huggingartists lyrics lm-head causal-lm

<div class="inline-flex flex-col" style="line-height: 1.5;"> <div class="flex"> <div style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://images.genius.com/1aa6c04aad3652556046bb3aabe96498.900x900x1.jpg')"> </div> </div> <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div> <div style="text-align: center; font-size: 16px; font-weight: 800">Billie Eilish</div> <a href="https://genius.com/artists/billie-eilish"> <div style="text-align: center; font-size: 14px;">@billie-eilish</div> </a> </div>

I was made with huggingartists.

Create your own bot based on your favorite artist with the demo!

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 Billie Eilish.

Dataset is available here. And can be used with:

from datasets import load_dataset

dataset = load_dataset("huggingartists/billie-eilish")

Or with Transformers library:

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

model = AutoModelWithLMHead.from_pretrained("huggingartists/billie-eilish")

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 Billie Eilish'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.

How to use

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

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

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.

About

Built by Aleksey Korshuk

Follow

For more details, visit the project repository.

GitHub stars