Egor Letov

🚀 HuggingArtists Model - Egor Letov

This is a HuggingArtists model based on the lyrics of Egor Letov. It can generate text in the style of Egor Letov's lyrics, offering a unique experience for music and text generation enthusiasts.

I was made with huggingartists.

Create your own bot based on your favorite artist with 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/egor-letov')
generator("I am", num_return_sequences=5)

Or with Transformers library:

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

model = AutoModelWithLMHead.from_pretrained("huggingartists/egor-letov")

✨ Features

• Artist-Specific Text Generation: Generate text in the style of Egor Letov's lyrics.
• Easy to Use: Can be used directly with the Transformers pipeline or library.

📚 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 Egor Letov. Dataset is available here. And can be used with:

from datasets import load_dataset

dataset = load_dataset("huggingartists/egor-letov")

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 Egor Letov'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.

🔧 Technical Details

The model inherits from the pre-trained GPT - 2 architecture and is fine - tuned on Egor Letov's lyrics. This allows it to capture the unique language patterns and themes present in his music.

⚠️ 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

For more details, visit the project repository.