for MSc. Voice Technology at the University of Groningen. The research developed the Dutch dysarthric speech recognition with self-supervised learning (SSL) models, wav2vec 2.0 and XLSR-53. The repo contains the fine-tuned models and the evaluation dataset.

tacotron-2

DeepMind's Tacotron-2 Tensorflow implementation

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

ucllm_nedo_prod_reproduce