Translators - is a library which aims to bring free, multiple, enjoyable translation to individuals and students in Python

Overview

PyPI - Version PyPI - License PyPI - Python PyPI - Status PyPI - Wheel Downloads


Translators is a library which aims to bring free, multiple, enjoyable translation to individuals and students in Python. It based on the translation interface of Google, Yandex, Microsoft(Bing), Baidu, Alibaba, Tencent, NetEase(Youdao), Sogou, Kingsoft(Iciba), Iflytek, Deepl, Caiyun, Argos, etc.

Installation

From PyPI

# Windows, Mac, Linux
pip install translators --upgrade

# Linux javascript runtime environment:
sudo yum -y install nodejs

From Source

git clone https://github.com/UlionTse/translators.git
cd translators
python setup.py install

Getting Started

import translators as ts

wyw_text = '季姬寂,集鸡,鸡即棘鸡。棘鸡饥叽,季姬及箕稷济鸡。'
chs_text = '季姬感到寂寞,罗集了一些鸡来养,鸡是那种出自荆棘丛中的野鸡。野鸡饿了唧唧叫,季姬就拿竹箕中的谷物喂鸡。'
html_text = '''



	这是标题


这是文章《你的父亲》

''' ## language # input languages print(ts.google(wyw_text)) # default: from_language='auto', to_language='en' # output language_map print(ts._google.language_map) ## professional field print(ts.alibaba(wyw_text, professional_field='general')) # ("general","message","offer") print(ts.baidu(wyw_text, professional_field='common')) # ('common','medicine','electronics','mechanics') print(ts.caiyun(wyw_text, from_language='zh', professional_field=None)) # ("medicine","law","machinery") ## property rs = [ts.tencent(x) for x in [wyw_text, chs_text]] print(ts._tencent.query_count) print(dir(ts._tencent)) ## requests print(ts.youdao(wyw_text, sleep_seconds=5, timeout=None, proxies=None)) ## host # cn print(ts.google(wyw_text, if_use_cn_host=True)) print(ts.bing(wyw_text, if_use_cn_host=False)) # reset host print(ts.google(wyw_text, reset_host_url=None)) print(ts.yandex(wyw_text, reset_host_url=None)) ## detail result print(ts.sogou(wyw_text, is_detail_result=True)) ## translate html print(ts.translate_html(html_text, translator=ts.google, to_language='en', n_jobs=-1)) ## others print(ts._argos.host_pool) print(ts.argos(wyw_text, reset_host_url=None)) ## help help(ts.google)

Issues

Linux Runtime Environment

  1. To support javascript runtime environment, you should sudo yum -y install nodejs .
  2. PS, ts.baidu() does not work on Linux without desktop.

Supported Country and Region Service

  1. If you have requests error, please check whether this service is provided in your country or region.
  2. Check the website about eg: help(ts.google).

HttpError 4xx

  1. Please check whether you made high frequency requests.
  2. Please check whether this service is provided in your country or region.
  3. Detail to solve HttpError itself.
  4. Please issue me, thanks.

RequestsError or ProxyError

  1. Check whether the advanced version of requests you have installed can access the site properly. If not, try lowering the version or otherwise.
  2. Check that agents are enabled on your computer. If it is enabled, try turning it off or otherwise.

More About Translators

Features

Translator Number of Supported Languages Advantage
Iciba 187 support the most languages in the world
Google 109 support more languages in the world
Bing 102 support more languages in the world
Yandex 100 support more languages in the world, support word to emoji
Iflytek 70 support more languages in the world
Sogou 61 support more languages in the world
Baidu 28 support main languages, support professional field
Deepl 24 high quality to translate but response slowly
Tencent 17 support main languages
Argos 17 support main languages , open-source
Youdao 15 support main languages, high quality
Alibaba 12 support main languages, support professional field
Caiyun 6 high quality to translate but response slowly, support professional field

Support Language

Language Language of Translator Google Yandex Bing Baidu Alibaba Tencent Youdao Sogou Deepl Caiyun Argos Iciba Iflytek
english en Y Y Y Y Y Y Y Y Y Y Y ... ...
chinese zh Y Y Y Y Y Y Y Y Y Y Y
arabic ar Y Y Y Y(ara) Y Y Y Y Y
russian ru Y Y Y Y Y Y Y Y Y Y Y
french fr Y Y Y Y(fra) Y Y Y Y Y Y Y
german de Y Y Y Y Y Y Y Y Y
spanish es Y Y Y Y(spa) Y Y Y Y Y Y Y
portuguese pt Y Y Y(pt/pt-pt) Y Y Y Y Y Y Y
italian it Y Y Y Y Y Y Y Y Y Y
japanese ja Y Y Y Y(jp) Y Y Y Y Y Y
korean ko Y Y Y Y(kor) Y Y Y Y
greek el Y Y Y Y Y Y
dutch nl Y Y Y Y Y Y Y
hindi hi Y Y Y Y Y Y
turkish tr Y Y Y Y Y Y Y
malay ms Y Y Y Y Y
thai th Y Y Y Y Y Y Y
vietnamese vi Y Y Y Y(vie) Y Y Y Y Y
indonesian id Y Y Y Y Y Y Y Y
hebrew he Y(iw) Y Y Y
polish pl Y Y Y Y Y Y Y
mongolian mn Y Y Y(nm)
czech cs Y Y Y Y Y Y
hungarian hu Y Y Y Y Y Y
estonian et Y Y Y Y(est) Y Y
bulgarian bg Y Y Y Y(bul) Y Y
danish da Y Y Y Y(dan) Y Y
finnish fi Y Y Y Y(fin) Y Y
romanian ro Y Y Y Y(rom) Y Y
swedish sv Y Y Y Y(swe) Y Y
slovenian sl Y Y Y Y(slo) Y Y
persian/farsi fa Y Y Y Y
bosnian bs Y Y Y(bs-Latn) Y(bs-Latn)
serbian sr Y Y Y(sr-Latn/sr-Cyrl) Y(sr-Latn/sr-Cyrl)
fijian fj Y Y
filipino tl Y Y Y(fil) Y(fil)
haitiancreole ht Y Y Y Y
catalan ca Y Y Y Y
croatian hr Y Y Y Y
latvian lv Y Y Y Y Y
lithuanian lt Y Y Y Y Y
urdu ur Y Y Y Y
ukrainian uk Y Y Y Y
welsh cy Y Y Y Y
tahiti ty Y Y
tongan to Y Y
swahili sw Y Y Y Y
samoan sm Y Y Y
slovak sk Y Y Y Y Y
afrikaans af Y Y Y Y
norwegian no Y Y Y Y
bengali bn Y Y Y(bn-BD) Y
malagasy mg Y Y Y Y
maltese mt Y Y Y Y
queretaro otomi otq Y Y
klingon/tlhingan hol tlh Y Y
gujarati gu Y Y Y
tamil ta Y Y Y
telugu te Y Y Y
punjabi pa Y Y Y
amharic am Y Y
azerbaijani az Y Y
bashkir ba Y
belarusian be Y Y
cebuano ceb Y Y
chuvash cv Y
esperanto eo Y Y
basque eu Y Y
irish ga Y Y Y
emoji emj Y
... ...

More supported language, eg:

# request once first, then:
print(ts._google.language_map)

About Chinese Language

Language Language of Translator Google Yandex Bing Baidu Alibaba Tencent Youdao Sogou Iciba Iflytek Caiyun Deepl Argos
Chinese(简体) zh-CHS Y(zh-CN) Y(zh) Y(zh-Hans) Y(zh) Y(zh) Y(zh) Y Y Y(zh) Y(zh) Y(zh) Y(zh) Y(zh)
Chinese(繁体) zh-CHT Y(zh-TW) Y(zh-Hant) Y(cht) Y(zh-TW) Y Y(cnt)
Chinese(文言文) wyw Y
Chinese(粤语) yue Y Y Y Y Y
Chinese(内蒙语) mn N[外蒙] N[外蒙] Y[内蒙]
Chinese(维吾尔语) uy Y
Chinese(藏语) ti Y
Chinese(白苗文) mww Y Y Y
Chinese(彝语) ii Y

License

MIT Llicense

The code for the Subformer, from the EMNLP 2021 Findings paper: "Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers", by Machel Reid, Edison Marrese-Taylor, and Yutaka Matsuo

Subformer This repository contains the code for the Subformer. To help overcome this we propose the Subformer, allowing us to retain performance while

Machel Reid 10 Dec 27, 2022
Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

LancoPKU 105 Jan 03, 2023
Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation This is the official PyTorch implementation

Salesforce 564 Jan 08, 2023
Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing

Introduction Funnel-Transformer is a new self-attention model that gradually compresses the sequence of hidden states to a shorter one and hence reduc

GUOKUN LAI 197 Dec 11, 2022
Reading Wikipedia to Answer Open-Domain Questions

DrQA This is a PyTorch implementation of the DrQA system described in the ACL 2017 paper Reading Wikipedia to Answer Open-Domain Questions. Quick Link

Facebook Research 4.3k Jan 01, 2023
pyMorfologik MorfologikpyMorfologik - Python binding for Morfologik.

Python binding for Morfologik Morfologik is Polish morphological analyzer. For more information see http://github.com/morfologik/morfologik-stemming/

Damian Mirecki 18 Dec 29, 2021
Easy Language Model Pretraining leveraging Huggingface's Transformers and Datasets

Easy Language Model Pretraining leveraging Huggingface's Transformers and Datasets What is LASSL • How to Use What is LASSL LASSL은 LAnguage Semi-Super

LASSL: LAnguage Self-Supervised Learning 116 Dec 27, 2022
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

NL-Augmenter 🦎 → 🐍 The NL-Augmenter is a collaborative effort intended to add transformations of datasets dealing with natural language. Transformat

684 Jan 09, 2023
Google and Stanford University released a new pre-trained model called ELECTRA

Google and Stanford University released a new pre-trained model called ELECTRA, which has a much compact model size and relatively competitive performance compared to BERT and its variants. For furth

Yiming Cui 1.2k Dec 30, 2022
Semantic search through a vectorized Wikipedia (SentenceBERT) with the Weaviate vector search engine

Semantic search through Wikipedia with the Weaviate vector search engine Weaviate is an open source vector search engine with build-in vectorization a

SeMI Technologies 191 Dec 26, 2022
A Chinese to English Neural Model Translation Project

ZH-EN NMT Chinese to English Neural Machine Translation This project is inspired by Stanford's CS224N NMT Project Dataset used in this project: News C

Zhenbang Feng 29 Nov 26, 2022
A simple chatbot based on chatterbot that you can use for anything has basic features

Chatbotium A simple chatbot based on chatterbot that you can use for anything has basic features. I have some errors Read the paragraph below: Known b

Herman 1 Feb 16, 2022
IEEEXtreme15.0 Questions And Answers

IEEEXtreme15.0 Questions And Answers IEEEXtreme is a global challenge in which teams of IEEE Student members – advised and proctored by an IEEE member

Dilan Perera 15 Oct 24, 2022
TaCL: Improve BERT Pre-training with Token-aware Contrastive Learning

TaCL: Improve BERT Pre-training with Token-aware Contrastive Learning

Yixuan Su 26 Oct 17, 2022
A Transformer Implementation that is easy to understand and customizable.

Simple Transformer I've written a series of articles on the transformer architecture and language models on Medium. This repository contains an implem

Naoki Shibuya 4 Jan 20, 2022
Understand Text Summarization and create your own summarizer in python

Automatic summarization is the process of shortening a text document with software, in order to create a summary with the major points of the original document. Technologies that can make a coherent

Sreekanth M 1 Oct 18, 2022
Deduplication is the task to combine different representations of the same real world entity.

Deduplication is the task to combine different representations of the same real world entity. This package implements deduplication using active learning. Active learning allows for rapid training wi

63 Nov 17, 2022
To create a deep learning model which can explain the content of an image in the form of speech through caption generation with attention mechanism on Flickr8K dataset.

To create a deep learning model which can explain the content of an image in the form of speech through caption generation with attention mechanism on Flickr8K dataset.

Ragesh Hajela 0 Feb 08, 2022
Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Silero Models: pre-trained speech-to-text, text-to-speech models and benchmarks made embarrassingly simple

Alexander Veysov 3.2k Dec 31, 2022
Utilizing RBERT model for KLUE Relation Extraction task

RBERT for Relation Extraction task for KLUE Project Description Relation Extraction task is one of the task of Korean Language Understanding Evaluatio

snoop2head 14 Nov 15, 2022