File size: 4,259 Bytes
d5ee97c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"import numpy as np\n",
"import soundfile as sf\n",
"from pathlib import Path\n",
"from shutil import copyfile\n",
"from tqdm import tqdm\n",
"\n",
"input_dataset_path = \"[your_local_path]/synpaflex-corpus/v0.1/\"\n",
"reorganized_dataset_path = \"../synpaflex/\"\n",
"\n",
"maximal_duration = 12 # maximal audio file duration in seconds\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"wav_dir = os.path.join(reorganized_dataset_path, \"wavs/\")\n",
"os.makedirs(wav_dir, exist_ok=True)\n",
"data = []\n",
"total_duration = 0\n",
"\n",
"# Precomputing walk_count for tqdm\n",
"walk_count = 0\n",
"for subdir, dirs, files in os.walk(input_dataset_path):\n",
" walk_count += 1\n",
"\n",
"# walk through dataset\n",
"for subdir, dirs, files in tqdm(os.walk(input_dataset_path), total=walk_count, bar_format='Data Reorganization : {l_bar}{bar}|'):\n",
" for filename in files:\n",
" filepath = os.path.join(subdir, filename)\n",
"\n",
" # read wav files\n",
" if filepath.endswith(\".wav\"):\n",
" try:\n",
" wav, sr = sf.read(filepath)\n",
" duration = len(wav) / sr\n",
" \n",
" # Only keep files with shorter durations than maximal_duration\n",
" if duration <= maximal_duration:\n",
" total_duration += duration\n",
" path = Path(filepath)\n",
" current_path = Path(path.parent.absolute())\n",
" \n",
" # find corresponding text file\n",
" txt_file_path = os.path.join(current_path, \"txt\", filename.replace('.wav','.txt'))\n",
" if not os.path.exists(txt_file_path):\n",
" parent_path = Path(current_path.parent.absolute())\n",
" txt_file_path = os.path.join(parent_path, \"txt\", filename.replace('.wav', '.txt'))\n",
" if not os.path.exists(txt_file_path):\n",
" break\n",
" norm_text_file_path = txt_file_path.replace(\".txt\", \"_norm.txt\")\n",
" text = open(txt_file_path, \"r\").read()\n",
" if os.path.exists(norm_text_file_path):\n",
" norm_text = open(norm_text_file_path, 'r').read()\n",
" else : \n",
" norm_text = text\n",
" \n",
" # ignore file if text contains digits, otherwise copy wav file and keep metadata to memory \n",
" if not any(chr.isdigit() for chr in text):\n",
" data_line = filename.replace(\".wav\", \"\") + '|' + text + '|' + norm_text\n",
" data.append(data_line)\n",
" copyfile(filepath, os.path.join(wav_dir, filename))\n",
"\n",
" except RuntimeError:\n",
" print(filepath + \" not recognized and ignored.\") \n",
"\n",
"# save metadata\n",
"with open(os.path.join(reorganized_dataset_path, \"synpaflex.txt\"), 'w') as f:\n",
" for item in data:\n",
" f.write(\"%s\\n\" % item)\n",
"\n",
"# display reorganized dataset total duration\n",
"duration_hours = total_duration / 3600\n",
"print(\"total duration = \" + str(f\"{duration_hours:.2f}\") + \" hours\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|