Rumeysa Keskin
Rumeysa Keskin
Speaker-Verification
Verifying the identity of a person from characteristics of the voice independent from language via NVIDIA NeMo models (ECAPA-TDNN, SpeakerNet, TitaNet-L).
Turkish-Text-to-Speech
Speech synthesis (TTS) in low-resource languages by training from scratch with Fastpitch and fine-tuning with HifiGan
Image-Caption-Generation
InceptionV3-Multi-layer GRU based automatic image captioning with Keras and TensorFlow frameworks
Turkish-Speech-to-Text
Fine-tuning for automatic speech recognition on low-resource languages with character-based CTC model
EuroSat-Satellite-CNN-and-ResNet
Classifying custom image datasets by creating Convolutional Neural Networks and Residual Networks from scratch with PyTorch