Intern
ANR Software Private
06.2024 - 07.2024
- Developed and trained a Speech-to-Text machine learning model, enhancing its accuracy and efficiency in real-time transcription.
- Preprocessed large audio datasets by implementing noise reduction, feature extraction, and normalization techniques, optimizing deep learning algorithms to improve model accuracy and reduce processing time.
- Collaborated with developers and data scientists to fine-tune the model, integrate NLP techniques for better contextual understanding, and conducted extensive testing to ensure reliability across different accents and audio conditions.
