Musicgen Songstarter V0.2

🚀 Model Card for musicgen-songstarter-v0.2

This model, fine - tuned from musicgen - stereo - melody - large, generates stereo audio at 32khz and is designed to offer useful song ideas for music producers.

musicgen - songstarter - v0.2 is a musicgen - stereo - melody - large fine - tuned on a dataset of melody loops from my Splice sample library. It's intended to be used to generate song ideas that are useful for music producers. It generates stereo audio in 32khz.

👀 Update: I wrote a blogpost detailing how and why I trained this model, including training details, the dataset, Weights and Biases logs, etc.

Compared to musicgen - songstarter - v0.1, this new version:

• was trained on 3x more unique, manually - curated samples that I painstakingly purchased on Splice
• Is twice the size, bumped up from size medium ➡️ large transformer LM

If you find this model interesting, please consider:

• following me on GitHub
• following me on Twitter

🚀 Quick Start

📦 Installation

Install audiocraft:

pip install -U git+https://github.com/facebookresearch/audiocraft#egg=audiocraft

💻 Usage Examples

Basic Usage

Then, you should be able to load this model just like any other musicgen checkpoint here on the Hub:

import torchaudio
from audiocraft.models import MusicGen
from audiocraft.data.audio import audio_write

model = MusicGen.get_pretrained('nateraw/musicgen-songstarter-v0.2')
model.set_generation_params(duration=8)  # generate 8 seconds.
wav = model.generate_unconditional(4)    # generates 4 unconditional audio samples
descriptions = ['acoustic, guitar, melody, trap, d minor, 90 bpm'] * 3
wav = model.generate(descriptions)  # generates 3 samples.

melody, sr = torchaudio.load('./assets/bach.mp3')
# generates using the melody from the given audio and the provided descriptions.
wav = model.generate_with_chroma(descriptions, melody[None].expand(3, -1, -1), sr)

for idx, one_wav in enumerate(wav):
    # Will save under {idx}.wav, with loudness normalization at -14 db LUFS.
    audio_write(f'{idx}', one_wav.cpu(), model.sample_rate, strategy="loudness", loudness_compressor=True)

Prompt Format

Follow the following prompt format:

{tag_1}, {tag_2}, ..., {tag_n}, {key}, {bpm} bpm

For example:

hip hop, soul, piano, chords, jazz, neo jazz, G# minor, 140 bpm

For some example tags, [see the prompt format section of musicgen - songstarter - v0.1's readme](https://huggingface.co/nateraw/musicgen-songstarter-v0.1#prompt - format). The tags there are for the smaller v1 dataset, but should give you an idea of what the model saw.

Samples

🔧 Technical Details

General Information

For more verbose details, you can check out the blogpost.

Training Information

📄 License

The model is under the cc - by - nc - 4.0 license.

Acknowledgements

This work would not have been possible without:

• Lambda Labs, for subsidizing larger training runs by providing some compute credits
• Replicate, for early development compute resources

Thank you ❤️