All Projects → tatsuyah → deep-improvisation

tatsuyah / deep-improvisation

Licence: MIT License
Easy-to-use Deep LSTM Neural Network to generate song sounds like containing improvisation.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to deep-improvisation

Ailearning
AiLearning: 机器学习 - MachineLearning - ML、深度学习 - DeepLearning - DL、自然语言处理 NLP
Stars: ✭ 32,316 (+60873.58%)
Mutual labels:  lstm, rnn, deeplearning
Deeplearning.ai Assignments
Stars: ✭ 268 (+405.66%)
Mutual labels:  lstm, rnn, deeplearning
air writing
Online Hand Writing Recognition using BLSTM
Stars: ✭ 26 (-50.94%)
Mutual labels:  lstm, rnn, deeplearning
Deepjazz
Deep learning driven jazz generation using Keras & Theano!
Stars: ✭ 2,766 (+5118.87%)
Mutual labels:  lstm, rnn, jazz
SpeakerDiarization RNN CNN LSTM
Speaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2 speakers (on separate channels).
Stars: ✭ 56 (+5.66%)
Mutual labels:  lstm, rnn
question-pair
A siamese LSTM to detect sentence/question pairs.
Stars: ✭ 25 (-52.83%)
Mutual labels:  lstm, rnn
sequence-rnn-py
Sequence analyzing using Recurrent Neural Networks (RNN) based on Keras
Stars: ✭ 28 (-47.17%)
Mutual labels:  lstm, rnn
Forecasting-Solar-Energy
Forecasting Solar Power: Analysis of using a LSTM Neural Network
Stars: ✭ 23 (-56.6%)
Mutual labels:  lstm, deeplearning
EBIM-NLI
Enhanced BiLSTM Inference Model for Natural Language Inference
Stars: ✭ 24 (-54.72%)
Mutual labels:  lstm, rnn
lstm-electric-load-forecast
Electric load forecast using Long-Short-Term-Memory (LSTM) recurrent neural network
Stars: ✭ 56 (+5.66%)
Mutual labels:  lstm, rnn
OCR
Optical character recognition Using Deep Learning
Stars: ✭ 25 (-52.83%)
Mutual labels:  lstm, deeplearning
novel writer
Train LSTM to writer novel (HongLouMeng here) in Pytorch.
Stars: ✭ 14 (-73.58%)
Mutual labels:  lstm, rnn
Paper-Implementation-DSTP-RNN-For-Stock-Prediction-Based-On-DA-RNN
基於DA-RNN之DSTP-RNN論文試做(Ver1.0)
Stars: ✭ 62 (+16.98%)
Mutual labels:  lstm, rnn
ArrayLSTM
GPU/CPU (CUDA) Implementation of "Recurrent Memory Array Structures", Simple RNN, LSTM, Array LSTM..
Stars: ✭ 21 (-60.38%)
Mutual labels:  lstm, rnn
ConvLSTM-PyTorch
ConvLSTM/ConvGRU (Encoder-Decoder) with PyTorch on Moving-MNIST
Stars: ✭ 202 (+281.13%)
Mutual labels:  lstm, rnn
theano-recurrence
Recurrent Neural Networks (RNN, GRU, LSTM) and their Bidirectional versions (BiRNN, BiGRU, BiLSTM) for word & character level language modelling in Theano
Stars: ✭ 40 (-24.53%)
Mutual labels:  lstm, rnn
automatic-personality-prediction
[AAAI 2020] Modeling Personality with Attentive Networks and Contextual Embeddings
Stars: ✭ 43 (-18.87%)
Mutual labels:  lstm, rnn
myDL
Deep Learning
Stars: ✭ 18 (-66.04%)
Mutual labels:  lstm, rnn
Learning-Lab-C-Library
This library provides a set of basic functions for different type of deep learning (and other) algorithms in C.This deep learning library will be constantly updated
Stars: ✭ 20 (-62.26%)
Mutual labels:  lstm, deeplearning
tf-ran-cell
Recurrent Additive Networks for Tensorflow
Stars: ✭ 16 (-69.81%)
Mutual labels:  lstm, rnn

Deep Improvisation

Easy-to-use Deep LSTM Neural Network to generate song like containing improvisation.

Demo (SoundCloud)

screenshot

Dependencies

  • Keras
  • TensorFlow
  • Python MIDI

Usage

1. Set up environment (conda recommended)

pip install -r requirements.txt

2. Parse MIDI file to text

python ./src/parse_midi_to_text.py

3. Train the model (GPU recommended)

python ./src/training.py

4. Generate music

python ./src/generate_music.py

Note

  • You can use other MIDI file to train the model to generate new song. Change the file ./midi/original/original_song.mid.
  • MIDI format is usually consist of multiple track and this repository is currently not supporting automatic detection which track is main part of the song. So you may have to choose track as index of the pattern in parse_midi_to_text.py.

License

MIT © Tatsuya Hatanaka

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].