Tuan-Vu Trinh

Diff-VC. Diffusion Model for Voice Conversion

yolo8-tracking-counting-speed_estimation. Tracking, counting and speed estimation using yolo8

handwritten-ocr. My personal implementation of SVTR model for handwritten OCR

KWS-BCResnet. Keyword Spotting using BCResNet and Arcface Loss

yolo-ncnn-cpp. everything to infer yolo with ncnn and cpp

tflite-yamnet-audio-classification. Yamnet model using tflite_model_maker with esc-50 dataset

ASR-based-KWS. QbE Keyword Spotting System based on ASR

bark-voice-cloning. Personal customization of some bark-voice-cloning implementations

Intent-Classification-and-Entity-Recognition. Intent classification and Entity Recoginition

Paraphrasing-Generation-T5. Training paraphasing using huggingface T5

OCR-Vietnamese-Text-Generator. A synthetic data generator for text recognition

NER-Flair-ONNX. This code is used to convert and infer Flair-ONNX model

voicemaker. Js Web for changing voice

Hubert-Training. Python

finetune-wav2vec2. Python

ConvNextV2-Classification. Python

Voice-Restoration. Speech Restoration

VITS2-TTS. Python

tflite-detection-yolov5. Java

Wav2Vec2-Serving-API. Python

pytorch-ml-utils. Some utility functions / decorators / modules related to Pytorch to help speed up coding

OneFormer3D. My personal customization of OneFormer3D

TiktokAutoUploader. Automatically Edits Videos and Uploads to Tiktok with CLI, Requests not Selenium.

fastapi-course. Python

buzz. Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

Document-Scanner. Simple Document Scanner using Semantic Segmentation

interview-question-data-science-.

Vietnamese_LLMs. Dự án bao gồm: 1. Xây dựng bộ dữ Instructions Vietnamese (chất lượng, nhiều, và đa dạng). 2.LLM Training, Finetuning, Evaluating & Testing trên Open-source mô hình ngôn ngữ: bloomz, OpenLLaMA, GPT-J pythia etc. 3. Ứng dụng và Giao diện Người dùng (UI)

MEDIAR. (NeurIPS 2022 CellSeg Challenge - 1st Winner) Open source code for "MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy"

jetson-voice. ASR/NLP/TTS deep learning inference library for NVIDIA Jetson using PyTorch and TensorRT

PaddleOCR-FastAPI. Python

playtorch-study. Study playtorch for mobile

wav2vec2-pretraining.

bytetrack-yolo-ncnn-cpp. C++

computer-vision-notebooks. Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM.

Image-Colorizer-Pix2Pix. Jupyter Notebook