Melanie Martinez

🚀 HuggingArtists Model: Melanie Martinez

This is a model created with huggingartists. It can generate lyrics in the style of Melanie Martinez. You can also create your own bot based on your favorite artist using the demo.

🚀 Quick Start

You can use this model directly with a pipeline for text generation:

from transformers import pipeline
generator = pipeline('text-generation',
                     model='huggingartists/melanie-martinez')
generator("I am", num_return_sequences=5)

Or with Transformers library:

from transformers import AutoTokenizer, AutoModelWithLMHead
  
tokenizer = AutoTokenizer.from_pretrained("huggingartists/melanie-martinez")

model = AutoModelWithLMHead.from_pretrained("huggingartists/melanie-martinez")

✨ Features

• Generate lyrics in the style of Melanie Martinez.
• Based on a pre - trained GPT - 2 model, fine - tuned on Melanie Martinez's lyrics.

📦 Installation

There is no specific installation steps provided in the original README. However, to use the model, you need to have the transformers and datasets libraries installed. You can install them using pip:

pip install transformers datasets

📚 Documentation

How does it work?

To understand how the model was developed, check the W&B report.

Training data

The model was trained on lyrics from Melanie Martinez. Dataset is available here. And can be used with:

from datasets import load_dataset

dataset = load_dataset("huggingartists/melanie-martinez")

Explore the data, which is tracked with W&B artifacts at every step of the pipeline.

Training procedure

The model is based on a pre-trained GPT-2 which is fine-tuned on Melanie Martinez's lyrics. Hyperparameters and metrics are recorded in the W&B training run for full transparency and reproducibility. At the end of training, the final model is logged and versioned.

Limitations and bias

The model suffers from the same limitations and bias as GPT-2. In addition, the data present in the user's tweets further affects the text generated by the model.

🔧 Technical Details

The model uses a pre-trained GPT - 2 architecture and fine - tunes it on Melanie Martinez's lyrics dataset. The training process is tracked using Weights & Biases (W&B) to record hyperparameters and metrics for transparency and reproducibility.

📄 About

Built by Aleksey Korshuk

For more details, visit the project repository.

📦 Information Table