|
|
|
|
|
|
|
|
|
import os |
|
import time as reqtime |
|
import datetime |
|
from pytz import timezone |
|
|
|
import gradio as gr |
|
|
|
import numpy as np |
|
|
|
import os |
|
import random |
|
from collections import Counter |
|
|
|
import TMIDIX |
|
|
|
from midi_to_colab_audio import midi_to_colab_audio |
|
|
|
|
|
|
|
def Generate_Chords_Progression(input_midi, input_sampling_resolution): |
|
|
|
print('=' * 70) |
|
print('Req start time: {:%Y-%m-%d %H:%M:%S}'.format(datetime.datetime.now(PDT))) |
|
start_time = reqtime.time() |
|
|
|
print('=' * 70) |
|
|
|
fn = os.path.basename(input_midi.name) |
|
fn1 = fn.split('.')[0] |
|
|
|
print('=' * 70) |
|
print('Ultimate MIDI Classifier') |
|
print('=' * 70) |
|
|
|
print('Input MIDI file name:', fn) |
|
|
|
print('=' * 70) |
|
|
|
print('Done!') |
|
print('=' * 70) |
|
|
|
classification_summary_string = '=' * 70 |
|
classification_summary_string += '\n' |
|
|
|
samples_overlap = 340 - chunk_size // input_sampling_resolution // 3 |
|
|
|
print('Composition has', notes_counter, 'notes') |
|
print('=' * 70) |
|
print('Composition was split into' , len(input_data), 'samples', 'of 340 notes each with', samples_overlap, 'notes overlap') |
|
print('=' * 70) |
|
print('Number of notes in all composition samples:', len(input_data) * 340) |
|
print('=' * 70) |
|
|
|
classification_summary_string += 'Composition has ' + str(notes_counter) + ' notes\n' |
|
classification_summary_string += '=' * 70 |
|
classification_summary_string += '\n' |
|
classification_summary_string += 'Composition was split into ' + 'samples of 340 notes each with ' + str(samples_overlap) + ' notes overlap\n' |
|
classification_summary_string += 'Number of notes in all composition samples: ' + str(len(input_data) * 340) + '\n' |
|
classification_summary_string += '=' * 70 |
|
classification_summary_string += '\n' |
|
|
|
|
|
|
|
print('=' * 70) |
|
print('Ultimate MIDI Classifier') |
|
print('=' * 70) |
|
|
|
print('=' * 70) |
|
print('Done!') |
|
print('=' * 70) |
|
|
|
result_toks = [final_result[0]-512, final_result[1]-512] |
|
mc_song_artist = song_artist_tokens_to_song_artist(result_toks) |
|
gidx = genre_labels_fnames.index(mc_song_artist) |
|
mc_genre = genre_labels[gidx][1] |
|
|
|
print('Most common classification genre label:', mc_genre) |
|
print('Most common classification song-artist label:', mc_song_artist) |
|
print('Most common song-artist classification label ratio:' , results.count(final_result) / len(results)) |
|
print('=' * 70) |
|
|
|
classification_summary_string += 'Most common classification genre label: ' + str(mc_genre) + '\n' |
|
classification_summary_string += 'Most common classification song-artist label: ' + str(mc_song_artist) + '\n' |
|
classification_summary_string += 'Most common song-artist classification label ratio: '+ str(results.count(final_result) / len(results)) + '\n' |
|
classification_summary_string += '=' * 70 |
|
classification_summary_string += '\n' |
|
|
|
print('All classification labels summary:') |
|
print('=' * 70) |
|
|
|
all_artists_labels = [] |
|
|
|
for i, res in enumerate(results): |
|
result_toks = [res[0]-512, res[1]-512] |
|
song_artist = song_artist_tokens_to_song_artist(result_toks) |
|
gidx = genre_labels_fnames.index(song_artist) |
|
genre = genre_labels[gidx][1] |
|
|
|
print('Notes', i*(340-samples_overlap), '-', (i*(340-samples_overlap))+340, '===', genre, '---', song_artist) |
|
classification_summary_string += 'Notes ' + str(i*samples_overlap) + ' - ' + str((i*samples_overlap)+340) + ' === ' + str(genre) + ' --- ' + str(song_artist) + '\n' |
|
|
|
artist_label = str_strip_artist(song_artist.split(' --- ')[1]) |
|
|
|
all_artists_labels.append(artist_label) |
|
|
|
classification_summary_string += '=' * 70 |
|
classification_summary_string += '\n' |
|
print('=' * 70) |
|
|
|
mode_artist_label = mode(all_artists_labels) |
|
mode_artist_label_count = all_artists_labels.count(mode_artist_label) |
|
|
|
print('Aggregated artist classification label:', mode_artist_label) |
|
print('Aggregated artist classification label ratio:', mode_artist_label_count / len(all_artists_labels)) |
|
classification_summary_string += 'Aggregated artist classification label: ' + str(mode_artist_label) + '\n' |
|
classification_summary_string += 'Aggregated artist classification label ratio: ' + str(mode_artist_label_count / len(all_artists_labels)) + '\n' |
|
classification_summary_string += '=' * 70 |
|
classification_summary_string += '\n' |
|
|
|
print('=' * 70) |
|
print('Done!') |
|
print('=' * 70) |
|
|
|
|
|
|
|
print('-' * 70) |
|
print('Req end time: {:%Y-%m-%d %H:%M:%S}'.format(datetime.datetime.now(PDT))) |
|
print('-' * 70) |
|
print('Req execution time:', (reqtime.time() - start_time), 'sec') |
|
|
|
return classification_summary_string |
|
|
|
|
|
|
|
if __name__ == "__main__": |
|
|
|
PDT = timezone('US/Pacific') |
|
|
|
print('=' * 70) |
|
print('App start time: {:%Y-%m-%d %H:%M:%S}'.format(datetime.datetime.now(PDT))) |
|
print('=' * 70) |
|
|
|
print('=' * 70) |
|
print('Loading Ultimate MIDI Classifier labels...') |
|
print('=' * 70) |
|
good_chords_chunks = TMIDIX.Tegridy_Any_Pickle_File_Reader('pitches_chords_progressions_5_3_15') |
|
|
|
print('=' * 70) |
|
print('Done!') |
|
print('=' * 70) |
|
|
|
app = gr.Blocks() |
|
with app: |
|
gr.Markdown("<h1 style='text-align: center; margin-bottom: 1rem'>Chords Progressions Generator</h1>") |
|
gr.Markdown("<h1 style='text-align: center; margin-bottom: 1rem'>Generate unique chords progressions</h1>") |
|
gr.Markdown( |
|
"\n\n" |
|
"This is a demo for Tegridy MIDI Dataset\n\n" |
|
"Check out [Tegridy MIDI Dataset](https://github.com/asigalov61/Tegridy-MIDI-Dataset) on GitHub!\n\n" |
|
"[Open In Colab]" |
|
"(https://colab.research.google.com/github/asigalov61/Tegridy-MIDI-Dataset/blob/master/Chords-Progressions/Pitches_Chords_Progressions_Generator.ipynb)" |
|
" for all options, faster execution and endless generation" |
|
) |
|
|
|
gr.Markdown("## Select generation options") |
|
|
|
input_sampling_resolution = gr.Slider(1, 5, value=2, step=1, label="Classification sampling resolution") |
|
|
|
run_btn = gr.Button("classify", variant="primary") |
|
|
|
gr.Markdown("## Generation results") |
|
|
|
output_midi_cls_summary = gr.Textbox(label="MIDI classification results") |
|
|
|
run_event = run_btn.click(ClassifyMIDI, [input_midi, input_sampling_resolution], |
|
[output_midi_cls_summary]) |
|
|
|
app.queue().launch() |
