Awesome
中文 | English
bilingual_book_maker
The bilingual_book_maker is an AI translation tool that uses ChatGPT to assist users in creating multi-language versions of epub/txt/srt files and books. This tool is exclusively designed for translating epub books that have entered the public domain and is not intended for copyrighted works. Before using this tool, please review the project's disclaimer.
Supported Models
gpt-4, gpt-3.5-turbo, claude-2, palm, llama-2, azure-openai, command-nightly, gemini
For using Non-OpenAI models, use class liteLLM()
- liteLLM supports all models above.
Find more info here for using liteLLM: https://github.com/BerriAI/litellm/blob/main/setup.py
Preparation
- ChatGPT or OpenAI token 1
- epub/txt books
- Environment with internet access or proxy
- Python 3.8+
Use
pip install -r requirements.txt
orpip install -U bbook_maker
(you can use)- Use
--openai_key
option to specify OpenAI API key. If you have multiple keys, separate them by commas (xxx,xxx,xxx) to reduce errors caused by API call limits. Or, just set environment variableBBM_OPENAI_API_KEY
instead. - A sample book,
test_books/animal_farm.epub
, is provided for testing purposes. - The default underlying model is GPT-3.5-turbo, which is used by ChatGPT currently. Use
--model gpt4
to change the underlying model toGPT4
. You can also useGPT4omini
.- Important to note that
gpt-4
is significantly more expensive thangpt-4-turbo
, but to avoid bumping into rate limits, we automatically balance queries acrossgpt-4-1106-preview
,gpt-4
,gpt-4-32k
,gpt-4-0613
,gpt-4-32k-0613
.- If you want to use a specific model alias with OpenAI (eg
gpt-4-1106-preview
orgpt-3.5-turbo-0125
), you can use--model openai --model_list gpt-4-1106-preview,gpt-3.5-turbo-0125
.--model_list
takes a comma-separated list of model aliases.
- If you want to use a specific model alias with OpenAI (eg
- If using chatgptapi, you can add
--use_context
to add a context paragraph to each passage sent to the model for translation (see below).
- Important to note that
- Support DeepL model DeepL Translator need pay to get the token use
--model deepl --deepl_key ${deepl_key}
- Support DeepL free model
--model deeplfree
- Support Google Gemini model
--model gemini --gemini_key ${gemini_key}
- Support Claude model, use
--model claude --claude_key ${claude_key}
- Support Tencent TranSmart model (Free), use
--model tencentransmart
- Support Ollama self-host models, use
--ollama_model ${ollama_model_name}
- If ollama server is not running on localhost, use
--api_base http://x.x.x.x:port/v1
to point to the ollama server address
- If ollama server is not running on localhost, use
- Use
--test
option to preview the result if you haven't paid for the service. Note that there is a limit and it may take some time. - Set the target language like
--language "Simplified Chinese"
. Default target language is"Simplified Chinese"
. Read available languages by helper message:python make_book.py --help
- Use
--proxy
option to specify proxy server for internet access. Enter a string such ashttp://127.0.0.1:7890
. - Use
--resume
option to manually resume the process after an interruption. - epub is made of html files. By default, we only translate contents in
<p>
. Use--translate-tags
to specify tags need for translation. Use comma to separate multiple tags. For example:--translate-tags h1,h2,h3,p,div
- Use
--book_from
option to specify e-reader type (Now onlykobo
is available), and use--device_path
to specify the mounting point. - If you want to change api_base like using Cloudflare Workers, use
--api_base <URL>
to support it. Note: the api url should be 'https://xxxx/v1
'. Quotation marks are required. - Once the translation is complete, a bilingual book named
${book_name}_bilingual.epub
would be generated. - If there are any errors or you wish to interrupt the translation by pressing
CTRL+C
. A book named${book_name}_bilingual_temp.epub
would be generated. You can simply rename it to any desired name. - If you want to translate strings in an e-book that aren't labeled with any tags, you can use the
--allow_navigable_strings
parameter. This will add the strings to the translation queue. Note that it's best to look for e-books that are more standardized if possible. - To tweak the prompt, use the
--prompt
parameter. Valid placeholders for theuser
role template include{text}
and{language}
. It supports a few ways to configure the prompt: If you don't need to set thesystem
role content, you can simply set it up like this:--prompt "Translate {text} to {language}."
or--prompt prompt_template_sample.txt
(example of a text file can be found at ./prompt_template_sample.txt). If you need to set thesystem
role content, you can use the following format:--prompt '{"user":"Translate {text} to {language}", "system": "You are a professional translator."}'
or--prompt prompt_template_sample.json
(example of a JSON file can be found at ./prompt_template_sample.json). You can also set theuser
andsystem
role prompt by setting environment variables:BBM_CHATGPTAPI_USER_MSG_TEMPLATE
andBBM_CHATGPTAPI_SYS_MSG
. - Use the
--batch_size
parameter to specify the number of lines for batch translation (default is 10, currently only effective for txt files). --accumulated_num
Wait for how many tokens have been accumulated before starting the translation. gpt3.5 limits the total_token to 4090. For example, if you use --accumulated_num 1600, maybe openai will output 2200 tokens and maybe 200 tokens for other messages in the system messages user messages, 1600+2200+200=4000, So you are close to reaching the limit. You have to choose your own value, there is no way to know if the limit is reached before sending--use_context
prompts the model to create a three-paragraph summary. If it's the beginning of the translation, it will summarize the entire passage sent (the size depending on--accumulated_num
). For subsequent passages, it will amend the summary to include details from the most recent passage, creating a running one-paragraph context payload of the important details of the entire translated work. This improves consistency of flow and tone throughout the translation. This option is available for all ChatGPT-compatible models.- Use
--context_paragraph_limit
to set a limit on the number of context paragraphs when using the--use_context
option. - Use
--temperature
to set the temperature parameter forchatgptapi
/gpt4
/claude
models. For example:--temperature 0.7
. - Use
--block_size
to merge multiple paragraphs into one block. This may increase accuracy and speed up the process but can disturb the original format. Must be used with--single_translate
. For example:--block_size 5
. - Use
--single_translate
to output only the translated book without creating a bilingual version. --translation_style
example:--translation_style "color: #808080; font-style: italic;"
--retranslate
--retranslate "$translated_filepath" "file_name_in_epub" "start_str" "end_str"(optional)
<br> Retranslate from start_str to end_str's tag:python3 "make_book.py" --book_name "test_books/animal_farm.epub" --retranslate 'test_books/animal_farm_bilingual.epub' 'index_split_002.html' 'in spite of the present book shortage which' 'This kind of thing is not a good symptom. Obviously'
<br> Retranslate start_str's tag:python3 "make_book.py" --book_name "test_books/animal_farm.epub" --retranslate 'test_books/animal_farm_bilingual.epub' 'index_split_002.html' 'in spite of the present book shortage which'
Examples
Note if use pip install bbook_maker
all commands can change to bbook_maker args
# Test quickly
python3 make_book.py --book_name test_books/animal_farm.epub --openai_key ${openai_key} --test --language zh-hans
# Test quickly for src
python3 make_book.py --book_name test_books/Lex_Fridman_episode_322.srt --openai_key ${openai_key} --test
# Or translate the whole book
python3 make_book.py --book_name test_books/animal_farm.epub --openai_key ${openai_key} --language zh-hans
# Or translate the whole book using Gemini
python3 make_book.py --book_name test_books/animal_farm.epub --gemini_key ${gemini_key} --model gemini
# Set env OPENAI_API_KEY to ignore option --openai_key
export OPENAI_API_KEY=${your_api_key}
# Use the GPT-4 model with context to Japanese
python3 make_book.py --book_name test_books/animal_farm.epub --model gpt4 --use_context --language ja
# Use a specific OpenAI model alias
python3 make_book.py --book_name test_books/animal_farm.epub --model openai --model_list gpt-4-1106-preview --openai_key ${openai_key}
**Note** you can use other `openai like` model in this way
python3 make_book.py --book_name test_books/animal_farm.epub --model openai --model_list yi-34b-chat-0205 --openai_key ${openai_key} --api_base "https://api.lingyiwanwu.com/v1"
# Use a specific list of OpenAI model aliases
python3 make_book.py --book_name test_books/animal_farm.epub --model openai --model_list gpt-4-1106-preview,gpt-4-0125-preview,gpt-3.5-turbo-0125 --openai_key ${openai_key}
# Use the DeepL model with Japanese
python3 make_book.py --book_name test_books/animal_farm.epub --model deepl --deepl_key ${deepl_key} --language ja
# Use the Claude model with Japanese
python3 make_book.py --book_name test_books/animal_farm.epub --model claude --claude_key ${claude_key} --language ja
# Use the CustomAPI model with Japanese
python3 make_book.py --book_name test_books/animal_farm.epub --model customapi --custom_api ${custom_api} --language ja
# Translate contents in <div> and <p>
python3 make_book.py --book_name test_books/animal_farm.epub --translate-tags div,p
# Tweaking the prompt
python3 make_book.py --book_name test_books/animal_farm.epub --prompt prompt_template_sample.txt
# or
python3 make_book.py --book_name test_books/animal_farm.epub --prompt prompt_template_sample.json
# or
python3 make_book.py --book_name test_books/animal_farm.epub --prompt "Please translate \`{text}\` to {language}"
# Translate books download from Rakuten Kobo on kobo e-reader
python3 make_book.py --book_from kobo --device_path /tmp/kobo
# translate txt file
python3 make_book.py --book_name test_books/the_little_prince.txt --test --language zh-hans
# aggregated translation txt file
python3 make_book.py --book_name test_books/the_little_prince.txt --test --batch_size 20
# Using Caiyun model to translate
# (the api currently only support: simplified chinese <-> english, simplified chinese <-> japanese)
# the official Caiyun has provided a test token (3975l6lr5pcbvidl6jl2)
# you can apply your own token by following this tutorial(https://bobtranslate.com/service/translate/caiyun.html)
python3 make_book.py --model caiyun --caiyun_key 3975l6lr5pcbvidl6jl2 --book_name test_books/animal_farm.epub
# Set env BBM_CAIYUN_API_KEY to ignore option --openai_key
export BBM_CAIYUN_API_KEY=${your_api_key}
More understandable example
python3 make_book.py --book_name 'animal_farm.epub' --openai_key sk-XXXXX --api_base 'https://xxxxx/v1'
# Or python3 is not in your PATH
python make_book.py --book_name 'animal_farm.epub' --openai_key sk-XXXXX --api_base 'https://xxxxx/v1'
Microsoft Azure Endpoints
python3 make_book.py --book_name 'animal_farm.epub' --openai_key XXXXX --api_base 'https://example-endpoint.openai.azure.com' --deployment_id 'deployment-name'
# Or python3 is not in your PATH
python make_book.py --book_name 'animal_farm.epub' --openai_key XXXXX --api_base 'https://example-endpoint.openai.azure.com' --deployment_id 'deployment-name'
Docker
You can use Docker if you don't want to deal with setting up the environment.
# Build image
docker build --tag bilingual_book_maker .
# Run container
# "$folder_path" represents the folder where your book file locates. Also, it is where the processed file will be stored.
# Windows PowerShell
$folder_path=your_folder_path # $folder_path="C:\Users\user\mybook\"
$book_name=your_book_name # $book_name="animal_farm.epub"
$openai_key=your_api_key # $openai_key="sk-xxx"
$language=your_language # see utils.py
docker run --rm --name bilingual_book_maker --mount type=bind,source=$folder_path,target='/app/test_books' bilingual_book_maker --book_name "/app/test_books/$book_name" --openai_key $openai_key --language $language
# Linux
export folder_path=${your_folder_path}
export book_name=${your_book_name}
export openai_key=${your_api_key}
export language=${your_language}
docker run --rm --name bilingual_book_maker --mount type=bind,source=${folder_path},target='/app/test_books' bilingual_book_maker --book_name "/app/test_books/${book_name}" --openai_key ${openai_key} --language "${language}"
For example:
# Linux
docker run --rm --name bilingual_book_maker --mount type=bind,source=/home/user/my_books,target='/app/test_books' bilingual_book_maker --book_name /app/test_books/animal_farm.epub --openai_key sk-XXX --test --test_num 1 --language zh-hant
Notes
- API token from free trial has limit. If you want to speed up the process, consider paying for the service or use multiple OpenAI tokens
- PR is welcome
Thanks
Contribution
- Any issues or PRs are welcome.
- TODOs in the issue can also be selected.
- Please run
black make_book.py
2 before submitting the code.
Others better
- 书译 iOS -> AI 全书翻译工具
Appreciation
Thank you, that's enough.