indicate 0.2.0__py3-none-any.whl

indicate/notebooks/transliterate_cricket.ipynb

@@ -0,0 +1,305 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_json('../data/players_with_hindi_names.json')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<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>id</th>\n",
+       "      <th>hindi_name</th>\n",
+       "      <th>hindi_long_name</th>\n",
+       "      <th>english_name</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>date_of_birth</th>\n",
+       "      <th>country_id</th>\n",
+       "      <th>slug</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>90143</td>\n",
+       "      <td>आर गुरबाज़</td>\n",
+       "      <td>रहमानउल्लाह गुरबाज़</td>\n",
+       "      <td>Rahmanullah Gurbaz</td>\n",
+       "      <td>M</td>\n",
+       "      <td>{'year': 2001, 'month': 11, 'date': 28}</td>\n",
+       "      <td>40</td>\n",
+       "      <td>rahmanullah-gurbaz</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>54018</td>\n",
+       "      <td>एम रिज़वान</td>\n",
+       "      <td>मोहम्मद रिज़वान</td>\n",
+       "      <td>Mohammad Rizwan</td>\n",
+       "      <td>M</td>\n",
+       "      <td>{'year': 1992, 'month': 6, 'date': 1}</td>\n",
+       "      <td>7</td>\n",
+       "      <td>mohammad-rizwan</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>47686</td>\n",
+       "      <td>एस मक़सूद</td>\n",
+       "      <td>सोहेब मक़सूद</td>\n",
+       "      <td>Sohaib Maqsood</td>\n",
+       "      <td>M</td>\n",
+       "      <td>{'year': 1987, 'month': 4, 'date': 15}</td>\n",
+       "      <td>7</td>\n",
+       "      <td>sohaib-maqsood</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>53649</td>\n",
+       "      <td>आर आर रुसो</td>\n",
+       "      <td>राइली रुसो</td>\n",
+       "      <td>Rossouw, RR</td>\n",
+       "      <td>M</td>\n",
+       "      <td>{'year': 1989, 'month': 10, 'date': 9}</td>\n",
+       "      <td>3</td>\n",
+       "      <td>rilee-rossouw</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>72393</td>\n",
+       "      <td>एस हेटमायर</td>\n",
+       "      <td>शिमरॉन हेटमायर</td>\n",
+       "      <td>Hetmyer, SO</td>\n",
+       "      <td>M</td>\n",
+       "      <td>{'year': 1996, 'month': 12, 'date': 26}</td>\n",
+       "      <td>4</td>\n",
+       "      <td>shimron-hetmyer</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      id  hindi_name      hindi_long_name        english_name gender  \\\n",
+       "0  90143  आर गुरबाज़  रहमानउल्लाह गुरबाज़  Rahmanullah Gurbaz      M   \n",
+       "1  54018  एम रिज़वान      मोहम्मद रिज़वान     Mohammad Rizwan      M   \n",
+       "2  47686   एस मक़सूद         सोहेब मक़सूद      Sohaib Maqsood      M   \n",
+       "3  53649  आर आर रुसो           राइली रुसो         Rossouw, RR      M   \n",
+       "4  72393  एस हेटमायर       शिमरॉन हेटमायर         Hetmyer, SO      M   \n",
+       "\n",
+       "                             date_of_birth  country_id                slug  \n",
+       "0  {'year': 2001, 'month': 11, 'date': 28}          40  rahmanullah-gurbaz  \n",
+       "1    {'year': 1992, 'month': 6, 'date': 1}           7     mohammad-rizwan  \n",
+       "2   {'year': 1987, 'month': 4, 'date': 15}           7      sohaib-maqsood  \n",
+       "3   {'year': 1989, 'month': 10, 'date': 9}           3       rilee-rossouw  \n",
+       "4  {'year': 1996, 'month': 12, 'date': 26}           4     shimron-hetmyer  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of samples: 2512\n",
+      "Number of unique input tokens: 452\n",
+      "Number of unique output tokens: 457\n",
+      "Max sequence length for inputs: 22\n",
+      "Max sequence length for outputs: 26\n"
+     ]
+    }
+   ],
+   "source": [
+    "from keras.models import Model\n",
+    "from keras.layers import Input, LSTM, Dense\n",
+    "import numpy as np\n",
+    "\n",
+    "batch_size = 64  # Batch size for training.\n",
+    "epochs = 10  # Number of epochs to train for.\n",
+    "latent_dim = 256  # Latent dimensionality of the encoding space.\n",
+    "num_samples = 1000  # Number of samples to train on.\n",
+    "# Path to the data txt file on disk.\n",
+    "\n",
+    "# Vectorize the data.\n",
+    "input_texts = df.hindi_name.tolist()\n",
+    "target_texts = df.english_name.tolist()\n",
+    "input_characters = set()\n",
+    "target_characters = set()\n",
+    "\n",
+    "input_list =  df['hindi_name'].tolist()\n",
+    "target_list =  df['english_name'].tolist()\n",
+    "\n",
+    "for char in input_list:\n",
+    "    if char not in input_characters:\n",
+    "        input_characters.add(char)\n",
+    "for char in target_list:\n",
+    "    if char not in target_characters:\n",
+    "        target_characters.add(char)\n",
+    "            \n",
+    "\n",
+    "input_characters = sorted(list(input_characters))\n",
+    "target_characters = sorted(list(target_characters))\n",
+    "num_encoder_tokens = len(input_characters)\n",
+    "num_decoder_tokens = len(target_characters)\n",
+    "max_encoder_seq_length = max([len(txt) for txt in input_texts])\n",
+    "max_decoder_seq_length = max([len(txt) for txt in target_texts])\n",
+    "\n",
+    "print('Number of samples:', len(input_texts))\n",
+    "print('Number of unique input tokens:', num_encoder_tokens)\n",
+    "print('Number of unique output tokens:', num_decoder_tokens)\n",
+    "print('Max sequence length for inputs:', max_encoder_seq_length)\n",
+    "print('Max sequence length for outputs:', max_decoder_seq_length)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "KeyError",
+     "evalue": "'आ'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-15-094370a4c3f2>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m     16\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0minput_text\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtarget_text\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mzip\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minput_texts\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtarget_texts\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     17\u001b[0m     \u001b[1;32mfor\u001b[0m \u001b[0mt\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mchar\u001b[0m \u001b[1;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minput_text\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 18\u001b[1;33m         \u001b[0mencoder_input_data\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mt\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minput_token_index\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mchar\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;36m1.\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     19\u001b[0m     \u001b[1;32mfor\u001b[0m \u001b[0mt\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mchar\u001b[0m \u001b[1;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtarget_text\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     20\u001b[0m         \u001b[1;31m# decoder_target_data is ahead of decoder_input_data by one timestep\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mKeyError\u001b[0m: 'आ'"
+     ]
+    }
+   ],
+   "source": [
+    "input_token_index = dict(\n",
+    "    [(char, i) for i, char in enumerate(input_characters)])\n",
+    "target_token_index = dict(\n",
+    "    [(char, i) for i, char in enumerate(target_characters)])\n",
+    "\n",
+    "encoder_input_data = np.zeros(\n",
+    "    (len(input_texts), max_encoder_seq_length, num_encoder_tokens),\n",
+    "    dtype='float32')\n",
+    "decoder_input_data = np.zeros(\n",
+    "    (len(input_texts), max_decoder_seq_length, num_decoder_tokens),\n",
+    "    dtype='float32')\n",
+    "decoder_target_data = np.zeros(\n",
+    "    (len(input_texts), max_decoder_seq_length, num_decoder_tokens),\n",
+    "    dtype='float32')\n",
+    "\n",
+    "for i, (input_text, target_text) in enumerate(zip(input_texts, target_texts)):\n",
+    "    for t, char in enumerate(input_text):\n",
+    "        encoder_input_data[i, t, input_token_index[char]] = 1.\n",
+    "    for t, char in enumerate(target_text):\n",
+    "        # decoder_target_data is ahead of decoder_input_data by one timestep\n",
+    "        decoder_input_data[i, t, target_token_index[char]] = 1.\n",
+    "        if t > 0:\n",
+    "            # decoder_target_data will be ahead by one timestep\n",
+    "            # and will not include the start character.\n",
+    "            decoder_target_data[i, t - 1, target_token_index[char]] = 1.\n",
+    "\n",
+    "# Define an input sequence and process it.\n",
+    "encoder_inputs = Input(shape=(None, num_encoder_tokens))\n",
+    "encoder = LSTM(latent_dim, return_state=True)\n",
+    "encoder_outputs, state_h, state_c = encoder(encoder_inputs)\n",
+    "# We discard `encoder_outputs` and only keep the states.\n",
+    "encoder_states = [state_h, state_c]\n",
+    "# Set up the decoder, using `encoder_states` as initial state.\n",
+    "decoder_inputs = Input(shape=(None, num_decoder_tokens))\n",
+    "# We set up our decoder to return full output sequences,\n",
+    "# and to return internal states as well. We don't use the\n",
+    "# return states in the training model, but we will use them in inference.\n",
+    "decoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)\n",
+    "decoder_outputs, _, _ = decoder_lstm(decoder_inputs,\n",
+    "                                     initial_state=encoder_states)\n",
+    "decoder_dense = Dense(num_decoder_tokens, activation='softmax')\n",
+    "decoder_outputs = decoder_dense(decoder_outputs)\n",
+    "\n",
+    "# Define the model that will turn\n",
+    "# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`\n",
+    "model = Model([encoder_inputs, decoder_inputs], decoder_outputs)\n",
+    "\n",
+    "# Run training\n",
+    "model.compile(optimizer='rmsprop', loss='categorical_crossentropy')\n",
+    "model.fit([encoder_input_data, decoder_input_data], decoder_target_data,\n",
+    "          batch_size=batch_size,\n",
+    "          epochs=epochs,\n",
+    "          validation_split=0.2)\n",
+    "# Save model\n",
+    "model.save('s2s.h5')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

indicate/tests/__init__.py

@@ -0,0 +1,12 @@
+import sys
+from contextlib import contextmanager
+from io import StringIO
+
+
+@contextmanager
+def capture(command, *args, **kwargs):
+    out, sys.stdout = sys.stdout, StringIO()
+    command(*args, **kwargs)
+    sys.stdout.seek(0)
+    yield sys.stdout.read()
+    sys.stdout = out

indicate/tests/test_010_hindi_translate.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+Test Hindi to English translation
+"""
+
+import unittest
+
+from indicate.hindi2english import HindiToEnglish
+
+class TestHindiToEnglish(unittest.TestCase):
+    def test_hindi_to_english(self):
+        test_inputs = ["राजशेखर चिंतालपति","गौरव सूद"]
+        test_outputs = ["rajshekhar chintalpati","gaurav sood"]
+        for hindi, english in zip(test_inputs, test_outputs):
+            self.assertEqual(HindiToEnglish.transliterate(hindi), english)
+
+if __name__ == "__main__":
+    unittest.main()

indicate/transliterate.py

@@ -0,0 +1,28 @@
+import sys
+import argparse
+
+from .hindi2english import HindiToEnglish
+
+hindi2english = HindiToEnglish.transliterate
+
+
+def main(argv=sys.argv[1:]):
+    title = "Transliterate from Hindi to English"
+    parser = argparse.ArgumentParser(description=title)
+    parser.add_argument("--type", default=None, help="hin2eng")
+    parser.add_argument("--input", default=None, help="Hindi text")
+    args = parser.parse_args(argv)
+    print(args)
+    if not args.input or not args.type:
+        return -1
+
+    output = ""
+    if args.type == "hin2eng":
+        output = hindi2english(args.input)
+    print(output)
+
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

indicate/utils.py

@@ -0,0 +1,86 @@
+import tensorflow as tf
+
+def sequence_to_chars(tokenizer, sequence):
+    """Convert a sequence of indices back to characters."""
+    word_index = tokenizer.word_index
+    reverse_map = {val: key for key, val in word_index.items()}
+    retext = ''
+
+    # Convert tensor to numpy array if it's a tensor
+    if tf.is_tensor(sequence):
+        sequence = sequence.numpy()
+
+    for q in sequence:
+        q_int = int(q)  # Convert to integer
+        if q_int != 0:  # Skip padding token
+            retext += reverse_map[q_int]
+    return retext
+
+def evaluate_sentence(sentence, units, input_lang_tokenizer, target_lang_tokenizer,
+                     encoder, decoder, max_length_input):
+    """Evaluate/translate a single sentence."""
+    # Convert input sentence to token indices
+    inputs = [input_lang_tokenizer.word_index[i] for i in sentence]
+    inputs = tf.keras.preprocessing.sequence.pad_sequences([inputs],
+                                                         maxlen=max_length_input,
+                                                         padding='post')
+    inputs = tf.convert_to_tensor(inputs)
+
+    # Use the same batch size as decoder.batch_sz for consistency
+    inference_batch_size = inputs.shape[0]
+
+    inputs = tf.tile(inputs, [inference_batch_size, 1])  # Replicate input to match batch size
+
+    # Initialize encoder state
+    enc_start_state = [tf.zeros((inference_batch_size, units)),
+                      tf.zeros((inference_batch_size, units))]
+
+    # Get encoder output
+    enc_out, enc_h, enc_c = encoder(inputs, enc_start_state)
+
+    # Initialize decoder with encoder's final state
+    dec_state = [enc_h, enc_c]
+
+    # Prepare decoder input with start token
+    dec_input = tf.fill([inference_batch_size, 1],
+                       target_lang_tokenizer.word_index['^'])
+
+    outputs = []
+
+    # Decoding loop
+    for t in range(decoder.max_length_output):
+        # Call decoder
+        predictions, dec_state, _ = decoder(dec_input, dec_state, enc_out)
+
+        # Get predicted token (use first batch item since all are the same)
+        predicted_id = tf.argmax(predictions, axis=-1).numpy()[0, -1]
+
+        # Append prediction
+        outputs.append(predicted_id)
+
+        # Break if end token is predicted
+        if predicted_id == target_lang_tokenizer.word_index['$']:
+            break
+
+        # Update decoder input
+        dec_input = tf.fill([inference_batch_size, 1], predicted_id)
+
+    return tf.convert_to_tensor(outputs)
+
+
+def translate(sentence, units, input_lang_tokenizer, target_lang_tokenizer,
+             encoder, decoder, max_length_input):
+    """Translate a sentence from source to target language."""
+    result = evaluate_sentence(sentence,
+                             units,
+                             input_lang_tokenizer,
+                             target_lang_tokenizer,
+                             encoder,
+                             decoder,
+                             max_length_input)
+
+    # Convert the output tokens back to characters
+    translated_text = sequence_to_chars(target_lang_tokenizer, result)
+
+    # Remove the end token and return
+    return translated_text.strip('$')

indicate-0.2.0.dist-info/LICENSE

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2021 Rajasekhar Chintalapati and Gaurav Sood
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

indicate-0.2.0.dist-info/METADATA

@@ -0,0 +1,139 @@
+Metadata-Version: 2.2
+Name: indicate
+Version: 0.2.0
+Summary: Transliterations to/from Indian languages
+Home-page: https://github.com/in-rolls/indicate
+Author: Rajashekar Chintalapati, Gaurav Sood
+Author-email: rajshekar.ch@gmail.com, gsood07@gmail.com
+License: MIT
+Keywords: transliterate indic hindi english
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Utilities
+License-File: LICENSE
+Requires-Dist: tqdm
+Requires-Dist: func-timeout
+Requires-Dist: tensorflow==2.18.0
+Provides-Extra: dev
+Requires-Dist: check-manifest; extra == "dev"
+Provides-Extra: test
+Requires-Dist: coverage; extra == "test"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: summary
+
+==================================================
+Indicate: Transliterate Indic Languages to English
+==================================================
+
+.. image:: https://app.travis-ci.com/in-rolls/indicate.svg?branch=master
+    :target: https://travis-ci.org/in-rolls/indicate
+.. image:: https://img.shields.io/pypi/v/indicate.svg
+    :target: https://pypi.python.org/pypi/indicate
+.. image:: https://readthedocs.org/projects/indicate/badge/?version=latest
+    :target: http://notnews.readthedocs.io/en/latest/?badge=latest
+    :alt: Documentation Status
+.. image:: https://static.pepy.tech/badge/indicate
+    :target: https://pepy.tech/project/indicate
+
+Transliterations to/from Indian languages are still generally low quality. One problem is access to data. Another is that there is no standard  transliteration.
+For Hindi--English, we build novel dataset for names using the ESPNcricinfo. For instance, see `here <https://www.espncricinfo.com/hindi/series/pakistan-tour-of-england-2021-1239529/england-vs-pakistan-1st-odi-1239537/full-scorecard>`__ for hindi version of the `english scorecard <https://www.espncricinfo.com/series/pakistan-tour-of-england-2021-1239529/england-vs-pakistan-1st-odi-1239537/full-scorecard>`__.
+We also create a dataset from `election affidavits <https://affidavit.eci.gov.in/CandidateCustomFilter>`__
+We also exploit the `Google Dakshina dataset <https://github.com/google-research-datasets/dakshina>`__.
+
+To overcome the fact that there isn't one standard way of transliteration, we provide k-best transliterations.
+
+Install
+-------
+We strongly recommend installing `indicate` inside a Python virtual environment
+(see `venv documentation <https://docs.python.org/3/library/venv.html#creating-virtual-environments>`__)
+
+::
+
+    pip install indicate
+
+General API
+-----------
+1. transliterate.hindi2english will take Hindi text and translate into English.
+
+Examples
+--------
+::
+
+  from indicate import transliterate
+  english_translated = transliterate.hindi2english("हिंदी")
+  print(english_translated)
+
+output -
+hindi
+
+Functions
+----------
+We expose 1 function, which will take Hindi text and transliterate it to English.
+
+- **transliterate.hindi2english(input)**
+
+  - What it does:
+
+    - Converts given hindi text into English alphabet
+
+  - Output
+
+    - Returns text in English
+
+Data
+----
+The datasets used to train the model:
+
+- `Indian Election affidavits <https://affidavit.eci.gov.in/CandidateCustomFilter>`__
+
+- `Google Dakshina dataset <https://github.com/google-research-datasets/dakshina>`__
+
+- `ESPN Cric Info <https://www.espncricinfo.com/hindi/series/pakistan-tour-of-england-2021-1239529/england-vs-pakistan-1st-odi-1239537/full-scorecard>`__ for hindi version of the `english scorecard <https://www.espncricinfo.com/series/pakistan-tour-of-england-2021-1239529/england-vs-pakistan-1st-odi-1239537/full-scorecard>`__.
+
+- `IIT Bombay English-Hindi Corpus <https://www.cfilt.iitb.ac.in/iitb_parallel/>`__
+
+Evaluation
+----------
+Model was evaluated on test dataset of Google Dakshina dataset, Model predicted 73.64% exact matches.
+`Indic-trans <https://github.com/libindic/indic-trans>`__ predicted 63.12% exact matches on Google Dakshina dataset.
+Below is the edit distance metrics on test dataset (0.0 mean exact match, the farther away from 0.0,
+the difference is more between predicted text and actual text)
+
+.. image:: https://github.com/in-rolls/indicate/raw/master/images/h2e_ed.png
+   :width: 400
+   :alt: Edit distance metrics of model on Google Dakshina test dataset
+
+
+Authors
+-------
+
+Rajashekar Chintalapati and Gaurav Sood
+
+Contributor Code of Conduct
+---------------------------------
+
+The project welcomes contributions from everyone! In fact, it depends on
+it. To maintain this welcoming atmosphere, and to collaborate in a fun
+and productive way, we expect contributors to the project to abide by
+the `Contributor Code of
+Conduct <http://contributor-covenant.org/version/1/0/0/>`__.
+
+License
+----------
+
+The package is released under the `MIT
+License <https://opensource.org/licenses/MIT>`__.

indicate-0.2.0.dist-info/RECORD

@@ -0,0 +1,26 @@
+indicate/__init__.py,sha256=89udvCQOFZ2icsiF0Nmk_KeUWLq3vhQxzA38Hz1ARWA,70
+indicate/decoder.py,sha256=_u7npwJlmF2N--bfwb6hok3QF0ezObj9FyOjhr5ENjY,2567
+indicate/encoder.py,sha256=pkFv7rggaISgdHMQflfi019gbp9FVjsU3ex_-eBqGtI,910
+indicate/hindi2english.py,sha256=T4lcR8NpHhr7-Gq4XFOJJbGSFyvv57AOsUnvt9nuAII,4677
+indicate/logging.py,sha256=AGzjUiPusLS7QJnMdjHDSWRkxC_WoL4jKv0_b2YuhJ0,96
+indicate/transliterate.py,sha256=jrVfz7VaR2p-FthcMXFSDym-UmU9WeFu30ZrXzAzR34,667
+indicate/utils.py,sha256=gD7WjTlBBsh9tPXi8i8wO3d6JDYCtp-rnUNyOnZN-04,3168
+indicate/data/model/hindi_to_english/english_tokens.json,sha256=g_pssuCQyXnE05DRVqing852wHMcxZ-eT5753feCTJs,14480
+indicate/data/model/hindi_to_english/hindi_tokens.json,sha256=mMZYNM8HkKz7eCHFgHGe8KEKbrXMGz-Mq3v-zQ2lJvU,22545
+indicate/data/model/hindi_to_english/saved_weights/decoder.weights.h5,sha256=e-An6CE6yVi2J8Y8cGn7adogLhCD3UVPqNxf8kbX75o,39543312
+indicate/data/model/hindi_to_english/saved_weights/encoder.weights.h5,sha256=6sd66LpwQlCXbK6od_hd2tR_KOzGHG0Q5PqLk7-h7gE,21208200
+indicate/notebooks/Data_Preparation.ipynb,sha256=O65ytgmQRxujLS5LShxFtTnXr4ZTockDkHEPub0cGiw,37341
+indicate/notebooks/Inference.ipynb,sha256=Y2k7oHAfQP579XTB-KL3ahiQTGdFygidBCqNNr6LqEI,72057
+indicate/notebooks/Inference_latest.ipynb,sha256=2cGLK-KHWg3gKAJcABhZbEEuo6uoP2rzWAQt-Q8U9Jc,95628
+indicate/notebooks/Train.ipynb,sha256=ZmG5iZ_n79FSBbyJBNOkTdmz_7JkNnWkng9A6wQ8U-w,58879
+indicate/notebooks/Train_latest.ipynb,sha256=m91MAI2zxCKvts_QVgjc_mWXYi3Wb9a5Dur8EymCIRc,69089
+indicate/notebooks/Transliterate.ipynb,sha256=u4MZ-9za3S0Dvz87QtKZnh1CIo8uYGR2RYYCj7hlA0I,308328
+indicate/notebooks/transliterate_cricket.ipynb,sha256=Dr0iu3r0XwIF0a_DwQqQZ7qauKk4AfLkFEWjglRDb58,13072
+indicate/tests/__init__.py,sha256=ezvdIE58d5GooM9wrJ51pNk9U3pb-LWMWE2nKYqiQP0,275
+indicate/tests/test_010_hindi_translate.py,sha256=69XHcpDlRtOw9gMYv11cSBBOSsG31q_pfqi0mT9K1EE,590
+indicate-0.2.0.dist-info/LICENSE,sha256=iEky6BOuLfXUmOQ67jpWOyqapJVj37qeXqUIHIhVHYM,1106
+indicate-0.2.0.dist-info/METADATA,sha256=wxXC9ZmUTgWUZ6ysC17hCIlzHnT5W8_ph7b5MXnirv8,5269
+indicate-0.2.0.dist-info/WHEEL,sha256=9Hm2OB-j1QcCUq9Jguht7ayGIIZBRTdOXD1qg9cCgPM,109
+indicate-0.2.0.dist-info/entry_points.txt,sha256=LrGK3DYYXfR5vWPG5RvW9wj7R6ZoSfa0iuxvXIkmZec,62
+indicate-0.2.0.dist-info/top_level.txt,sha256=MH_uxn6O8-g_WCij25wOlx2cNuv9-mScUuZDBPSb2AA,9
+indicate-0.2.0.dist-info/RECORD,,

indicate-0.2.0.dist-info/WHEEL

@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.8.0)
+Root-Is-Purelib: true
+Tag: py2-none-any
+Tag: py3-none-any
+

indicate-0.2.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+hindi2english = indicate.transliterate:main

indicate-0.2.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+indicate