Role: Student AI Researcher at Skinopathy
- Fine-tuned the OpenAI Whisper Large-v3 Turbo model to improve audio recognition of dermatology terminology using QLoRA.
- Achieved a 33% reduction in Word Error Rate (WER), improving accuracy from 14.5% to 9.5%.
- Cleaned and processed over 100 dermatology documents, which were used to synthesize more than 780 English audio samples with varied accents and genders using the Google Text-to-Speech API for training purposes.
Skills: Artificial Intelligence (AI) · speech-to-text · Fine Tuning · QLoRA · Natural Language Processing (NLP) · Text-to-Speech Synthesis · Data Processing · Data Cleaning · OpenAI Whisper · Audio Recognition · Project Management
