File size: 4,535 Bytes
b0c0df0 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import datasets\n",
"import json\n",
"\n",
"# Define the dataset features (audio, text, and source)\n",
"# change the data structure according to your needs, only important changes here is using datasets.Audio to load audio file\n",
"# And provide audio path in the data construction\n",
"# once loaded through datasets.Audio, we can access audio data, in the form of np.array(float32) using doc[\"audio\"][\"array\"]\n",
"features = datasets.Features(\n",
" {\n",
" \"audio\": datasets.Audio(sampling_rate=16000),\n",
" \"prompt\": datasets.Value(\"string\"),\n",
" \"gt\": datasets.Value(\"string\"),\n",
" \"source\": datasets.Value(\"string\"),\n",
" \"task\": datasets.Value(\"string\"),\n",
" }\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# loading data into dict form\n",
"def load_audio_data(data_path):\n",
" with open(data_path, 'r') as f:\n",
" data_lines = f.readlines()\n",
"\n",
" audio_list = []\n",
" prompt_list = []\n",
" gt_list = []\n",
" source_list = []\n",
" task_list = []\n",
"\n",
" for line in data_lines:\n",
" json_data = json.loads(line.strip())\n",
"\n",
" audio_list.append(json_data['audio']) # Path to the actual audio file\n",
" prompt_list.append(\"<|audio_bos|><|AUDIO|><|audio_eos|>\" + json_data['prompt'])\n",
" gt_list.append(json_data['gt'])\n",
" source_list.append(json_data['source'])\n",
" task_list.append(json_data['task'])\n",
"\n",
" # Return a dictionary where keys are features and values are lists of data\n",
" return {\n",
" 'audio': audio_list,\n",
" 'prompt': prompt_list,\n",
" 'gt': gt_list,\n",
" 'source': source_list,\n",
" 'task': task_list\n",
" }"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# load data according to different task\n",
"def load_audio_data_task(data_path, task):\n",
" with open(data_path, 'r') as f:\n",
" data_lines = f.readlines()\n",
"\n",
" audio_list = []\n",
" prompt_list = []\n",
" gt_list = []\n",
" source_list = []\n",
" task_list = []\n",
"\n",
" for line in data_lines:\n",
" json_data = json.loads(line.strip())\n",
" if json_data['source'] == task: \n",
"\n",
" \n",
" audio_list.append(json_data['audio']) # Path to the actual audio file\n",
" prompt_list.append(\"<|audio_bos|><|AUDIO|><|audio_eos|>\" + json_data['prompt'])\n",
" gt_list.append(json_data['gt'])\n",
" source_list.append(json_data['source'])\n",
" task_list.append(json_data['task'])\n",
"\n",
" # Return a dictionary where keys are features and values are lists of data\n",
" return {\n",
" 'audio': audio_list,\n",
" 'prompt': prompt_list,\n",
" 'gt': gt_list,\n",
" 'source': source_list,\n",
" 'task': task_list\n",
" }\n",
"\n",
"\n",
"tasks = ['librispeech_test_other', 'librispeech_dev_other', 'librispeech_test_clean', 'librispeech_dev_clean']\n",
"\n",
"# description_root\n",
"data_description_path = \"./librispeech_eval.jsonl\"\n",
"\n",
"data_dict = {}\n",
"for task in tasks:\n",
"\n",
" # Load the dataset into a Hugging Face Dataset object\n",
" data = load_audio_data_task(data_description_path, task)\n",
"\n",
" # Create a Dataset from the data and features\n",
" dataset = datasets.Dataset.from_dict(data, features=features)\n",
"\n",
" # Verify the dataset structure\n",
" print(dataset)\n",
"\n",
" data_dict[task] = dataset\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"data = datasets.DatasetDict(data_dict)\n",
"data.push_to_hub(\"Alarak/librispeech\")"
]
}
],
"metadata": {
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|