music generation

ProviderDancingIguana
Categoryaudio-generation
Licenseapache-2.0
Downloads100
Stars0

Overview

This music generation model by DancingIguana offers an open-source alternative for integrating high-fidelity audio synthesis into your applications. Designed for developers who need flexible audio assets, it allows for the programmatic creation of musical tracks based on text prompts or structural parameters. Unlike proprietary black-box APIs, its Apache-2.0 license ensures seamless integration into commercial pipelines without restrictive licensing overhead. It is particularly well-suited for game development, dynamic background scoring, and content creation tools where rapid iteration of audio prototypes is required. While it focuses on generation rather than editing, it provides a robust foundation for building automated soundscapes and generative music experiences.

Highlights

  • Apache-2.0 license for flexible commercial integration
  • High-fidelity audio synthesis from text prompts
  • Ideal for dynamic game soundtracks and content tools
  • Open-source architecture enabling transparent deployment

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("DancingIguana/music-generation")
tokenizer = AutoTokenizer.from_pretrained("DancingIguana/music-generation")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download DancingIguana/music-generation

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download DancingIguana/music-generation config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('DancingIguana/music-generation')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/DancingIguana/music-generation

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/DancingIguana/music-generation

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('DancingIguana/music-generation')
tokenizer = AutoTokenizer.from_pretrained('DancingIguana/music-generation')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
tags:

  • generated_from_trainer

model-index:
  • name: music-generation

results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

music-generation

This model a trained from scratch version of distilgpt2 on a dataset where the text represents musical notes. The dataset consists of one stream of notes from MIDI files (the stream with most notes), where all of the melodies were transposed either to C major or A minor. Also, the BPM of the song is ignored, the duration of each note is based on its quarter length.

Each element in the melody is represented by a series of letters and numbers with the following structure.

  • For a note: ns[pitch of the note as a string]s[duration]

* Examples: nsC4s0p25, nsF7s1p0,
  • For a rest: rs[duration]:

* Examples: rs0p5, rs1q6
  • For a chord: cs[number of notes in chord]s[pitches of chords separated by "s"]s[duration]

* Examples: cs2sE7sF7s1q3, cs2sG3sGw3s0p25

The following special symbols are replaced in the strings by the following:
  • . = p

  • / = q

  • # =

  • - = t

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0005

  • train_batch_size: 32

  • eval_batch_size: 32

  • seed: 42

  • gradient_accumulation_steps: 8

  • total_train_batch_size: 256

  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

  • lr_scheduler_type: cosine

  • lr_scheduler_warmup_steps: 1000

  • num_epochs: 100

  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.19.4
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1
View official source
Join our Telegram