A design of MIDI language for music generation task, specifically for Natural Language Processing (NLP) models.

Overview

MIDI Language

Introduction

Reference

Paper: Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions: code

This is a modified version with an extension of multi-instrumental support.

Function

Convert Midi into event sequence, and represented by mapped integer array.

This could send to NLP models for AI auto music composition.

Due to this project considers more about music structures as well as its chord and melody on higher level, including note, drum, tempo, musical instrument (program in midi) and its expressions (tempo and velocity), rather than digging into too much details like sound source & direction, instrumental performing techniques (such as, bend sound, piano sustain pedal, violin overtones), the language of MIDI is design this way (see chapter Details below).

Usage

See language.py, it contains procedures:

  • load w2i (word to integer) and i2w (integer to word), for not calculating it every time;
  • encode midi to iteger array, each object handle one mid file;
  • decode integer array to midi, each object handle many results and export to mid files;

The code language.py has arguments:

  • input: input file of audio file to encode/decode;
  • output: output file of audio file to encode;
  • train: if have, it will switch to training mode with variations (data augmentation);

MidiEncoder data augmentation:

  • pitch_variation_range: a random pitch shift within a range for whole midi;
  • velocity_scale_variation_range: a random note/drum velocity scale for whole midi;
  • velocity_noise_scale_variation_range: a random note/drum velocity scale for each element within midi;
  • tempo_scale_variation_range: a random tempo change for whole midi;

MidiDecoder needs numerator and denominator time signatures for reconstructing midi files.

Details

Event Structure

Required:

  • Bar
  • Position (0~split-1)

Optional:

  • note:
    • Note
    • Program (0~127)
    • Pitch (0~127)
    • Velocity (0~127)
    • Duration (0~split*bar_scale-1)
  • drum:
    • Drum
    • Program (0~127)
    • Pitch (0~127)
    • Velocity (0~127)
    • Duration (0~split*bar_scale-1)
  • chord:
    • Chord (chroma_name:chord_name)
  • tempo:
    • Tempo_Class (T0~Ti)
    • Tempo_Value (0~59)
Owner
Robert Bogan Kang
hello rbk!
Robert Bogan Kang
Binaural Speech Synthesis

Binaural Speech Synthesis This repository contains code to train a mono-to-binaural neural sound renderer. If you use this code or the provided datase

Facebook Research 135 Dec 18, 2022
A python script that will use hydra to get user and password to login to ssh, ftp, and telnet

Hydra-Auto-Hack A python script that will use hydra to get user and password to login to ssh, ftp, and telnet Project Description This python script w

2 Jan 16, 2022
A Non-Autoregressive Transformer based TTS, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS.

A Non-Autoregressive Transformer based TTS, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to ach

Keon Lee 237 Jan 02, 2023
SimBERT升级版(SimBERTv2)!

RoFormer-Sim RoFormer-Sim,又称SimBERTv2,是我们之前发布的SimBERT模型的升级版。 介绍 https://kexue.fm/archives/8454 训练 tensorflow 1.14 + keras 2.3.1 + bert4keras 0.10.6 下载

317 Dec 23, 2022
[ICLR'19] Trellis Networks for Sequence Modeling

TrellisNet for Sequence Modeling This repository contains the experiments done in paper Trellis Networks for Sequence Modeling by Shaojie Bai, J. Zico

CMU Locus Lab 460 Oct 13, 2022
Simple tool/toolkit for evaluating NLG (Natural Language Generation) offering various automated metrics.

Simple tool/toolkit for evaluating NLG (Natural Language Generation) offering various automated metrics. Jury offers a smooth and easy-to-use interface. It uses datasets for underlying metric computa

Open Business Software Solutions 129 Jan 06, 2023
Model parallel transformers in JAX and Haiku

Table of contents Mesh Transformer JAX Updates Pretrained Models GPT-J-6B Links Acknowledgments License Model Details Zero-Shot Evaluations Architectu

Ben Wang 4.9k Jan 04, 2023
glow-speak is a fast, local, neural text to speech system that uses eSpeak-ng as a text/phoneme front-end.

Glow-Speak glow-speak is a fast, local, neural text to speech system that uses eSpeak-ng as a text/phoneme front-end. Installation git clone https://g

Rhasspy 8 Dec 25, 2022
Code for Findings of ACL 2022 Paper "Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors"

SWRM Code for Findings of ACL 2022 Paper "Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors" Clone Clone th

14 Jan 03, 2023
Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge. Proceedings of EMNLP 2021

AAGCN-ACSA EMNLP 2021 Introduction This repository was used in our paper: Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment An

Akuchi 36 Dec 18, 2022
:mag: Transformers at scale for question answering & neural search. Using NLP via a modular Retriever-Reader-Pipeline. Supporting DPR, Elasticsearch, HuggingFace's Modelhub...

Haystack is an end-to-end framework that enables you to build powerful and production-ready pipelines for different search use cases. Whether you want

deepset 6.4k Jan 09, 2023
Contains the code and data for our #ICSE2022 paper titled as "CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences"

CodeFill This repository contains the code for our paper titled as "CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Namin

Software Analytics Lab 11 Oct 31, 2022
LeBenchmark: a reproducible framework for assessing SSL from speech

LeBenchmark: a reproducible framework for assessing SSL from speech

11 Nov 30, 2022
PRAnCER is a web platform that enables the rapid annotation of medical terms within clinical notes.

PRAnCER (Platform enabling Rapid Annotation for Clinical Entity Recognition) is a web platform that enables the rapid annotation of medical terms within clinical notes. A user can highlight spans of

Sontag Lab 39 Nov 14, 2022
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

DeeBERT This is the code base for the paper DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference. Code in this repository is also available

Castorini 132 Nov 14, 2022
An open-source NLP research library, built on PyTorch.

An Apache 2.0 NLP research library, built on PyTorch, for developing state-of-the-art deep learning models on a wide variety of linguistic tasks. Quic

AI2 11.4k Jan 01, 2023
A Structured Self-attentive Sentence Embedding

Structured Self-attentive sentence embeddings Implementation for the paper A Structured Self-Attentive Sentence Embedding, which was published in ICLR

Kaushal Shetty 488 Nov 28, 2022
code for modular summarization work published in ACL2021 by Krishna et al

This repository contains the code for running modular summarization pipelines as described in the publication Krishna K, Khosla K, Bigham J, Lipton ZC

Approximately Correct Machine Intelligence (ACMI) Lab 21 Nov 24, 2022
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context

LSTC: Boosting Atomic Action Detection with Long-Short-Term Context This Repository contains the code on AVA of our ACM MM 2021 paper: LSTC: Boosting

Tencent YouTu Research 9 Oct 11, 2022
The NewSHead dataset is a multi-doc headline dataset used in NHNet for training a headline summarization model.

This repository contains the raw dataset used in NHNet [1] for the task of News Story Headline Generation. The code of data processing and training is available under Tensorflow Models - NHNet.

Google Research Datasets 31 Jul 15, 2022