distilgpt2 abc irish music generation

Providerehcalabres
Categoryaudio-generation
Licenseapache-2.0
Downloads153
Stars0

Overview

The distilgpt2-abc-irish-music model is a specialized generative tool designed for developers working with symbolic music representation. Rather than outputting raw audio, it generates music in ABC notation—a lightweight, text-based format that is easily parsed and converted into MIDI or sheet music. This makes it an ideal choice for integrating procedural music generation into apps, games, or digital archives without the overhead of heavy audio files. By leveraging a distilled GPT-2 architecture, the model provides a computationally efficient way to generate traditional Irish melodies that maintain structural coherence. Compared to general-purpose LLMs, this model is fine-tuned specifically for the rhythmic and melodic constraints of the Irish folk tradition, ensuring higher stylistic accuracy for niche musical applications.

Highlights

  • Generates music using lightweight, text-based ABC notation
  • Optimized for traditional Irish folk melody structures
  • Low latency inference via distilled GPT-2 architecture
  • Easy integration with MIDI and sheet music converters
  • Permissive Apache-2.0 license for commercial 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("ehcalabres/distilgpt2-abc-irish-music-generation")
tokenizer = AutoTokenizer.from_pretrained("ehcalabres/distilgpt2-abc-irish-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 ehcalabres/distilgpt2-abc-irish-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 ehcalabres/distilgpt2-abc-irish-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('ehcalabres/distilgpt2-abc-irish-music-generation')

Git Download

Make sure git-lfs is installed first

Git Download
git lfs install
git clone https://huggingface.co/ehcalabres/distilgpt2-abc-irish-music-generation

To skip LFS large-file downloads, use:

Skip LFS
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/ehcalabres/distilgpt2-abc-irish-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('ehcalabres/distilgpt2-abc-irish-music-generation')
tokenizer = AutoTokenizer.from_pretrained('ehcalabres/distilgpt2-abc-irish-music-generation')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
tags:

  • generated_from_trainer

base_model: distilgpt2
model-index:
  • name: distilgpt2-abc-irish-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. -->

distilgpt2-abc-irish-music-generation

This model is a fine-tuned version of distilgpt2 on an unknown dataset.

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: 5e-05

  • train_batch_size: 4

  • eval_batch_size: 4

  • seed: 42

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

  • lr_scheduler_type: linear

  • lr_scheduler_warmup_steps: 500

  • num_epochs: 10

Training results

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1
Join our Telegram