{
"cells": [
{
"cell_type": "markdown",
"id": "7a9aa1cb",
"metadata": {},
"source": [
"## 미디 파일에 맞는 스타일 벡터 생성을 위한 곳"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "19ba84e1",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"file name: 0.mid\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" \n",
" \n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"ename": "KeyError",
"evalue": "'add4'",
"output_type": "error",
"traceback": [
"\u001b[31m---------------------------------------------------------------------------\u001b[39m",
"\u001b[31mKeyError\u001b[39m Traceback (most recent call last)",
"\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[2]\u001b[39m\u001b[32m, line 21\u001b[39m\n\u001b[32m 11\u001b[39m MIDI.set_midi(os.path.join(\u001b[33m\"\u001b[39m\u001b[33mdata\u001b[39m\u001b[33m\"\u001b[39m, filename))\n\u001b[32m 13\u001b[39m midiplayer.play_score(MIDI._midi) \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n\u001b[32m 15\u001b[39m tokenized_data.append({\n\u001b[32m 16\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mvector\u001b[39m\u001b[33m\"\u001b[39m:{ \u001b[38;5;66;03m# Max is 100\u001b[39;00m\n\u001b[32m 17\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mBPM\u001b[39m\u001b[33m\"\u001b[39m:\u001b[32m128\u001b[39m,\n\u001b[32m 18\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mAggressive\u001b[39m\u001b[33m\"\u001b[39m:\u001b[32m13\u001b[39m,\n\u001b[32m 19\u001b[39m \n\u001b[32m 20\u001b[39m },\n\u001b[32m---> \u001b[39m\u001b[32m21\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mtoken\u001b[39m\u001b[33m\"\u001b[39m:\u001b[43mMIDI\u001b[49m\u001b[43m.\u001b[49m\u001b[43mtoken_id\u001b[49m\n\u001b[32m 22\u001b[39m })\n",
"\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\rrayy\\anaconda3\\envs\\diva\\Lib\\site-packages\\HarmonyMIDIToken\\tokenizer.py:169\u001b[39m, in \u001b[36mHarmonyMIDIToken.token_id\u001b[39m\u001b[34m(self)\u001b[39m\n\u001b[32m 167\u001b[39m \u001b[38;5;250m\u001b[39m\u001b[33;03m\"\"\"HarmonyMIDIToken에 대한 토큰 ID를 반환한다.\"\"\"\u001b[39;00m\n\u001b[32m 168\u001b[39m melody_tokens = \u001b[38;5;28mself\u001b[39m._tokenize(\u001b[38;5;28mself\u001b[39m.melody)\n\u001b[32m--> \u001b[39m\u001b[32m169\u001b[39m chords_tokens = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_tokenize\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mchords\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 170\u001b[39m bass_tokens = \u001b[38;5;28mself\u001b[39m._tokenize(\u001b[38;5;28mself\u001b[39m.bass)\n\u001b[32m 172\u001b[39m token = [\u001b[38;5;28mself\u001b[39m.bpm, \u001b[32m100\u001b[39m] + melody_tokens +[\u001b[32m200\u001b[39m]+ chords_tokens +[\u001b[32m300\u001b[39m]+ bass_tokens\n",
"\u001b[36mFile \u001b[39m\u001b[32mc:\\Users\\rrayy\\anaconda3\\envs\\diva\\Lib\\site-packages\\HarmonyMIDIToken\\tokenizer.py:113\u001b[39m, in \u001b[36mHarmonyMIDIToken._tokenize\u001b[39m\u001b[34m(self, data)\u001b[39m\n\u001b[32m 110\u001b[39m chord = pychord_chord(value)\n\u001b[32m 112\u001b[39m tokens.append(\u001b[38;5;28mself\u001b[39m._note_name_to_intpitch(chord._root+\u001b[33m\"\u001b[39m\u001b[33m4\u001b[39m\u001b[33m\"\u001b[39m))\n\u001b[32m--> \u001b[39m\u001b[32m113\u001b[39m tokens.append(\u001b[43mquality_map\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;28;43mstr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mchord\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_quality\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m)\n\u001b[32m 115\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m j \u001b[38;5;129;01min\u001b[39;00m chord._appended:\n\u001b[32m 116\u001b[39m tokens.append(\u001b[38;5;28mself\u001b[39m._note_name_to_intpitch(j+\u001b[33m\"\u001b[39m\u001b[33m4\u001b[39m\u001b[33m\"\u001b[39m))\n",
"\u001b[31mKeyError\u001b[39m: 'add4'"
]
}
],
"source": [
"from HarmonyMIDIToken import HarmonyMIDIToken as Tokenizer\n",
"from utillity import midiplayer\n",
"import os\n",
"\n",
"tokenized_data = []\n",
"\n",
"for filename in os.listdir(\"data\"):\n",
" if filename.endswith(\".mid\"):\n",
" MIDI = Tokenizer()\n",
" print(f\"file name: {filename}\")\n",
" MIDI.set_midi(os.path.join(\"data\", filename))\n",
" \n",
" midiplayer.play_score(MIDI._midi) # type: ignore\n",
"\n",
" tokenized_data.append({\n",
" \"vector\":{ # Max is 100\n",
" \"BPM\":128,\n",
" \"Aggressive\":13,\n",
" \n",
" },\n",
" \"token\":MIDI.token_id\n",
" })\n",
" "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f79a6edf",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tokenized MIDI data: 31\n"
]
}
],
"source": [
"print(\"Tokenized MIDI data:\", len(tokenized_data))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "21a9ba89",
"metadata": {},
"outputs": [],
"source": [
"import json # JSON 파일로 토크나이저 미디 데이터 저장\n",
"\n",
"with open('tokenized_midi_data.json', 'w') as f:\n",
" json.dump(tokenized_data, f, indent=4)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dea532d4",
"metadata": {},
"outputs": [],
"source": [
"import json # JSON으로 저장한 토크나이저 미디 데이터 불러오기\n",
"\n",
"with open('tokenized_midi_data.json', 'r') as f:\n",
" tokenized_data = json.load(f)\n",
"# Convert string keys back to tuple\n",
"# tokenized_data = {tuple(key.split(\"|\")): value for key, value in tokenized_data.items()}\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "34c244ab",
"metadata": {},
"outputs": [],
"source": [
"# value로 key 찾기\n",
"def get_key_by_value(D:dict, value):\n",
" for k, v in D.items():\n",
" if v == value:\n",
" return k\n",
" return None"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "diva",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}