---
inference: false
tags:
- musicgen
license: cc-by-nc-4.0
---

# MusicGen - Small - 300M

MusicGen is a text-to-music model capable of genreating high-quality music samples conditioned on text descriptions or audio prompts.
It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. 
Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. 
By introducing a small delay between the codebooks, we show we can predict them in parallel, thus having only 50 auto-regressive steps per second of audio.

MusicGen was published in [Simple and Controllable Music Generation](https://arxiv.org/abs/2306.05284) by *Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, Alexandre Défossez*.

Four checkpoints are released:
- [**small** (this checkpoint)](https://huggingface.co/facebook/musicgen-small)
- [medium](https://huggingface.co/facebook/musicgen-medium)
- [large](https://huggingface.co/facebook/musicgen-large)
- [melody](https://huggingface.co/facebook/musicgen-melody)

## Example

Try out MusicGen yourself!

* Audiocraft Colab:

<a target="_blank" href="https://colab.research.google.com/drive/1fxGqfg96RBUvGxZ1XXN07s3DthrKUl4-?usp=sharing">
  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>

* Hugging Face Colab:

<a target="_blank" href="https://colab.research.google.com/github/sanchit-gandhi/notebooks/blob/main/MusicGen.ipynb"> 
  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> 
</a>

* Hugging Face Demo:

<a target="_blank" href="https://huggingface.co/spaces/facebook/MusicGen">
  <img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
</a>

## 🤗 Transformers Usage

You can run MusicGen locally with the 🤗 Transformers library from version 4.31.0 onwards.

1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) from main:

```
pip install git+https://github.com/huggingface/transformers.git
```

2. Run the following Python code to generate text-conditional audio samples:

```py
from transformers import AutoProcessor, MusicgenForConditionalGeneration


processor = AutoProcessor.from_pretrained("facebook/musicgen-small")
model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-small")

inputs = processor(
    text=["80s pop track with bassy drums and synth", "90s rock song with loud guitars and heavy drums"],
    padding=True,
    return_tensors="pt",
)

audio_values = model.generate(**inputs, max_new_tokens=256)
```

3. Listen to the audio samples either in an ipynb notebook:

```py
from IPython.display import Audio

sampling_rate = model.config.audio_encoder.sampling_rate
Audio(audio_values[0].numpy(), rate=sampling_rate)
```

Or save them as a `.wav` file using a third-party library, e.g. `scipy`:

```py
import scipy

sampling_rate = model.config.audio_encoder.sampling_rate
scipy.io.wavfile.write("musicgen_out.wav", rate=sampling_rate, data=audio_values[0, 0].numpy())
```

For more details on using the MusicGen model for inference using the 🤗 Transformers library, refer to the [MusicGen docs](https://huggingface.co/docs/transformers/model_doc/musicgen).

## Audiocraft Usage

You can also run MusicGen locally through the original [Audiocraft library]((https://github.com/facebookresearch/audiocraft):

1. First install the [`audiocraft` library](https://github.com/facebookresearch/audiocraft)
```
pip install git+https://github.com/facebookresearch/audiocraft.git
```

2. Make sure to have [`ffmpeg`](https://ffmpeg.org/download.html) installed:
```
apt get install ffmpeg
```

3. Run the following Python code:

```py
from audiocraft.models import MusicGen
from audiocraft.data.audio import audio_write

model = MusicGen.get_pretrained("small")
model.set_generation_params(duration=8)  # generate 8 seconds.

descriptions = ["happy rock", "energetic EDM"]

wav = model.generate(descriptions)  # generates 2 samples.

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")
```

## Model details

**Model card:** More details on the model can be found in [MusicGen's model card](https://github.com/facebookresearch/audiocraft/blob/main/model_cards/MUSICGEN_MODEL_CARD.md).

**Paper or resources for more information:** More information can be found in the paper [Simple and Controllable Music Generation](https://arxiv.org/abs/2306.05284).

**Citation details:**
```
@misc{copet2023simple,
      title={Simple and Controllable Music Generation}, 
      author={Jade Copet and Felix Kreuk and Itai Gat and Tal Remez and David Kant and Gabriel Synnaeve and Yossi Adi and Alexandre Défossez},
      year={2023},
      eprint={2306.05284},
      archivePrefix={arXiv},
      primaryClass={cs.SD}
}
```

**License:** Code is released under MIT, model weights are released under CC-BY-NC 4.0.

**Where to send questions or comments about the model:** Questions and comments about MusicGen can be sent via the [Github repository](https://github.com/facebookresearch/audiocraft) of the project, or by opening an issue.