tuanio

noisy-student-training-asr

Pytorch implementation of Noisy Student Training for Automatic Speech Recognition and Automatic Pronunciation Error Detection problem

image2latex

Image to Latex using Encoder-Decoder architecture

create-visa-account

RFM-model-collaborative-filtering

Collaborative Filtering with Clustering customer, RFM model

tuanio.github.io

This is an academic blog

whisper-ctc

Whisper Encoder (extracted from pretrained) with a Linear on top and solve using CTC criterion

custom-chatbot-ui

ling-wav2vec2

Official implementation of LingWav2Vec2: Linguistic-augmented Wav2Vec2 for Mispronunciation Detection

single-or-multiple-speakers-detection

tuanio

audio-llm-prefix-tuning

cs224n

Learning resources of cs224n Stanford study by myself.

Discriminator-Constrained-Optimal-Transport-Network

gradio-chat-rag

setup-vicuna

tiepvupsu.github.io

My Machine Learning blog

TransRepairImplementation

Tools implemented according to the paper 'automatic testing and improvement of machine translation'

diffusion-work

EfficientConformer-Edit

[ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

gan_workspace_for_speech

GANSpeechAugment

hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

MaskCycleGAN-VC

Fork from https://github.com/GANtastic3/MaskCycleGAN-VC

MaskCycleGAN-VC-pytorch-lightning

melgan

Fork from melgan-neurips

simulate-noisy-speech-from-clean

SpeechAttentionGAN

SpeechUVCGANv2

Rethinking CycleGAN: Improving Quality of GANs for Unpaired Image-to-Image Translation