Buckets:
| { | |
| "cells": [ | |
| { | |
| "cell_type": "code", | |
| "execution_count": 1, | |
| "metadata": { | |
| "id": "tYm5pVspx9xd" | |
| }, | |
| "outputs": [], | |
| "source": [ | |
| "import os\n", | |
| "import cv2\n", | |
| "import numpy as np\n", | |
| "import pandas as pd\n", | |
| "import matplotlib.pyplot as plt\n", | |
| "from PIL import Image\n", | |
| "from tensorflow.keras import datasets\n", | |
| "import tensorflow as tf\n", | |
| "from datasets import load_dataset\n", | |
| "from tensorflow.keras import layers, models, Input\n", | |
| "from tensorflow.keras.optimizers import Adam\n", | |
| "from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint\n", | |
| "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n", | |
| "from sklearn.model_selection import train_test_split\n", | |
| "from sklearn.metrics import classification_report" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 2, | |
| "metadata": { | |
| "id": "uuEHs11CybIY", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 448, | |
| "referenced_widgets": [ | |
| "aa313eee96804d609757d002d5e74e56", | |
| "3470ee488cfa4e49b06f8a87f3f7b04b", | |
| "820198f3b97a47ed8fe4df52e52784db", | |
| "c4d52890dbc645b4839eca04f04dc095", | |
| "58dad371f9b1418b96c68fce92aa7d91", | |
| "7302cde51c014e3ba4f53e4544027416", | |
| "4ef9183414634faca637707777ad37ab", | |
| "9844e8a0f4204c0fa3dada598d513bb4", | |
| "3379384ba9cb4557a8ba902f4ea9fb8e", | |
| "0fdb6b8ca2fa4336b7062b8527680565", | |
| "c2c17f4cac3b491c9608fc46954393c2", | |
| "a33c7f53e54c4bcda2809109dc88af6d", | |
| "e4501b4aeb864b69a049ce3555801f3a", | |
| "e4539eb73176411cbaf79f2c9e23ee77", | |
| "76308a0c9e0641caa60b8cacc54444f2", | |
| "4b0dca03899841608c8776972970a757", | |
| "9426b0161fff4cd5a73e94933e53cd1b", | |
| "3458ecb921314ac9847db8fa8cef72c4", | |
| "b4e82788b6854359a040930a46feb58f", | |
| "f3b82a043a8244579e87b1c94111dd64", | |
| "4b236b923d514089b27e0655322ab30a", | |
| "70bc59cd67e84c2d8b74ab066080c118", | |
| "8db77ab57cc64bb6a23b2ad873a90d2b", | |
| "b2b24d1591a347fcab06f7c7af8f2b71", | |
| "acf47046a0c04c839e0f31d073eba3de", | |
| "78dd58c598164df29cc00172d1369219", | |
| "4e69090fdf124637906eaa5c4895d702", | |
| "52e3fcd92ff4483e9e80f2cd08d52e4c", | |
| "5b090e4fe38740b7994ea24a4faba077", | |
| "0a60d3dddd804e6b936ef34885ff2493", | |
| "14389181189a4542ba77d687489e75c4", | |
| "9c8cbfed8d1b4f1499e94597fccce5e4", | |
| "b52322ee82834a3884b732cbe2c1a80a", | |
| "9c6f7e3adbf442459a7619b50cccbad6", | |
| "7811c59647d140c38c15045434ece00d", | |
| "bc392bd61ca94f359b65a9a76de4abb6", | |
| "31928153f8ba46f8892451b043486a5a", | |
| "f22a20011692425996bf25f5b89338a5", | |
| "5116ae03451f4576b2108e39e431b518", | |
| "d60aba9eec7f4c0eb2e05a7148d6eb5d", | |
| "c6409b87ad2a4146b9e06dbaf1383f10", | |
| "14ee8f727ed3426890f1f76d629d28ba", | |
| "53cc6ca8114f4c8f97ff963511f188cd", | |
| "0d63ed78c4da4a68afbfab605ef0a57c", | |
| "9836562b9d4a47b093d2d45df2f631ba", | |
| "924c05e23f114f06a966125d94451e47", | |
| "41e7d783bb7d4db7963bfcbd6faf3711", | |
| "ac3e4bc7548e45729a34c70224001201", | |
| "abfe72f663a0424eba43345ac948cc36", | |
| "8a7e7f5448e84d0383695841859ac083", | |
| "541620a7831145bb9fe57982e62ba706", | |
| "3ec8503dfb0f44e184e94aa3fd8fa2fd", | |
| "4f00f0b7c5de45cc96a0c88f9c513ec7", | |
| "6a5f7619e80e429ca87000da6b874f96", | |
| "8b167c6e50bf43efab4de8d4289adf33", | |
| "60302f73bec544e89dae361010003105", | |
| "b838344d3ac7419e96905f99208bf3b5", | |
| "f8e49d33d8b446028190b90151a7c92e", | |
| "f3bcf8f9b44441c8bb3897260040dabb", | |
| "c436a0a10ade41c6bcedc484caf96383", | |
| "d54a970092594aa99814a9da0fbdf487", | |
| "e1bd0176b16c485db625639e1259dd3f", | |
| "49b3d246076241829249e651e2283b2f", | |
| "7b3fa406514848f3ad950b68417d29e3", | |
| "870df65e351444e689492d43f3ba0e32", | |
| "d31916a72fb644e594699eff0734c9cd" | |
| ] | |
| }, | |
| "outputId": "2ed2b74e-7cb0-4c58-a96c-4750a61d2fe4" | |
| }, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stderr", | |
| "text": [ | |
| "/usr/local/lib/python3.12/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: \n", | |
| "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", | |
| "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n", | |
| "You will be able to reuse this secret in all of your notebooks.\n", | |
| "Please note that authentication is recommended but still optional to access public models or datasets.\n", | |
| " warnings.warn(\n" | |
| ] | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/plain": [ | |
| "README.md: 0.00B [00:00, ?B/s]" | |
| ], | |
| "application/vnd.jupyter.widget-view+json": { | |
| "version_major": 2, | |
| "version_minor": 0, | |
| "model_id": "aa313eee96804d609757d002d5e74e56" | |
| } | |
| }, | |
| "metadata": {} | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/plain": [ | |
| "data/train-00000-of-00004.parquet: 0%| | 0.00/471M [00:00<?, ?B/s]" | |
| ], | |
| "application/vnd.jupyter.widget-view+json": { | |
| "version_major": 2, | |
| "version_minor": 0, | |
| "model_id": "a33c7f53e54c4bcda2809109dc88af6d" | |
| } | |
| }, | |
| "metadata": {} | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/plain": [ | |
| "data/train-00001-of-00004.parquet: 0%| | 0.00/475M [00:00<?, ?B/s]" | |
| ], | |
| "application/vnd.jupyter.widget-view+json": { | |
| "version_major": 2, | |
| "version_minor": 0, | |
| "model_id": "8db77ab57cc64bb6a23b2ad873a90d2b" | |
| } | |
| }, | |
| "metadata": {} | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/plain": [ | |
| "data/train-00002-of-00004.parquet: 0%| | 0.00/427M [00:00<?, ?B/s]" | |
| ], | |
| "application/vnd.jupyter.widget-view+json": { | |
| "version_major": 2, | |
| "version_minor": 0, | |
| "model_id": "9c6f7e3adbf442459a7619b50cccbad6" | |
| } | |
| }, | |
| "metadata": {} | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/plain": [ | |
| "data/train-00003-of-00004.parquet: 0%| | 0.00/494M [00:00<?, ?B/s]" | |
| ], | |
| "application/vnd.jupyter.widget-view+json": { | |
| "version_major": 2, | |
| "version_minor": 0, | |
| "model_id": "9836562b9d4a47b093d2d45df2f631ba" | |
| } | |
| }, | |
| "metadata": {} | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/plain": [ | |
| "Generating train split: 0%| | 0/2160000 [00:00<?, ? examples/s]" | |
| ], | |
| "application/vnd.jupyter.widget-view+json": { | |
| "version_major": 2, | |
| "version_minor": 0, | |
| "model_id": "60302f73bec544e89dae361010003105" | |
| } | |
| }, | |
| "metadata": {} | |
| } | |
| ], | |
| "source": [ | |
| "dataset = load_dataset(\"mssqpi/Arabic-OCR-Dataset\")" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 3, | |
| "metadata": { | |
| "id": "Kojidf-t3X33" | |
| }, | |
| "outputs": [], | |
| "source": [ | |
| "data = dataset['train'].to_pandas().sample(10000,random_state=42)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 4, | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 206 | |
| }, | |
| "id": "keRHyPqF3kMp", | |
| "outputId": "623871e4-fdd6-4d3c-f7f2-8fe095983d8f" | |
| }, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| " image text\n", | |
| "49403 {'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD... للمنظمين\n", | |
| "900283 {'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD... تأويلاته\n", | |
| "1972199 {'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD... ومعراجه\n", | |
| "907367 {'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD... كانجريلور\n", | |
| "736158 {'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD... الاثينين" | |
| ], | |
| "text/html": [ | |
| "\n", | |
| " <div id=\"df-a44df2c5-916e-4da3-a0c8-4d813ab9823e\" class=\"colab-df-container\">\n", | |
| " <div>\n", | |
| "<style scoped>\n", | |
| " .dataframe tbody tr th:only-of-type {\n", | |
| " vertical-align: middle;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe tbody tr th {\n", | |
| " vertical-align: top;\n", | |
| " }\n", | |
| "\n", | |
| " .dataframe thead th {\n", | |
| " text-align: right;\n", | |
| " }\n", | |
| "</style>\n", | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: right;\">\n", | |
| " <th></th>\n", | |
| " <th>image</th>\n", | |
| " <th>text</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <th>49403</th>\n", | |
| " <td>{'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD...</td>\n", | |
| " <td>للمنظمين</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>900283</th>\n", | |
| " <td>{'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD...</td>\n", | |
| " <td>تأويلاته</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>1972199</th>\n", | |
| " <td>{'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD...</td>\n", | |
| " <td>ومعراجه</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>907367</th>\n", | |
| " <td>{'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD...</td>\n", | |
| " <td>كانجريلور</td>\n", | |
| " </tr>\n", | |
| " <tr>\n", | |
| " <th>736158</th>\n", | |
| " <td>{'bytes': b'\\x89PNG\\r\\n\\x1a\\n\\x00\\x00\\x00\\rIHD...</td>\n", | |
| " <td>الاثينين</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>\n", | |
| "</div>\n", | |
| " <div class=\"colab-df-buttons\">\n", | |
| "\n", | |
| " <div class=\"colab-df-container\">\n", | |
| " <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a44df2c5-916e-4da3-a0c8-4d813ab9823e')\"\n", | |
| " title=\"Convert this dataframe to an interactive table.\"\n", | |
| " style=\"display:none;\">\n", | |
| "\n", | |
| " <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n", | |
| " <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n", | |
| " </svg>\n", | |
| " </button>\n", | |
| "\n", | |
| " <style>\n", | |
| " .colab-df-container {\n", | |
| " display:flex;\n", | |
| " gap: 12px;\n", | |
| " }\n", | |
| "\n", | |
| " .colab-df-convert {\n", | |
| " background-color: #E8F0FE;\n", | |
| " border: none;\n", | |
| " border-radius: 50%;\n", | |
| " cursor: pointer;\n", | |
| " display: none;\n", | |
| " fill: #1967D2;\n", | |
| " height: 32px;\n", | |
| " padding: 0 0 0 0;\n", | |
| " width: 32px;\n", | |
| " }\n", | |
| "\n", | |
| " .colab-df-convert:hover {\n", | |
| " background-color: #E2EBFA;\n", | |
| " box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n", | |
| " fill: #174EA6;\n", | |
| " }\n", | |
| "\n", | |
| " .colab-df-buttons div {\n", | |
| " margin-bottom: 4px;\n", | |
| " }\n", | |
| "\n", | |
| " [theme=dark] .colab-df-convert {\n", | |
| " background-color: #3B4455;\n", | |
| " fill: #D2E3FC;\n", | |
| " }\n", | |
| "\n", | |
| " [theme=dark] .colab-df-convert:hover {\n", | |
| " background-color: #434B5C;\n", | |
| " box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n", | |
| " filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n", | |
| " fill: #FFFFFF;\n", | |
| " }\n", | |
| " </style>\n", | |
| "\n", | |
| " <script>\n", | |
| " const buttonEl =\n", | |
| " document.querySelector('#df-a44df2c5-916e-4da3-a0c8-4d813ab9823e button.colab-df-convert');\n", | |
| " buttonEl.style.display =\n", | |
| " google.colab.kernel.accessAllowed ? 'block' : 'none';\n", | |
| "\n", | |
| " async function convertToInteractive(key) {\n", | |
| " const element = document.querySelector('#df-a44df2c5-916e-4da3-a0c8-4d813ab9823e');\n", | |
| " const dataTable =\n", | |
| " await google.colab.kernel.invokeFunction('convertToInteractive',\n", | |
| " [key], {});\n", | |
| " if (!dataTable) return;\n", | |
| "\n", | |
| " const docLinkHtml = 'Like what you see? Visit the ' +\n", | |
| " '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n", | |
| " + ' to learn more about interactive tables.';\n", | |
| " element.innerHTML = '';\n", | |
| " dataTable['output_type'] = 'display_data';\n", | |
| " await google.colab.output.renderOutput(dataTable, element);\n", | |
| " const docLink = document.createElement('div');\n", | |
| " docLink.innerHTML = docLinkHtml;\n", | |
| " element.appendChild(docLink);\n", | |
| " }\n", | |
| " </script>\n", | |
| " </div>\n", | |
| "\n", | |
| "\n", | |
| " </div>\n", | |
| " </div>\n" | |
| ], | |
| "application/vnd.google.colaboratory.intrinsic+json": { | |
| "type": "dataframe", | |
| "variable_name": "data", | |
| "summary": "{\n \"name\": \"data\",\n \"rows\": 10000,\n \"fields\": [\n {\n \"column\": \"image\",\n \"properties\": {\n \"dtype\": \"object\",\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"text\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 9637,\n \"samples\": [\n \"\\u0623\\u0648\\u063a\\u0628\\u064a\\u0646\\u0627\",\n \"\\u062a\\u062a\\u062e\\u064a\\u0644\\u0647\\u0627\",\n \"\\u0644\\u0644\\u0645\\u062f\\u0627\\u0631\\u062a\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" | |
| } | |
| }, | |
| "metadata": {}, | |
| "execution_count": 4 | |
| } | |
| ], | |
| "source": [ | |
| "data.head()" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 5, | |
| "metadata": { | |
| "id": "2laa1mfB3pVC" | |
| }, | |
| "outputs": [], | |
| "source": [ | |
| "import io\n", | |
| "from tensorflow.keras.preprocessing.sequence import pad_sequences\n", | |
| "\n", | |
| "all_texts = \"\".join(data['text'].astype(str).tolist())\n", | |
| "vocab = sorted(list(set(all_texts)))\n", | |
| "\n", | |
| "char_to_num = layers.StringLookup(vocabulary=vocab, mask_token=None)\n", | |
| "num_to_char = layers.StringLookup(vocabulary=char_to_num.get_vocabulary(), mask_token=None, invert=True)\n", | |
| "\n", | |
| "def preprocess_single_image(image_data, img_width=128, img_height=32):\n", | |
| " img_bytes = image_data['bytes']\n", | |
| " img = Image.open(io.BytesIO(img_bytes)).convert('L')\n", | |
| " img = np.array(img)\n", | |
| "\n", | |
| " img = cv2.resize(img, (img_width, img_height))\n", | |
| "\n", | |
| " img = (img / 255.0).astype(np.float32)\n", | |
| " img = img.T\n", | |
| " return np.expand_dims(img, axis=-1)\n", | |
| "\n", | |
| "max_target_len = data['text'].str.len().max()\n", | |
| "\n", | |
| "def encode_single_text(text):\n", | |
| " tokens = char_to_num(tf.strings.unicode_split(text, input_encoding=\"UTF-8\"))\n", | |
| " return tokens.numpy()" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 6, | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "j5vBWG2R46oH", | |
| "outputId": "64bca127-7177-4391-cf47-65eabdaf1096" | |
| }, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stdout", | |
| "text": [ | |
| "Processing images...\n", | |
| "Processing labels...\n", | |
| "Images Shape: (10000, 128, 32, 1)\n", | |
| "Labels Shape: (10000, 10)\n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "print(\"Processing images...\")\n", | |
| "x_train = np.array([preprocess_single_image(img) for img in data['image']])\n", | |
| "\n", | |
| "print(\"Processing labels...\")\n", | |
| "y_raw = [encode_single_text(t) for t in data['text']]\n", | |
| "y_train = pad_sequences(y_raw, maxlen=max_target_len, padding='post', value=len(vocab))\n", | |
| "\n", | |
| "print(f\"Images Shape: {x_train.shape}\")\n", | |
| "print(f\"Labels Shape: {y_train.shape}\")" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 7, | |
| "metadata": { | |
| "id": "AinStU-V5omk" | |
| }, | |
| "outputs": [], | |
| "source": [ | |
| "class CTCLayer(layers.Layer):\n", | |
| " def __init__(self, name=None, **kwargs):\n", | |
| " super().__init__(name=name, **kwargs)\n", | |
| " self.loss_fn = tf.keras.backend.ctc_batch_cost\n", | |
| "\n", | |
| " def call(self, y_true, y_pred):\n", | |
| " batch_len = tf.cast(tf.shape(y_true)[0], dtype=\"int64\")\n", | |
| " input_length = tf.cast(tf.shape(y_pred)[1], dtype=\"int64\")\n", | |
| " label_length = tf.cast(tf.shape(y_true)[1], dtype=\"int64\")\n", | |
| "\n", | |
| " input_length = input_length * tf.ones(shape=(batch_len, 1), dtype=\"int64\")\n", | |
| " label_length = label_length * tf.ones(shape=(batch_len, 1), dtype=\"int64\")\n", | |
| "\n", | |
| " loss = self.loss_fn(y_true, y_pred, input_length, label_length)\n", | |
| " self.add_loss(loss)\n", | |
| " return y_pred" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 8, | |
| "metadata": { | |
| "id": "3k4rtv6h5BWm" | |
| }, | |
| "outputs": [], | |
| "source": [ | |
| "def build_model():\n", | |
| "\n", | |
| " input_img = layers.Input(shape=(128, 32, 1), name=\"image\", dtype=\"float32\")\n", | |
| " labels = layers.Input(name=\"label\", shape=(None,), dtype=\"float32\")\n", | |
| "\n", | |
| " x = layers.Conv2D(64, (3,3), activation=\"relu\", padding=\"same\")(input_img)\n", | |
| " x = layers.MaxPooling2D((2,2))(x)\n", | |
| "\n", | |
| " x = layers.Conv2D(128, (3,3), activation=\"relu\", padding=\"same\")(x)\n", | |
| " x = layers.MaxPooling2D((2,2))(x)\n", | |
| "\n", | |
| " x = layers.Conv2D(256, (3,3), activation=\"relu\", padding=\"same\")(x)\n", | |
| " x = layers.BatchNormalization()(x)\n", | |
| "\n", | |
| " new_shape = ((128 // 4), (32 // 4) * 256)\n", | |
| " x = layers.Reshape(target_shape=new_shape)(x)\n", | |
| "\n", | |
| " x = layers.Dense(128, activation=\"relu\")(x)\n", | |
| " x = layers.Dropout(0.2)(x)\n", | |
| "\n", | |
| " x = layers.Bidirectional(layers.LSTM(128, return_sequences=True))(x)\n", | |
| " x = layers.Bidirectional(layers.LSTM(128, return_sequences=True))(x)\n", | |
| "\n", | |
| " attention = layers.Attention()([x, x])\n", | |
| " x = layers.Concatenate()([x, attention])\n", | |
| "\n", | |
| " x = layers.Dense(128, activation=\"relu\")(x)\n", | |
| "\n", | |
| " output = layers.Dense(len(char_to_num.get_vocabulary()) + 1,\n", | |
| " activation=\"softmax\")(x)\n", | |
| "\n", | |
| " output = CTCLayer(name=\"ctc_loss\")(labels, output)\n", | |
| "\n", | |
| " model = models.Model(inputs=[input_img, labels], outputs=output)\n", | |
| "\n", | |
| " model.compile(\n", | |
| " optimizer=Adam(learning_rate=0.0003)\n", | |
| " )\n", | |
| "\n", | |
| " return model" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 10, | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "Xh33RqRg5qMH", | |
| "outputId": "8dbdd621-4195-4c2a-eefa-697f7373a32c" | |
| }, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stdout", | |
| "text": [ | |
| "Epoch 1/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 50ms/step - loss: 881.9417 - val_loss: 883.1257\n", | |
| "Epoch 2/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 43ms/step - loss: 775.3694 - val_loss: 775.1326\n", | |
| "Epoch 3/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 45ms/step - loss: 715.9431 - val_loss: 733.1523\n", | |
| "Epoch 4/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 638.9011 - val_loss: 656.8591\n", | |
| "Epoch 5/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 46ms/step - loss: 574.4877 - val_loss: 569.9963\n", | |
| "Epoch 6/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 521.5745 - val_loss: 508.9180\n", | |
| "Epoch 7/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 46ms/step - loss: 471.6784 - val_loss: 472.8302\n", | |
| "Epoch 8/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 50ms/step - loss: 429.2436 - val_loss: 436.2577\n", | |
| "Epoch 9/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 389.4254 - val_loss: 396.5726\n", | |
| "Epoch 10/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 353.0599 - val_loss: 357.9424\n", | |
| "Epoch 11/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 320.4995 - val_loss: 351.1459\n", | |
| "Epoch 12/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 289.5778 - val_loss: 315.2193\n", | |
| "Epoch 13/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 47ms/step - loss: 260.7647 - val_loss: 296.4472\n", | |
| "Epoch 14/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 50ms/step - loss: 233.4187 - val_loss: 263.9807\n", | |
| "Epoch 15/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 207.1428 - val_loss: 233.6859\n", | |
| "Epoch 16/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 184.9293 - val_loss: 210.7851\n", | |
| "Epoch 17/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 163.6417 - val_loss: 206.1649\n", | |
| "Epoch 18/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 145.5503 - val_loss: 180.6810\n", | |
| "Epoch 19/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 46ms/step - loss: 129.8056 - val_loss: 172.9629\n", | |
| "Epoch 20/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 116.7864 - val_loss: 169.0902\n", | |
| "Epoch 21/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 103.5912 - val_loss: 147.9836\n", | |
| "Epoch 22/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 47ms/step - loss: 92.8651 - val_loss: 147.4090\n", | |
| "Epoch 23/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 45ms/step - loss: 83.6917 - val_loss: 130.1801\n", | |
| "Epoch 24/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 46ms/step - loss: 77.2978 - val_loss: 131.3864\n", | |
| "Epoch 25/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 51ms/step - loss: 68.6769 - val_loss: 126.9749\n", | |
| "Epoch 26/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 60.3102 - val_loss: 108.5917\n", | |
| "Epoch 27/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 50ms/step - loss: 55.9240 - val_loss: 114.5114\n", | |
| "Epoch 28/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 51ms/step - loss: 51.1986 - val_loss: 159.3892\n", | |
| "Epoch 29/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 48.0373 - val_loss: 128.9067\n", | |
| "Epoch 30/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 44.2535 - val_loss: 109.6896\n", | |
| "Epoch 31/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 40.3403 - val_loss: 107.8465\n", | |
| "Epoch 32/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 37.2081 - val_loss: 110.0865\n", | |
| "Epoch 33/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 47ms/step - loss: 35.4945 - val_loss: 99.0449\n", | |
| "Epoch 34/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 45ms/step - loss: 30.5365 - val_loss: 91.1200\n", | |
| "Epoch 35/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 47ms/step - loss: 29.9046 - val_loss: 111.7029\n", | |
| "Epoch 36/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 29.0176 - val_loss: 93.5697\n", | |
| "Epoch 37/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 47ms/step - loss: 26.6574 - val_loss: 101.8789\n", | |
| "Epoch 38/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 47ms/step - loss: 24.9677 - val_loss: 89.0171\n", | |
| "Epoch 39/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 47ms/step - loss: 24.0240 - val_loss: 104.7533\n", | |
| "Epoch 40/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 45ms/step - loss: 22.2763 - val_loss: 91.9691\n", | |
| "Epoch 41/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 47ms/step - loss: 20.7392 - val_loss: 106.4075\n", | |
| "Epoch 42/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 51ms/step - loss: 20.2009 - val_loss: 85.6161\n", | |
| "Epoch 43/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 19.7458 - val_loss: 87.2551\n", | |
| "Epoch 44/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 18.4277 - val_loss: 86.2561\n", | |
| "Epoch 45/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 51ms/step - loss: 16.7157 - val_loss: 82.9311\n", | |
| "Epoch 46/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 47ms/step - loss: 15.2934 - val_loss: 83.4012\n", | |
| "Epoch 47/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 46ms/step - loss: 16.4429 - val_loss: 86.5792\n", | |
| "Epoch 48/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 47ms/step - loss: 14.7575 - val_loss: 118.4566\n", | |
| "Epoch 49/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m21s\u001b[0m 47ms/step - loss: 15.2590 - val_loss: 97.2995\n", | |
| "Epoch 50/50\n", | |
| "\u001b[1m250/250\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 51ms/step - loss: 13.1351 - val_loss: 89.7937\n" | |
| ] | |
| }, | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "<keras.src.callbacks.history.History at 0x7c6adabb7680>" | |
| ] | |
| }, | |
| "metadata": {}, | |
| "execution_count": 10 | |
| } | |
| ], | |
| "source": [ | |
| "from tensorflow.keras.preprocessing.sequence import pad_sequences\n", | |
| "\n", | |
| "encoded_labels = [char_to_num(tf.strings.unicode_split(t, \"UTF-8\")).numpy() for t in data['text']]\n", | |
| "\n", | |
| "max_label_len = max([len(l) for l in encoded_labels])\n", | |
| "train_labels = pad_sequences(encoded_labels, maxlen=max_label_len, padding='post', value=0)\n", | |
| "\n", | |
| "train_images = np.array([preprocess_single_image(img) for img in data['image']])\n", | |
| "\n", | |
| "model = build_model()\n", | |
| "model.fit(\n", | |
| " x=[train_images, train_labels],\n", | |
| " y=np.zeros(len(train_images)),\n", | |
| " batch_size=32,\n", | |
| " epochs=50,\n", | |
| " validation_split=0.2\n", | |
| ")" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 11, | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "0O_g9S8XPc_3", | |
| "outputId": "9890f71d-cf3d-4a33-d28b-ac34abc27b74" | |
| }, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stderr", | |
| "text": [ | |
| "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "model.save('OCR_model_updated.h5')" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 12, | |
| "metadata": { | |
| "id": "0xCtXCwmR_Tn" | |
| }, | |
| "outputs": [], | |
| "source": [ | |
| "model.save('OCR_model_updated.keras')" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "source": [ | |
| "def decode_batch_predictions(pred):\n", | |
| " input_len = np.ones(pred.shape[0]) * pred.shape[1]\n", | |
| " results = tf.keras.backend.ctc_decode(pred, input_length=input_len, greedy=True)[0][0]\n", | |
| " output_text = []\n", | |
| " for res in results.numpy():\n", | |
| " res = res[res != -1]\n", | |
| " decoded_string = tf.strings.reduce_join(num_to_char(res)).numpy().decode('utf-8')\n", | |
| " cleaned_string = decoded_string.replace('[UNK]', '')\n", | |
| " output_text.append(cleaned_string)\n", | |
| " return output_text\n", | |
| "\n", | |
| "\n", | |
| "image_path = '/content/mixmedia-01231056Ox6V8.png'\n", | |
| "\n", | |
| "with open(image_path, 'rb') as f:\n", | |
| " img_bytes = f.read()\n", | |
| "image_data = {'bytes': img_bytes}\n", | |
| "\n", | |
| "preprocessed_image = preprocess_single_image(image_data)\n", | |
| "\n", | |
| "input_image_batch = np.expand_dims(preprocessed_image, axis=0)\n", | |
| "\n", | |
| "\n", | |
| "output_layer_index = None\n", | |
| "for i, layer in enumerate(model.layers):\n", | |
| " if isinstance(layer, CTCLayer):\n", | |
| "\n", | |
| " output_layer_index = i - 1\n", | |
| " break\n", | |
| "\n", | |
| "if output_layer_index is not None:\n", | |
| " prediction_model_output = model.layers[output_layer_index].output\n", | |
| " prediction_model = models.Model(inputs=model.get_layer('image').output, outputs=prediction_model_output)\n", | |
| "else:\n", | |
| " raise ValueError(\"CTCLayer not found in the model.\")\n", | |
| "\n", | |
| "predictions = prediction_model.predict(input_image_batch)\n", | |
| "\n", | |
| "decoded_text = decode_batch_predictions(predictions)\n", | |
| "\n", | |
| "print(f\"Predicted text for {image_path}: {decoded_text[0]}\")" | |
| ], | |
| "metadata": { | |
| "colab": { | |
| "base_uri": "https://localhost:8080/" | |
| }, | |
| "id": "IG56rLqKl9Jo", | |
| "outputId": "7e248e84-3268-4407-8136-e2b69a9a7165" | |
| }, | |
| "execution_count": 18, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "name": "stdout", | |
| "text": [ | |
| "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1s/step\n", | |
| "Predicted text for /content/mixmedia-01231056Ox6V8.png: ثيثغ\n" | |
| ] | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "source": [], | |
| "metadata": { | |
| "id": "I_8g3at9m-UP" | |
| }, | |
| "execution_count": null, | |
| "outputs": [] | |
| } | |
| ], | |
| "metadata": { | |
| "accelerator": "GPU", | |
| "colab": { | |
| "gpuType": "T4", | |
| "provenance": [] | |
| }, | |
| "kernelspec": { | |
| "display_name": "Python 3", | |
| "name": "python3" | |
| }, | |
| "language_info": { | |
| "name": "python" | |
| }, | |
| "widgets": { | |
| "application/vnd.jupyter.widget-state+json": { | |
| "aa313eee96804d609757d002d5e74e56": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HBoxModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HBoxModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HBoxView", | |
| "box_style": "", | |
| "children": [ | |
| "IPY_MODEL_3470ee488cfa4e49b06f8a87f3f7b04b", | |
| "IPY_MODEL_820198f3b97a47ed8fe4df52e52784db", | |
| "IPY_MODEL_c4d52890dbc645b4839eca04f04dc095" | |
| ], | |
| "layout": "IPY_MODEL_58dad371f9b1418b96c68fce92aa7d91" | |
| } | |
| }, | |
| "3470ee488cfa4e49b06f8a87f3f7b04b": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_7302cde51c014e3ba4f53e4544027416", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_4ef9183414634faca637707777ad37ab", | |
| "value": "README.md: " | |
| } | |
| }, | |
| "820198f3b97a47ed8fe4df52e52784db": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "FloatProgressModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "FloatProgressModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "ProgressView", | |
| "bar_style": "success", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_9844e8a0f4204c0fa3dada598d513bb4", | |
| "max": 1, | |
| "min": 0, | |
| "orientation": "horizontal", | |
| "style": "IPY_MODEL_3379384ba9cb4557a8ba902f4ea9fb8e", | |
| "value": 1 | |
| } | |
| }, | |
| "c4d52890dbc645b4839eca04f04dc095": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_0fdb6b8ca2fa4336b7062b8527680565", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_c2c17f4cac3b491c9608fc46954393c2", | |
| "value": " 1.77k/? [00:00<00:00, 136kB/s]" | |
| } | |
| }, | |
| "58dad371f9b1418b96c68fce92aa7d91": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "7302cde51c014e3ba4f53e4544027416": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "4ef9183414634faca637707777ad37ab": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "9844e8a0f4204c0fa3dada598d513bb4": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": "20px" | |
| } | |
| }, | |
| "3379384ba9cb4557a8ba902f4ea9fb8e": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "ProgressStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "ProgressStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "bar_color": null, | |
| "description_width": "" | |
| } | |
| }, | |
| "0fdb6b8ca2fa4336b7062b8527680565": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "c2c17f4cac3b491c9608fc46954393c2": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "a33c7f53e54c4bcda2809109dc88af6d": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HBoxModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HBoxModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HBoxView", | |
| "box_style": "", | |
| "children": [ | |
| "IPY_MODEL_e4501b4aeb864b69a049ce3555801f3a", | |
| "IPY_MODEL_e4539eb73176411cbaf79f2c9e23ee77", | |
| "IPY_MODEL_76308a0c9e0641caa60b8cacc54444f2" | |
| ], | |
| "layout": "IPY_MODEL_4b0dca03899841608c8776972970a757" | |
| } | |
| }, | |
| "e4501b4aeb864b69a049ce3555801f3a": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_9426b0161fff4cd5a73e94933e53cd1b", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_3458ecb921314ac9847db8fa8cef72c4", | |
| "value": "data/train-00000-of-00004.parquet: 100%" | |
| } | |
| }, | |
| "e4539eb73176411cbaf79f2c9e23ee77": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "FloatProgressModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "FloatProgressModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "ProgressView", | |
| "bar_style": "success", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_b4e82788b6854359a040930a46feb58f", | |
| "max": 471207255, | |
| "min": 0, | |
| "orientation": "horizontal", | |
| "style": "IPY_MODEL_f3b82a043a8244579e87b1c94111dd64", | |
| "value": 471207255 | |
| } | |
| }, | |
| "76308a0c9e0641caa60b8cacc54444f2": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_4b236b923d514089b27e0655322ab30a", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_70bc59cd67e84c2d8b74ab066080c118", | |
| "value": " 471M/471M [00:09<00:00, 283MB/s]" | |
| } | |
| }, | |
| "4b0dca03899841608c8776972970a757": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "9426b0161fff4cd5a73e94933e53cd1b": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "3458ecb921314ac9847db8fa8cef72c4": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "b4e82788b6854359a040930a46feb58f": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "f3b82a043a8244579e87b1c94111dd64": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "ProgressStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "ProgressStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "bar_color": null, | |
| "description_width": "" | |
| } | |
| }, | |
| "4b236b923d514089b27e0655322ab30a": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "70bc59cd67e84c2d8b74ab066080c118": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "8db77ab57cc64bb6a23b2ad873a90d2b": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HBoxModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HBoxModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HBoxView", | |
| "box_style": "", | |
| "children": [ | |
| "IPY_MODEL_b2b24d1591a347fcab06f7c7af8f2b71", | |
| "IPY_MODEL_acf47046a0c04c839e0f31d073eba3de", | |
| "IPY_MODEL_78dd58c598164df29cc00172d1369219" | |
| ], | |
| "layout": "IPY_MODEL_4e69090fdf124637906eaa5c4895d702" | |
| } | |
| }, | |
| "b2b24d1591a347fcab06f7c7af8f2b71": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_52e3fcd92ff4483e9e80f2cd08d52e4c", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_5b090e4fe38740b7994ea24a4faba077", | |
| "value": "data/train-00001-of-00004.parquet: 100%" | |
| } | |
| }, | |
| "acf47046a0c04c839e0f31d073eba3de": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "FloatProgressModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "FloatProgressModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "ProgressView", | |
| "bar_style": "success", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_0a60d3dddd804e6b936ef34885ff2493", | |
| "max": 474847238, | |
| "min": 0, | |
| "orientation": "horizontal", | |
| "style": "IPY_MODEL_14389181189a4542ba77d687489e75c4", | |
| "value": 474847238 | |
| } | |
| }, | |
| "78dd58c598164df29cc00172d1369219": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_9c8cbfed8d1b4f1499e94597fccce5e4", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_b52322ee82834a3884b732cbe2c1a80a", | |
| "value": " 475M/475M [00:07<00:00, 184MB/s]" | |
| } | |
| }, | |
| "4e69090fdf124637906eaa5c4895d702": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "52e3fcd92ff4483e9e80f2cd08d52e4c": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "5b090e4fe38740b7994ea24a4faba077": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "0a60d3dddd804e6b936ef34885ff2493": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "14389181189a4542ba77d687489e75c4": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "ProgressStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "ProgressStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "bar_color": null, | |
| "description_width": "" | |
| } | |
| }, | |
| "9c8cbfed8d1b4f1499e94597fccce5e4": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "b52322ee82834a3884b732cbe2c1a80a": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "9c6f7e3adbf442459a7619b50cccbad6": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HBoxModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HBoxModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HBoxView", | |
| "box_style": "", | |
| "children": [ | |
| "IPY_MODEL_7811c59647d140c38c15045434ece00d", | |
| "IPY_MODEL_bc392bd61ca94f359b65a9a76de4abb6", | |
| "IPY_MODEL_31928153f8ba46f8892451b043486a5a" | |
| ], | |
| "layout": "IPY_MODEL_f22a20011692425996bf25f5b89338a5" | |
| } | |
| }, | |
| "7811c59647d140c38c15045434ece00d": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_5116ae03451f4576b2108e39e431b518", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_d60aba9eec7f4c0eb2e05a7148d6eb5d", | |
| "value": "data/train-00002-of-00004.parquet: 100%" | |
| } | |
| }, | |
| "bc392bd61ca94f359b65a9a76de4abb6": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "FloatProgressModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "FloatProgressModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "ProgressView", | |
| "bar_style": "success", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_c6409b87ad2a4146b9e06dbaf1383f10", | |
| "max": 427004454, | |
| "min": 0, | |
| "orientation": "horizontal", | |
| "style": "IPY_MODEL_14ee8f727ed3426890f1f76d629d28ba", | |
| "value": 427004454 | |
| } | |
| }, | |
| "31928153f8ba46f8892451b043486a5a": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_53cc6ca8114f4c8f97ff963511f188cd", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_0d63ed78c4da4a68afbfab605ef0a57c", | |
| "value": " 427M/427M [00:06<00:00, 105MB/s]" | |
| } | |
| }, | |
| "f22a20011692425996bf25f5b89338a5": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "5116ae03451f4576b2108e39e431b518": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "d60aba9eec7f4c0eb2e05a7148d6eb5d": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "c6409b87ad2a4146b9e06dbaf1383f10": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "14ee8f727ed3426890f1f76d629d28ba": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "ProgressStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "ProgressStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "bar_color": null, | |
| "description_width": "" | |
| } | |
| }, | |
| "53cc6ca8114f4c8f97ff963511f188cd": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "0d63ed78c4da4a68afbfab605ef0a57c": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "9836562b9d4a47b093d2d45df2f631ba": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HBoxModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HBoxModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HBoxView", | |
| "box_style": "", | |
| "children": [ | |
| "IPY_MODEL_924c05e23f114f06a966125d94451e47", | |
| "IPY_MODEL_41e7d783bb7d4db7963bfcbd6faf3711", | |
| "IPY_MODEL_ac3e4bc7548e45729a34c70224001201" | |
| ], | |
| "layout": "IPY_MODEL_abfe72f663a0424eba43345ac948cc36" | |
| } | |
| }, | |
| "924c05e23f114f06a966125d94451e47": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_8a7e7f5448e84d0383695841859ac083", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_541620a7831145bb9fe57982e62ba706", | |
| "value": "data/train-00003-of-00004.parquet: 100%" | |
| } | |
| }, | |
| "41e7d783bb7d4db7963bfcbd6faf3711": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "FloatProgressModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "FloatProgressModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "ProgressView", | |
| "bar_style": "success", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_3ec8503dfb0f44e184e94aa3fd8fa2fd", | |
| "max": 493761857, | |
| "min": 0, | |
| "orientation": "horizontal", | |
| "style": "IPY_MODEL_4f00f0b7c5de45cc96a0c88f9c513ec7", | |
| "value": 493761857 | |
| } | |
| }, | |
| "ac3e4bc7548e45729a34c70224001201": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_6a5f7619e80e429ca87000da6b874f96", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_8b167c6e50bf43efab4de8d4289adf33", | |
| "value": " 494M/494M [00:06<00:00, 128MB/s]" | |
| } | |
| }, | |
| "abfe72f663a0424eba43345ac948cc36": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "8a7e7f5448e84d0383695841859ac083": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "541620a7831145bb9fe57982e62ba706": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "3ec8503dfb0f44e184e94aa3fd8fa2fd": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "4f00f0b7c5de45cc96a0c88f9c513ec7": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "ProgressStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "ProgressStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "bar_color": null, | |
| "description_width": "" | |
| } | |
| }, | |
| "6a5f7619e80e429ca87000da6b874f96": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "8b167c6e50bf43efab4de8d4289adf33": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "60302f73bec544e89dae361010003105": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HBoxModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HBoxModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HBoxView", | |
| "box_style": "", | |
| "children": [ | |
| "IPY_MODEL_b838344d3ac7419e96905f99208bf3b5", | |
| "IPY_MODEL_f8e49d33d8b446028190b90151a7c92e", | |
| "IPY_MODEL_f3bcf8f9b44441c8bb3897260040dabb" | |
| ], | |
| "layout": "IPY_MODEL_c436a0a10ade41c6bcedc484caf96383" | |
| } | |
| }, | |
| "b838344d3ac7419e96905f99208bf3b5": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_d54a970092594aa99814a9da0fbdf487", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_e1bd0176b16c485db625639e1259dd3f", | |
| "value": "Generating train split: 100%" | |
| } | |
| }, | |
| "f8e49d33d8b446028190b90151a7c92e": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "FloatProgressModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "FloatProgressModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "ProgressView", | |
| "bar_style": "success", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_49b3d246076241829249e651e2283b2f", | |
| "max": 2160000, | |
| "min": 0, | |
| "orientation": "horizontal", | |
| "style": "IPY_MODEL_7b3fa406514848f3ad950b68417d29e3", | |
| "value": 2160000 | |
| } | |
| }, | |
| "f3bcf8f9b44441c8bb3897260040dabb": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "HTMLModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_dom_classes": [], | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "HTMLModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/controls", | |
| "_view_module_version": "1.5.0", | |
| "_view_name": "HTMLView", | |
| "description": "", | |
| "description_tooltip": null, | |
| "layout": "IPY_MODEL_870df65e351444e689492d43f3ba0e32", | |
| "placeholder": "", | |
| "style": "IPY_MODEL_d31916a72fb644e594699eff0734c9cd", | |
| "value": " 2160000/2160000 [00:14<00:00, 248289.55 examples/s]" | |
| } | |
| }, | |
| "c436a0a10ade41c6bcedc484caf96383": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "d54a970092594aa99814a9da0fbdf487": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "e1bd0176b16c485db625639e1259dd3f": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| }, | |
| "49b3d246076241829249e651e2283b2f": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "7b3fa406514848f3ad950b68417d29e3": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "ProgressStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "ProgressStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "bar_color": null, | |
| "description_width": "" | |
| } | |
| }, | |
| "870df65e351444e689492d43f3ba0e32": { | |
| "model_module": "@jupyter-widgets/base", | |
| "model_name": "LayoutModel", | |
| "model_module_version": "1.2.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/base", | |
| "_model_module_version": "1.2.0", | |
| "_model_name": "LayoutModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "LayoutView", | |
| "align_content": null, | |
| "align_items": null, | |
| "align_self": null, | |
| "border": null, | |
| "bottom": null, | |
| "display": null, | |
| "flex": null, | |
| "flex_flow": null, | |
| "grid_area": null, | |
| "grid_auto_columns": null, | |
| "grid_auto_flow": null, | |
| "grid_auto_rows": null, | |
| "grid_column": null, | |
| "grid_gap": null, | |
| "grid_row": null, | |
| "grid_template_areas": null, | |
| "grid_template_columns": null, | |
| "grid_template_rows": null, | |
| "height": null, | |
| "justify_content": null, | |
| "justify_items": null, | |
| "left": null, | |
| "margin": null, | |
| "max_height": null, | |
| "max_width": null, | |
| "min_height": null, | |
| "min_width": null, | |
| "object_fit": null, | |
| "object_position": null, | |
| "order": null, | |
| "overflow": null, | |
| "overflow_x": null, | |
| "overflow_y": null, | |
| "padding": null, | |
| "right": null, | |
| "top": null, | |
| "visibility": null, | |
| "width": null | |
| } | |
| }, | |
| "d31916a72fb644e594699eff0734c9cd": { | |
| "model_module": "@jupyter-widgets/controls", | |
| "model_name": "DescriptionStyleModel", | |
| "model_module_version": "1.5.0", | |
| "state": { | |
| "_model_module": "@jupyter-widgets/controls", | |
| "_model_module_version": "1.5.0", | |
| "_model_name": "DescriptionStyleModel", | |
| "_view_count": null, | |
| "_view_module": "@jupyter-widgets/base", | |
| "_view_module_version": "1.2.0", | |
| "_view_name": "StyleView", | |
| "description_width": "" | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "nbformat": 4, | |
| "nbformat_minor": 0 | |
| } |
Xet Storage Details
- Size:
- 114 kB
- Xet hash:
- a2ab6ba3320ef3f81f5f98f52bc6b13550bdd7e6a2f624ae44691b88c6cb58e9
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.