This is a generative model from the paper «Byte Pair Encoding for Symbolic Music» (EMNLP 2023). The model has been trained with Byte Pair Encoding (BPE) on the Maestro dataset to generate classical piano music with the REMI tokenizer. It has a vocabulary of 20k tokens learned with Byte Pair Encoding (BPE) using MidiTok. — Developed and shared by: Nathan Fradet — Affiliations: Sorbonne University (LIP6 lab) and Aubay — Model type: causal autoregressive Transformer — Backbone model: GPT2 — Music genres: Classical piano 🎹 — License: Apache 2.0 — Repository: https://github.com/Natooz/BPE-Symbolic-Music — Paper: ACL https://aclanthology.org/2023.emnlp-main.123/ — arXiv https://arxiv.org/abs/2301.11975 The model is designed for autoregressive music generation. It generates the continuation of a music prompt. Use the code below to get started with the model. You will need the miditok (>=v2.1.7), transformers and torch packages to make it run, that can be installed with pip. The model has been trained on the Maestro dataset. The dataset contains about 200 hours of classical piano music. The tokenizer is trained with Byte Pair Encoding (BPE) to build a vocabulary of 20k tokens. — Training…
Модальности:
Генерация текста
Задача: Генерация текста
Автор: NathanFradet
Теги: tensorboard, gpt2, miditok, music, music generation, piano, classical, text-generation-inference
Лайков: 3 | Загрузок: 349
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
