Musiclang 4k

🚀 MusicLang Predict model

MusicLang Predict is a generative AI model designed to create original MIDI soundtracks, offering diverse usage scenarios for music creation.

✨ Features

• Predict a new song from scratch (a fixed number of bars).
• Continue a song from a prompt.
• Predict a new song from a template.
• Continue a song from a prompt and a template.
• Provide an interface to create a template from an existing MIDI file.

📦 Installation

Install the musiclang-predict package with pip:

pip install musiclang-predict

💻 Usage Examples

Basic Usage

from musiclang_predict import predict, MusicLangTokenizer
from transformers import GPT2LMHeadModel

# Load model and tokenizer
model = GPT2LMHeadModel.from_pretrained('musiclang/musiclang-4k')
tokenizer = MusicLangTokenizer('musiclang/musiclang-4k')
soundtrack = predict(model, tokenizer, chord_duration=4, nb_chords=2)
soundtrack.to_midi('song.mid', tempo=120, time_signature=(4, 4))

Advanced Usage

Use an existing MIDI song as a song structure template

from musiclang_predict import midi_file_to_template, predict_with_template, MusicLangTokenizer
from transformers import GPT2LMHeadModel

# Load model and tokenizer
model = GPT2LMHeadModel.from_pretrained('musiclang/musiclang-4k')
tokenizer = MusicLangTokenizer('musiclang/musiclang-4k')

template = midi_file_to_template('my_song.mid')
soundtrack = predict_with_template(template, model, tokenizer)
soundtrack.to_midi('song.mid', tempo=template['tempo'], time_signature=template['time_signature'])

Use a prompt and a template to create a song

from musiclang_predict import midi_file_to_template, predict_with_template, MusicLangTokenizer
from transformers import GPT2LMHeadModel
from musiclang import Score

# Load model and tokenizer
model = GPT2LMHeadModel.from_pretrained('musiclang/musiclang-4k')
tokenizer = MusicLangTokenizer('musiclang/musiclang-4k')
template = midi_file_to_template('my_song.mid')
# Take the first chord of the template as a prompt
prompt = Score.from_midi('my_prompt.mid', chord_range=(0, 4))
soundtrack = predict_with_template(template, model, tokenizer, 
                                   prompt=prompt,  # Prompt the model with a musiclang score
                                   prompt_included_in_template=True  # To say the prompt score is included in the template
                                   )
soundtrack.to_midi('song.mid', tempo=template['tempo'], time_signature=template['time_signature'])

See MusicLang templates for a full description of the template format.

📄 License

The MusicLang predict package (this package) and its associated models are licensed under the GPL - 3.0 License. The MusicLang base language (musiclang package) is licensed under the BSD 3 - Clause License.

📞 Contact Us

If you want to help shape the future of open source music generation, please contact us.