{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1c550b9b-ab70-46a5-a584-29a0d3ae31ee",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Defaulting to user installation because normal site-packages is not writeable\n",
      "Collecting gradio\n",
      "  Using cached gradio-4.41.0-py3-none-any.whl.metadata (15 kB)\n",
      "Collecting aiofiles<24.0,>=22.0 (from gradio)\n",
      "  Using cached aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 kB)\n",
      "Requirement already satisfied: anyio<5.0,>=3.0 in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (4.4.0)\n",
      "Collecting fastapi (from gradio)\n",
      "  Using cached fastapi-0.112.1-py3-none-any.whl.metadata (27 kB)\n",
      "Collecting ffmpy (from gradio)\n",
      "  Using cached ffmpy-0.4.0-py3-none-any.whl.metadata (2.9 kB)\n",
      "Collecting gradio-client==1.3.0 (from gradio)\n",
      "  Using cached gradio_client-1.3.0-py3-none-any.whl.metadata (7.1 kB)\n",
      "Requirement already satisfied: httpx>=0.24.1 in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (0.27.0)\n",
      "Collecting huggingface-hub>=0.19.3 (from gradio)\n",
      "  Using cached huggingface_hub-0.24.5-py3-none-any.whl.metadata (13 kB)\n",
      "Collecting importlib-resources<7.0,>=1.3 (from gradio)\n",
      "  Using cached importlib_resources-6.4.3-py3-none-any.whl.metadata (3.9 kB)\n",
      "Requirement already satisfied: jinja2<4.0 in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (3.1.4)\n",
      "Requirement already satisfied: markupsafe~=2.0 in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (2.1.5)\n",
      "Requirement already satisfied: matplotlib~=3.0 in /usr/lib/python3/dist-packages (from gradio) (3.5.1)\n",
      "Requirement already satisfied: numpy<3.0,>=1.0 in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (1.26.4)\n",
      "Collecting orjson~=3.0 (from gradio)\n",
      "  Using cached orjson-3.10.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (50 kB)\n",
      "Requirement already satisfied: packaging in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (24.0)\n",
      "Requirement already satisfied: pandas<3.0,>=1.0 in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (2.2.2)\n",
      "Requirement already satisfied: pillow<11.0,>=8.0 in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (10.3.0)\n",
      "Collecting pydantic>=2.0 (from gradio)\n",
      "  Using cached pydantic-2.8.2-py3-none-any.whl.metadata (125 kB)\n",
      "Collecting pydub (from gradio)\n",
      "  Using cached pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
      "Collecting python-multipart>=0.0.9 (from gradio)\n",
      "  Using cached python_multipart-0.0.9-py3-none-any.whl.metadata (2.5 kB)\n",
      "Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/lib/python3/dist-packages (from gradio) (5.4.1)\n",
      "Collecting ruff>=0.2.2 (from gradio)\n",
      "  Using cached ruff-0.6.1-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (25 kB)\n",
      "Collecting semantic-version~=2.0 (from gradio)\n",
      "  Using cached semantic_version-2.10.0-py2.py3-none-any.whl.metadata (9.7 kB)\n",
      "Collecting tomlkit==0.12.0 (from gradio)\n",
      "  Using cached tomlkit-0.12.0-py3-none-any.whl.metadata (2.7 kB)\n",
      "Collecting typer<1.0,>=0.12 (from gradio)\n",
      "  Using cached typer-0.12.4-py3-none-any.whl.metadata (15 kB)\n",
      "Requirement already satisfied: typing-extensions~=4.0 in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (4.12.1)\n",
      "Requirement already satisfied: urllib3~=2.0 in /home/obai33/.local/lib/python3.10/site-packages (from gradio) (2.2.1)\n",
      "Collecting uvicorn>=0.14.0 (from gradio)\n",
      "  Using cached uvicorn-0.30.6-py3-none-any.whl.metadata (6.6 kB)\n",
      "Requirement already satisfied: fsspec in /home/obai33/.local/lib/python3.10/site-packages (from gradio-client==1.3.0->gradio) (2024.5.0)\n",
      "Collecting websockets<13.0,>=10.0 (from gradio-client==1.3.0->gradio)\n",
      "  Using cached websockets-12.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.6 kB)\n",
      "Requirement already satisfied: idna>=2.8 in /home/obai33/.local/lib/python3.10/site-packages (from anyio<5.0,>=3.0->gradio) (3.7)\n",
      "Requirement already satisfied: sniffio>=1.1 in /home/obai33/.local/lib/python3.10/site-packages (from anyio<5.0,>=3.0->gradio) (1.3.1)\n",
      "Requirement already satisfied: exceptiongroup>=1.0.2 in /home/obai33/.local/lib/python3.10/site-packages (from anyio<5.0,>=3.0->gradio) (1.2.1)\n",
      "Requirement already satisfied: certifi in /home/obai33/.local/lib/python3.10/site-packages (from httpx>=0.24.1->gradio) (2024.6.2)\n",
      "Requirement already satisfied: httpcore==1.* in /home/obai33/.local/lib/python3.10/site-packages (from httpx>=0.24.1->gradio) (1.0.5)\n",
      "Requirement already satisfied: h11<0.15,>=0.13 in /home/obai33/.local/lib/python3.10/site-packages (from httpcore==1.*->httpx>=0.24.1->gradio) (0.14.0)\n",
      "Requirement already satisfied: filelock in /home/obai33/.local/lib/python3.10/site-packages (from huggingface-hub>=0.19.3->gradio) (3.14.0)\n",
      "Requirement already satisfied: requests in /home/obai33/.local/lib/python3.10/site-packages (from huggingface-hub>=0.19.3->gradio) (2.32.3)\n",
      "Requirement already satisfied: tqdm>=4.42.1 in /home/obai33/.local/lib/python3.10/site-packages (from huggingface-hub>=0.19.3->gradio) (4.66.4)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /home/obai33/.local/lib/python3.10/site-packages (from pandas<3.0,>=1.0->gradio) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /usr/lib/python3/dist-packages (from pandas<3.0,>=1.0->gradio) (2022.1)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /home/obai33/.local/lib/python3.10/site-packages (from pandas<3.0,>=1.0->gradio) (2024.1)\n",
      "Collecting annotated-types>=0.4.0 (from pydantic>=2.0->gradio)\n",
      "  Using cached annotated_types-0.7.0-py3-none-any.whl.metadata (15 kB)\n",
      "Collecting pydantic-core==2.20.1 (from pydantic>=2.0->gradio)\n",
      "  Using cached pydantic_core-2.20.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.6 kB)\n",
      "Collecting click>=8.0.0 (from typer<1.0,>=0.12->gradio)\n",
      "  Using cached click-8.1.7-py3-none-any.whl.metadata (3.0 kB)\n",
      "Collecting shellingham>=1.3.0 (from typer<1.0,>=0.12->gradio)\n",
      "  Using cached shellingham-1.5.4-py2.py3-none-any.whl.metadata (3.5 kB)\n",
      "Requirement already satisfied: rich>=10.11.0 in /home/obai33/.local/lib/python3.10/site-packages (from typer<1.0,>=0.12->gradio) (13.7.1)\n",
      "Collecting starlette<0.39.0,>=0.37.2 (from fastapi->gradio)\n",
      "  Using cached starlette-0.38.2-py3-none-any.whl.metadata (5.9 kB)\n",
      "Requirement already satisfied: six>=1.5 in /usr/lib/python3/dist-packages (from python-dateutil>=2.8.2->pandas<3.0,>=1.0->gradio) (1.16.0)\n",
      "Requirement already satisfied: markdown-it-py>=2.2.0 in /home/obai33/.local/lib/python3.10/site-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /home/obai33/.local/lib/python3.10/site-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.18.0)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /home/obai33/.local/lib/python3.10/site-packages (from requests->huggingface-hub>=0.19.3->gradio) (3.3.2)\n",
      "Requirement already satisfied: mdurl~=0.1 in /home/obai33/.local/lib/python3.10/site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
      "Downloading gradio-4.41.0-py3-none-any.whl (12.6 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.6/12.6 MB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading gradio_client-1.3.0-py3-none-any.whl (318 kB)\n",
      "Downloading tomlkit-0.12.0-py3-none-any.whl (37 kB)\n",
      "Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
      "Downloading huggingface_hub-0.24.5-py3-none-any.whl (417 kB)\n",
      "Downloading importlib_resources-6.4.3-py3-none-any.whl (35 kB)\n",
      "Downloading orjson-3.10.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (141 kB)\n",
      "Downloading pydantic-2.8.2-py3-none-any.whl (423 kB)\n",
      "Downloading pydantic_core-2.20.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.1 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m8.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hDownloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n",
      "Downloading ruff-0.6.1-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (10.2 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.2/10.2 MB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hDownloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
      "Downloading typer-0.12.4-py3-none-any.whl (47 kB)\n",
      "Downloading uvicorn-0.30.6-py3-none-any.whl (62 kB)\n",
      "Downloading fastapi-0.112.1-py3-none-any.whl (93 kB)\n",
      "Downloading ffmpy-0.4.0-py3-none-any.whl (5.8 kB)\n",
      "Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
      "Downloading annotated_types-0.7.0-py3-none-any.whl (13 kB)\n",
      "Downloading click-8.1.7-py3-none-any.whl (97 kB)\n",
      "Downloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)\n",
      "Downloading starlette-0.38.2-py3-none-any.whl (72 kB)\n",
      "Downloading websockets-12.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (130 kB)\n",
      "Installing collected packages: pydub, websockets, tomlkit, shellingham, semantic-version, ruff, python-multipart, pydantic-core, orjson, importlib-resources, ffmpy, click, annotated-types, aiofiles, uvicorn, starlette, pydantic, huggingface-hub, typer, gradio-client, fastapi, gradio\n",
      "Successfully installed aiofiles-23.2.1 annotated-types-0.7.0 click-8.1.7 fastapi-0.112.1 ffmpy-0.4.0 gradio-4.41.0 gradio-client-1.3.0 huggingface-hub-0.24.5 importlib-resources-6.4.3 orjson-3.10.7 pydantic-2.8.2 pydantic-core-2.20.1 pydub-0.25.1 python-multipart-0.0.9 ruff-0.6.1 semantic-version-2.10.0 shellingham-1.5.4 starlette-0.38.2 tomlkit-0.12.0 typer-0.12.4 uvicorn-0.30.6 websockets-12.0\n"
     ]
    }
   ],
   "source": [
    "!pip install gradio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "c850d5ae-5d43-45fb-91cc-084427440a97",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import torch.nn.functional as F\n",
    "import torchvision\n",
    "import matplotlib.pyplot as plt\n",
    "import zipfile\n",
    "import os\n",
    "import gradio as gr\n",
    "from PIL import Image\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "c3d9ca4d-fb14-495e-b405-8a964ecc9a51",
   "metadata": {},
   "outputs": [],
   "source": [
    "CHARS = \"~=\" + \" abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789,.'-!?:;\\\"\"\n",
    "BLANK = 0\n",
    "PAD = 1\n",
    "CHARS_DICT = {c: i for i, c in enumerate(CHARS)}\n",
    "TEXTLEN = 30\n",
    "\n",
    "tokens_list = list(CHARS_DICT.keys())\n",
    "silence_token = '|'\n",
    "\n",
    "if silence_token not in tokens_list:\n",
    "    tokens_list.append(silence_token)\n",
    "\n",
    "\n",
    "def fit_picture(img):\n",
    "    target_height = 32\n",
    "    target_width = 400\n",
    "    \n",
    "    # Calculate resize dimensions\n",
    "    aspect_ratio = img.width / img.height\n",
    "    if aspect_ratio > (target_width / target_height):\n",
    "        resize_width = target_width\n",
    "        resize_height = int(target_width / aspect_ratio)\n",
    "    else:\n",
    "        resize_height = target_height\n",
    "        resize_width = int(target_height * aspect_ratio)\n",
    "    \n",
    "    # Resize transformation\n",
    "    resize_transform = transforms.Resize((resize_height, resize_width))\n",
    "    \n",
    "    # Pad transformation\n",
    "    padding_height = (target_height - resize_height) if target_height > resize_height else 0\n",
    "    padding_width = (target_width - resize_width) if target_width > resize_width else 0\n",
    "    pad_transform = transforms.Pad((0, 0, padding_width, padding_height), fill=0, padding_mode='constant')\n",
    "    \n",
    "    transform = torchvision.transforms.Compose([\n",
    "        torchvision.transforms.Grayscale(num_output_channels = 1),\n",
    "        torchvision.transforms.ToTensor(),\n",
    "        torchvision.transforms.Normalize(0.5,0.5),\n",
    "        resize_transform,\n",
    "        pad_transform\n",
    "    ])\n",
    "\n",
    "    fin_img = transform(img)\n",
    "    return fin_img\n",
    "\n",
    "def load_model(filename):\n",
    "    data = torch.load(filename)\n",
    "    recognizer.load_state_dict(data[\"recognizer\"])\n",
    "    optimizer.load_state_dict(data[\"optimizer\"])\n",
    "\n",
    "def ctc_decode_sequence(seq):\n",
    "    \"\"\"Removes blanks and repetitions from the sequence.\"\"\"\n",
    "    ret = []\n",
    "    prev = BLANK\n",
    "    for x in seq:\n",
    "        if prev != BLANK and prev != x:\n",
    "            ret.append(prev)\n",
    "        prev = x\n",
    "    if seq[-1] == 66:\n",
    "        ret.append(66)\n",
    "    return ret\n",
    "\n",
    "def ctc_decode(codes):\n",
    "    \"\"\"Decode a batch of sequences.\"\"\"\n",
    "    ret = []\n",
    "    for cs in codes.T:\n",
    "        ret.append(ctc_decode_sequence(cs))\n",
    "    return ret\n",
    "\n",
    "\n",
    "def decode_text(codes):\n",
    "  chars = [CHARS[c] for c in codes]\n",
    "  return ''.join(chars)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "6722e370-e7df-4efe-aa9d-e9436d3cc08e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Device: cuda\n"
     ]
    }
   ],
   "source": [
    "class Residual(torch.nn.Module):\n",
    "    def __init__(self, in_channels, out_channels, stride, pdrop = 0.2):\n",
    "        super().__init__()\n",
    "        self.conv1 = torch.nn.Conv2d(in_channels, out_channels, 3, stride, 1)\n",
    "        self.bn1 = torch.nn.BatchNorm2d(out_channels)\n",
    "        self.conv2 = torch.nn.Conv2d(out_channels, out_channels, 3, 1, 1)\n",
    "        self.bn2 = torch.nn.BatchNorm2d(out_channels)\n",
    "        if in_channels != out_channels or stride != 1:\n",
    "          self.skip = torch.nn.Conv2d(in_channels, out_channels, 1, stride, 0)\n",
    "        else:\n",
    "          self.skip = torch.nn.Identity()\n",
    "        self.dropout = torch.nn.Dropout2d(pdrop)\n",
    "\n",
    "    def forward(self, x):\n",
    "        y = torch.nn.functional.relu(self.bn1(self.conv1(x)))\n",
    "        y = torch.nn.functional.relu(self.bn2(self.conv2(y)) + self.skip(x))\n",
    "        y = self.dropout(y)\n",
    "        return y\n",
    "        \n",
    "class TextRecognizer(torch.nn.Module):\n",
    "    def __init__(self, labels):\n",
    "        super().__init__()\n",
    "        self.feature_extractor = torch.nn.Sequential(\n",
    "            Residual(1, 32, 1),\n",
    "            Residual(32, 32, 2),\n",
    "            Residual(32, 32, 1),\n",
    "            Residual(32, 64, 2),\n",
    "            Residual(64, 64, 1),\n",
    "            Residual(64, 128, (2,1)),\n",
    "            Residual(128, 128, 1),\n",
    "            Residual(128, 128, (2,1)),\n",
    "            Residual(128, 128, (2,1)),\n",
    "        )\n",
    "        self.recurrent = torch.nn.LSTM(128, 128, 1 ,bidirectional = True)\n",
    "        self.output = torch.nn.Linear(256, labels)\n",
    "\n",
    "    def forward(self, x):\n",
    "        x = self.feature_extractor(x)\n",
    "        x = x.squeeze(2)\n",
    "        x = x.permute(2,0,1)\n",
    "        x,_ = self.recurrent(x)\n",
    "        x = self.output(x)\n",
    "        return x\n",
    "\n",
    "recognizer = TextRecognizer(len(CHARS))\n",
    "DEVICE = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
    "print(\"Device:\", DEVICE)\n",
    "LR = 1e-3\n",
    "\n",
    "recognizer.to(DEVICE)\n",
    "optimizer = torch.optim.Adam(recognizer.parameters(), lr=LR)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "e61f1d87-4a82-4714-b4e1-33719064a735",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7889\n",
      "Running on public URL: https://e1090d81e4ea8bf190.gradio.live\n",
      "\n",
      "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"https://e1090d81e4ea8bf190.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Traceback (most recent call last):\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/queueing.py\", line 536, in process_events\n",
      "    response = await route_utils.call_process_api(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/route_utils.py\", line 288, in call_process_api\n",
      "    output = await app.get_blocks().process_api(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/blocks.py\", line 1931, in process_api\n",
      "    result = await self.call_function(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/blocks.py\", line 1516, in call_function\n",
      "    prediction = await anyio.to_thread.run_sync(  # type: ignore\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/to_thread.py\", line 56, in run_sync\n",
      "    return await get_async_backend().run_sync_in_worker_thread(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py\", line 2177, in run_sync_in_worker_thread\n",
      "    return await future\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py\", line 859, in run\n",
      "    result = context.run(func, *args)\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/utils.py\", line 826, in wrapper\n",
      "    response = f(*args, **kwargs)\n",
      "  File \"/tmp/ipykernel_848/2152623987.py\", line 5, in ctc_read\n",
      "    imagefin = fit_picture(image)\n",
      "  File \"/tmp/ipykernel_848/2382022948.py\", line 19, in fit_picture\n",
      "    aspect_ratio = img.width / img.height\n",
      "AttributeError: 'NoneType' object has no attribute 'width'\n",
      "Traceback (most recent call last):\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/queueing.py\", line 536, in process_events\n",
      "    response = await route_utils.call_process_api(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/route_utils.py\", line 288, in call_process_api\n",
      "    output = await app.get_blocks().process_api(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/blocks.py\", line 1931, in process_api\n",
      "    result = await self.call_function(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/blocks.py\", line 1516, in call_function\n",
      "    prediction = await anyio.to_thread.run_sync(  # type: ignore\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/to_thread.py\", line 56, in run_sync\n",
      "    return await get_async_backend().run_sync_in_worker_thread(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py\", line 2177, in run_sync_in_worker_thread\n",
      "    return await future\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py\", line 859, in run\n",
      "    result = context.run(func, *args)\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/utils.py\", line 826, in wrapper\n",
      "    response = f(*args, **kwargs)\n",
      "  File \"/tmp/ipykernel_848/2152623987.py\", line 5, in ctc_read\n",
      "    imagefin = fit_picture(image)\n",
      "  File \"/tmp/ipykernel_848/2382022948.py\", line 19, in fit_picture\n",
      "    aspect_ratio = img.width / img.height\n",
      "AttributeError: 'NoneType' object has no attribute 'width'\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([1, 1, 32, 400])\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/obai33/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\n",
      "  return F.conv2d(input, weight, bias, self.stride,\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([1, 1, 32, 400])\n",
      "torch.Size([1, 1, 32, 400])\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/obai33/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\n",
      "  return F.conv2d(input, weight, bias, self.stride,\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([1, 1, 32, 400])\n",
      "torch.Size([1, 1, 32, 400])\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/obai33/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\n",
      "  return F.conv2d(input, weight, bias, self.stride,\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([1, 1, 32, 400])\n",
      "torch.Size([1, 1, 32, 400])\n",
      "torch.Size([1, 1, 32, 400])\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Traceback (most recent call last):\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/queueing.py\", line 536, in process_events\n",
      "    response = await route_utils.call_process_api(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/route_utils.py\", line 288, in call_process_api\n",
      "    output = await app.get_blocks().process_api(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/blocks.py\", line 1931, in process_api\n",
      "    result = await self.call_function(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/blocks.py\", line 1516, in call_function\n",
      "    prediction = await anyio.to_thread.run_sync(  # type: ignore\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/to_thread.py\", line 56, in run_sync\n",
      "    return await get_async_backend().run_sync_in_worker_thread(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py\", line 2177, in run_sync_in_worker_thread\n",
      "    return await future\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py\", line 859, in run\n",
      "    result = context.run(func, *args)\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/utils.py\", line 826, in wrapper\n",
      "    response = f(*args, **kwargs)\n",
      "  File \"/tmp/ipykernel_848/2152623987.py\", line 5, in ctc_read\n",
      "    imagefin = fit_picture(image)\n",
      "  File \"/tmp/ipykernel_848/2382022948.py\", line 19, in fit_picture\n",
      "    aspect_ratio = img.width / img.height\n",
      "AttributeError: 'NoneType' object has no attribute 'width'\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([1, 1, 32, 400])\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/obai33/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\n",
      "  return F.conv2d(input, weight, bias, self.stride,\n",
      "Traceback (most recent call last):\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/queueing.py\", line 536, in process_events\n",
      "    response = await route_utils.call_process_api(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/route_utils.py\", line 288, in call_process_api\n",
      "    output = await app.get_blocks().process_api(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/blocks.py\", line 1931, in process_api\n",
      "    result = await self.call_function(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/blocks.py\", line 1516, in call_function\n",
      "    prediction = await anyio.to_thread.run_sync(  # type: ignore\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/to_thread.py\", line 56, in run_sync\n",
      "    return await get_async_backend().run_sync_in_worker_thread(\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py\", line 2177, in run_sync_in_worker_thread\n",
      "    return await future\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py\", line 859, in run\n",
      "    result = context.run(func, *args)\n",
      "  File \"/home/obai33/.local/lib/python3.10/site-packages/gradio/utils.py\", line 826, in wrapper\n",
      "    response = f(*args, **kwargs)\n",
      "  File \"/tmp/ipykernel_848/2152623987.py\", line 5, in ctc_read\n",
      "    imagefin = fit_picture(image)\n",
      "  File \"/tmp/ipykernel_848/2382022948.py\", line 19, in fit_picture\n",
      "    aspect_ratio = img.width / img.height\n",
      "AttributeError: 'NoneType' object has no attribute 'width'\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([1, 1, 32, 400])\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/obai33/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\n",
      "  return F.conv2d(input, weight, bias, self.stride,\n"
     ]
    }
   ],
   "source": [
    "load_model('model.pt')\n",
    "recognizer.eval()\n",
    "\n",
    "def ctc_read(image):\n",
    "    imagefin = fit_picture(image)\n",
    "    image_tensor = imagefin.unsqueeze(0).to(DEVICE)\n",
    "    print(image_tensor.size())\n",
    "    \n",
    "    with torch.no_grad():\n",
    "        scores = recognizer(image_tensor)\n",
    "\n",
    "    predictions = scores.argmax(2).cpu().numpy()\n",
    "\n",
    "    decoded_sequences = ctc_decode(predictions)\n",
    "\n",
    "    # Convert decoded sequences to text\n",
    "    for i in decoded_sequences:\n",
    "        decoded_text = decode_text(i)\n",
    "\n",
    "    return decoded_text\n",
    "\n",
    "\n",
    "# Gradio Interface\n",
    "iface = gr.Interface(\n",
    "    fn=ctc_read,\n",
    "    inputs=gr.Image(type=\"pil\"),  # PIL Image input\n",
    "    outputs=\"text\",  # Text output\n",
    "    title=\"Handwritten Text Recognition\",\n",
    "    description=\"Upload an image, and the custome AI will extract the text.\"\n",
    ")\n",
    "\n",
    "iface.launch(share=True)\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}