Pinned Loading

1. Extractive-question-answering-with-BERT-model-fine-tuned-on-the-SQuAD-dataset Extractive-question-answering-with-BERT-model-fine-tuned-on-the-SQuAD-dataset Public

   Finetuning a BERT model on the SQuAD dataset for the task of extractive question answering.

   Jupyter Notebook

2. Generate-Sketch-Drawings-with-Sketch-RNN-Variational-Autoencoder-Model Generate-Sketch-Drawings-with-Sketch-RNN-Variational-Autoencoder-Model Public

   Deep learning model that trains on a dataset of human-drawn sketches of a subject (e.g. bicycle, cat, etc.) and then generates new sketches of that subject.

   Python 1

3. Generate-Image-Caption-with-ResNet-Encoder-and-LSTM-Decoder Generate-Image-Caption-with-ResNet-Encoder-and-LSTM-Decoder Public

   Generate a sentence to describe an image, using ResNet encoder to extract image features and LSTM decoder to translate latent features into captions.

   Python 1

4. Automated-speech-recognition-on-a-new-language-by-finetuning-OpenAI-s-Whisper-model Automated-speech-recognition-on-a-new-language-by-finetuning-OpenAI-s-Whisper-model Public

   Fine-tuning OpenAI's Whisper model for automatic speech recognition on the Dhivehi language subset of the Common Voice 13 dataset

   Jupyter Notebook

5. Finetuning-pre-trained-DistilHuBERT-on-Music-Genre-Classfication Finetuning-pre-trained-DistilHuBERT-on-Music-Genre-Classfication Public

   Fine-tuning a pre-trained transformer model, DistilHuBERT, for music genre classification using the GTZAN dataset

   Jupyter Notebook

6. Finetuning-Swin-Transformer-for-multi-label-image-classification-on-Pascal-VOC-dataset Finetuning-Swin-Transformer-for-multi-label-image-classification-on-Pascal-VOC-dataset Public

   Fine-tuning a Swin Transformer model, a variant of Vision Transformer (ViT), for multi-label image classification on the Pascal VOC 2007 dataset

   Jupyter Notebook 1