Skip to content
View gokhaneraslan's full-sized avatar

Block or report gokhaneraslan

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
gokhaneraslan/README.md

👋 Hi, I'm @gokhaneraslan

AI Developer | Machine Learning | Backend Engineer

I craft intelligent solutions using cutting-edge AI technologies and build robust systems to power them.

🧠 AI & Machine Learning Expertise

  • Computer Vision: Object detection, image segmentation, classification systems
  • Natural Language Processing: Sentiment analysis, text processing, information extraction
  • Large Language Models: Prompt engineering, fine-tuning, application development
  • Speech AI: TTS model development, voice cloning, speech synthesis fine-tuning
  • Deep Learning: Neural network architecture design, model optimization
  • Model Fine-Tuning: Parameter-efficient tuning, LoRA, QLoRA, transfer learning
  • AI Deployment: Model serving, scalable inference pipelines

👀 I'm passionate about

  • Building AI solutions for real-world problems
  • Developing intelligent systems with practical applications
  • Creating seamless integrations between AI and backend systems
  • Fine-tuning models for specialized domains and applications

🛠️ Technology Stack

  • AI/ML: Python, PyTorch, TensorFlow, Scikit-learn, Hugging Face, NVIDIA CUDA, GCP, AWS
  • Speech Models: Tacotron, WaveNet, VITS, FastSpeech, Piper
  • Backend: FastAPI, Express.js, Node.js
  • Frontend: React.js
  • Databases: MongoDB, MySQL, PostgreSQL
  • Infrastructure: Docker, Nginx, Redis, Jenkins
  • Security: OAuth2, JWT
  • Version Control: Git, GitHub

🚀 Featured AI Projects

  • Advanced Computer Vision System: Developed object segmentation architecture with robotic integration
  • LLM-Powered Sentiment Engine: Created multilayered analysis using text and image processing
  • Agricultural AI Solution: Built deep neural networks for detection, classification and sorting
  • Intelligent Web Scraping: Designed AI-driven automated data extraction and processing system
  • Custom TTS Solution: Fine-tuned speech synthesis models for natural-sounding voice applications

🌱 I'm currently learning ...

📫 Connect With Me


"At the intersection of artificial intelligence and software engineering, creating systems that understand and adapt."

Popular repositories Loading

  1. chatterbox-finetuning chatterbox-finetuning Public

    Fine-tune Chatterbox TTS model for custom voice cloning with multi-language support. Includes training pipeline, inference tools, and VAD-based audio processing.

    Python 19 7

  2. tts-dataset-generator tts-dataset-generator Public

    With this tool you can create custom TTS dataset from video or audio.

    Python 5 2

  3. tacotron2-tts-training tacotron2-tts-training Public

    Training Tacotron 2 Text-to-Speech (TTS)

    Python 3 1

  4. XTTS_V2-finetuning XTTS_V2-finetuning Public

    Training XTTS V2 and PEFT LORA Text-to-Speech (TTS)

    Python 3 1

  5. gokhaneraslan gokhaneraslan Public

    Config files for my GitHub profile.

  6. llm-dataset-generator llm-dataset-generator Public

    Custom dataset generator from text and pdf

    Python