1-day current streak·14-day longest streak
Nguyễn Đình Thuần Digital Craftsman (ML Engineer / Backend Developer / Audio Alchemist) --- About Me Research & Development Focus Text-to-Speech Models Trained | Model | Status | |:------|:------:| |…
Nguyễn Đình Thuần

Digital Craftsman (ML Engineer / Backend Developer / Audio Alchemist)




---
About Me
python
class ThuanNguyen:
def __init__(self):
self.name = "Nguyễn Đình Thuần"
self.role = "Machine Learning Engineer"
self.location = "Ho Chi Minh City, Vietnam 🇻🇳"
self.education = "B.Eng Electronics & Telecommunications @ Ton Duc Thang University"
def current_focus(self):
return [
" Vietnamese Speech AI (TTS/STT)",
" NLP & Large Language Models",
" Real-time AI Systems",
" MLOps & Production Deployment"
]
def philosophy(self):
return "Bridging the gap between research papers and production systems"
Research & Development Focus
Text-to-Speech Models Trained
| Model | Status |
|:------|:------:|
| VibeVoice TTS | ✅ |
| ZipVoice TTS | ✅ |
| NeuTTS Air | ✅ |
| Chatterbox TTS | ✅ |
| Piper TTS | ✅ |
| Orpheus TTS | ✅ |
| VITS TTS | ✅ |
| F5 TTS | ✅ |
| Stylish TTS | ✅ |
| Index TTS | ✅ |
| VoxCPM TTS | ✅ |
| StyleTTS 2 Lite | ✅ |
| Spark TTS | ✅ |
| XTTS-V2 | ✅ |
| Mira-TTS | ✅ |
Speech-to-Text Models Trained
| Model | Status |
|:------|:------:|
| Wav2Vec STT | ✅ |
| Conformer STT | ✅ |
| Zipformer STT | ✅ |
| Whisper STT | ✅ |
Model Training Stats
┌─────────────────────────────┐
│ TTS Models Trained: 15 │
│ STT Models Trained: 4 │
│ Primary Language: 🇻🇳 │
└─────────────────────────────┘
---
Experience Timeline
mermaid
gantt
title Career Journey
dateFormat YYYY-MM
section TEL4VN
ML Engineer - Speech & NLP Systems :2024-03, 2025-09
section ARAR
AI Engineer - NLP & Chatbot :2025-09, 2026-01
TEL4VN – PITEL
Machine Learning Engineer · *Mar 2024 – Aug 2025*- Developed real-time Vietnamese speech AI and NLP systems
- Built and deployed production-grade speech processing pipelines
- Worked with FastAPI, Docker, and GPU/CUDA infrastructure
ARAR
AI Engineer · *Sep 2024 – Present*- Built SQL chatbots and Retrieval-Augmented Generation (RAG) systems
- Developed NLP-based solutions for real-world applications
Tech Arsenal
Core Stack
!Python !PyTorch !TensorFlow !FastAPIML & NLP
!HuggingFace !Transformers !scikit-learnInfrastructure
!Docker !CUDA !Linux !Git---
GitHub Analytics
Quick Stats
!Total Stars !Followers !Profile ViewsLet's Connect!
| Platform | Contact |
|:--------:|:--------|
| Email | [[email protected]](mailto:[email protected]) |
| Phone | 0347 505 920 |
| LinkedIn | iamdinhthuan |
| GitHub | iamdinhthuan |
Thanks for visiting!
-
viterbox-tts
No description.
Python ★ 117 6mo agoExplain → -
index-tts-finetune-vietnamese
No description.
Python ★ 45 7mo agoExplain → -
neutts-air-fintune ⑂
On-device TTS model by Neuphonic
Python ★ 35 6mo agoExplain → -
Vira-tts
No description.
Python ★ 25 4mo agoExplain → -
ViZipvoice
No description.
Python ★ 19 4d agoExplain → -
Traffic-sign-VietNam-recognition
No description.
Jupyter Notebook ★ 7 2y agoExplain → -
Kokoro-Vietnamese
No description.
Python ★ 4 7h agoExplain → -
orpheus-finetune-vi
No description.
Python ★ 4 9mo agoExplain → -
finetune_rnnt_whisper_vietnamese
No description.
Python ★ 4 1y agoExplain → -
vibeVoice-finetuning-vietnamese
No description.
Python ★ 4 9mo agoExplain → -
stylish-dataset ⑂
Tools for dataset creation and curation for use with stylish-tts.
Python ★ 4 1y agoExplain → -
fintune_wav2vec_speech_to_text_vietnamese
No description.
Python ★ 4 1y agoExplain → -
codex-skill
No description.
Shell ★ 3 22d agoExplain → -
EfficiencyConformer-ctc-vietnamese
High-performance Vietnamese speech recognition system using Conformer encoder with CTC decoder architecture.
Python ★ 3 1y agoExplain → -
VoxCPM-vi ⑂
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
Python ★ 3 5mo agoExplain → -
MaxMViT-MLP-SER
No description.
Python ★ 3 5mo agoExplain → -
stylish-tts
No description.
Python ★ 3 1y agoExplain → -
calendar_app
No description.
TypeScript ★ 3 8mo agoExplain → -
chatterbox-finetune-vi
No description.
Python ★ 3 7mo agoExplain → -
WaveWord_Detection
No description.
Python ★ 3 1y agoExplain → -
iamdinhthuan
No description.
★ 2 1mo agoExplain → -
zipformer-asr-api ⑂
REST-API implementation of ZipFormer for automatic speech recognition (ASR) built in Python and Docker.
Python ★ 1 1mo agoExplain → -
soprano ⑂
Soprano: Instant, Ultra-Realistic Text-to-Speech
Python ★ 1 5mo agoExplain → -
vietnamese-spell-correction
No description.
Python ★ 1 7mo agoExplain → -
g2p_vi
No description.
Python ★ 1 1y agoExplain → -
rustchain-bounties ⑂
Earn RTC crypto by contributing to the RustChain ecosystem. Bounties from 1-150 RTC. Star, code, write tutorials, find bugs.
★ 0 1mo agoExplain → -
Rustchain ⑂
DePIN for Vintage Hardware — Proof-of-Antiquity blockchain where old machines outmine new ones. AI-powered hardware fingerprinting, 15+ CPU architectures, Solana bridge (wRTC). $0 VC.
★ 0 1mo agoExplain → -
Flowise ⑂
Build AI Agents, Visually
TypeScript ★ 0 1mo agoExplain → -
OmniVoice ⑂
High-Quality Voice Cloning TTS for 600+ Languages
★ 0 2mo agoExplain → -
vietnormalizer ⑂
No description.
Python ★ 0 2mo agoExplain → -
CemoBAM ⑂
[APNOMS'25] - "CemoBAM: Advancing Multimodal Emotion Recognition through Heterogeneous Graph Networks and Cross-Modal Attention Mechanisms" by Nhut Minh Nguyen, Thu Thuy Le, Trung Thanh Nguyen, Tai Duc Phan, Anh Khoa Tran, and Duc Ngoc Minh Dang
★ 0 7mo agoExplain →
No repos match these filters.