translation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## English to German Translation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "translation = pipeline(\"translation_en_to_de\")\n",
    "## same with \n",
    "## translation = pipeline(\"translation_en_to_de\", model=\"t5-base\", tokenizer=\"t5-base\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"I like to study Data Science and Machine Learning\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ich studiere gerne Datenwissenschaft und maschinelles Lernen\n"
     ]
    }
   ],
   "source": [
    "translated_text = translation(text, max_length=40)[0]['translation_text']\n",
    "print(translated_text)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Custom Language Translation (e.g. English to Chinese)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import AutoModelWithLMHead, AutoTokenizer\n",
    "\n",
    "model = AutoModelWithLMHead.from_pretrained(\"Helsinki-NLP/opus-mt-en-zh\")\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"Helsinki-NLP/opus-mt-en-zh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "translation = pipeline(\"translation_en_to_zh\", model=model, tokenizer=tokenizer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "text = \"I like to study Data Science and Machine Learning\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "我喜欢学习数据科学和机器学习\n"
     ]
    }
   ],
   "source": [
    "translated_text = translation(text, max_length=40)[0]['translation_text']\n",
    "print(translated_text)"
   ]
  }
 ],
 "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": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}