app.py

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

from huggingface_hub import from_pretrained_keras

import numpy as np
import gradio as gr

characters = {'2', '3', '4', '5', '6', '7', '8', 'b', 'c', 'd', 'e', 'f', 'g', 'm', 'n', 'p', 'w', 'x', 'y'}
max_length = 5
img_width = 200
img_height = 50

model = from_pretrained_keras("keras-io/ocr-for-captcha")

prediction_model = keras.models.Model(
    model.get_layer(name="image").input, model.get_layer(name="dense2").output
)

# Mapping characters to integers
char_to_num = layers.StringLookup(
    vocabulary=list(characters), mask_token=None
)

# Mapping integers back to original characters
num_to_char = layers.StringLookup(
    vocabulary=char_to_num.get_vocabulary(), mask_token=None, invert=True
)

def decode_batch_predictions(pred):
    input_len = np.ones(pred.shape[0]) * pred.shape[1]
    # Use greedy search. For complex tasks, you can use beam search
    results = keras.backend.ctc_decode(pred, input_length=input_len, greedy=False, beam_width=5)[0][0][
        :, :max_length
    ]
    # Iterate over the results and get back the text
    output_text = []
    for res in results:
        res = tf.strings.reduce_join(num_to_char(res)).numpy().decode("utf-8")
        output_text.append(res)
    return output_text

def classify_image(img_path):
    # 1. Read image
    img = tf.io.read_file(img_path)
    # 2. Decode and convert to grayscale
    img = tf.io.decode_png(img, channels=1)
    # 3. Convert to float32 in [0, 1] range
    img = tf.image.convert_image_dtype(img, tf.float32)
    # 4. Resize to the desired size
    img = tf.image.resize(img, [img_height, img_width])
    # 5. Transpose the image because we want the time
    # dimension to correspond to the width of the image.
    img = tf.transpose(img, perm=[1, 0, 2])
    img = tf.expand_dims(img, axis=0)
    preds = prediction_model.predict(img)
    pred_text = decode_batch_predictions(preds)
    return pred_text
  
image = gr.inputs.Image(type='filepath')
text = gr.outputs.Textbox()

iface = gr.Interface(classify_image,image,text,
  title="OCR for CAPTCHA",
	description = "Keras Implementation of OCR model for reading captcha 🤖🦹🏻",
        article = "Author: <a href=\"https://huggingface.co/anuragshas\">Anurag Singh</a>"
)


iface.launch()