Feat/add target lang choices (#12)

* Feat: add multipile languages choices and a new argument language to set targett language

Co-authored-by: yihong0618 <zouzou0208@gmail.com>

.github/workflows/make_test_ebook.yaml

@@ -26,4 +26,4 @@ jobs:
       - name: make test ebook
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-        run: python3 make_book.py --book_name test_books/animal_farm.epub --no_limit --test --test_num 2
+        run: python3 make_book.py --book_name test_books/animal_farm.epub --no_limit --test --test_num 2 --language zh-hans

README.md

@@ -19,16 +19,19 @@ Make bilingual epub books Using AI translate
 3. 本地放了一个 animal_farm.epub 给大家测试
 4. 默认用了 ChatGPT 模型，用 `--model gpt3` 来使用 gpt3 模型
 5. 加了 `--test` 命令如果大家没付费可以加上这个先看看效果（有 limit 稍微有些慢）
+6. Set the target language like `--language "Simplified Chinese"`. 
+   Suppot ` "Japanese" / "Traditional Chinese" / "German" / "French" / "Korean"`.
+   Default target language is `"Simplified Chinese"`. Support language list please see the LANGUAGES at [utils.py](./utils.py).
 
 e.g.
 ```shell
 # 如果你想快速测一下
-python3 make_book.py --book_name test_books/animal_farm.epub --openai_key ${openai_key} --no_limit --test
+python3 make_book.py --book_name test_books/animal_farm.epub --openai_key ${openai_key} --no_limit --test --language "Simplified Chinese"
 # or do it
-python3 make_book.py --book_name test_books/animal_farm.epub --openai_key ${openai_key}
+python3 make_book.py --book_name test_books/animal_farm.epub --openai_key ${openai_key} --language "Simplified Chinese"
 # or 用 gpt3 模型
 export OPENAI_API_KEY=${your_api_key}
-python3 make_book.py --book_name test_books/animal_farm.epub --model gpt3 --no_limit
+python3 make_book.py --book_name test_books/animal_farm.epub --model gpt3 --no_limit --language "Simplified Chinese"
 ```
 
 ## 注意

make_book.py

@@ -11,6 +11,7 @@ import requests
 from bs4 import BeautifulSoup as bs
 from ebooklib import epub
 from rich import print
+from utils import LANGUAGES, TO_LANGUAGE_CODE
 
 NO_LIMIT = False
 IS_TEST = False
@@ -18,7 +19,7 @@ RESUME = False
 
 
 class Base:
-    def __init__(self, key):
+    def __init__(self, key, language):
         pass
 
     @abstractmethod
@@ -27,7 +28,7 @@ class Base:
 
 
 class GPT3(Base):
-    def __init__(self, key):
+    def __init__(self, key, language):
         self.api_key = key
         self.api_url = "https://api.openai.com/v1/completions"
         self.headers = {
@@ -43,10 +44,11 @@ class GPT3(Base):
             "top_p": 1,
         }
         self.session = requests.session()
+        self.language = language
 
     def translate(self, text):
         print(text)
-        self.data["prompt"] = f"Please help me to translate，`{text}` to Chinese"
+        self.data["prompt"] = f"Please help me to translate，`{text}` to {self.language}"
         r = self.session.post(self.api_url, headers=self.headers, json=self.data)
         if not r.ok:
             return text
@@ -64,12 +66,14 @@ class DeepL(Base):
 
 
 class ChatGPT(Base):
-    def __init__(self, key):
+    def __init__(self, key, language):
-        super().__init__(key)
+        super().__init__(key, language)
         self.key = key
+        self.language = language
 
     def translate(self, text):
         print(text)
+        print(self.language, "!!!")
         openai.api_key = self.key
         try:
             completion = openai.ChatCompletion.create(
@@ -78,7 +82,7 @@ class ChatGPT(Base):
                     {
                         "role": "user",
                         # english prompt here to save tokens
-                        "content": f"Please help me to translate，`{text}` to Chinese, please return only translated content not include the origin text",
+                        "content": f"Please help me to translate，`{text}` to {self.language}, please return only translated content not include the origin text",
                     }
                 ],
             )
@@ -117,10 +121,10 @@ class ChatGPT(Base):
 
 
 class BEPUB:
-    def __init__(self, epub_name, model, key, resume):
+    def __init__(self, epub_name, model, key, resume, language):
         self.epub_name = epub_name
         self.new_epub = epub.EpubBook()
-        self.translate_model = model(key)
+        self.translate_model = model(key, language)
         self.origin_book = epub.read_epub(self.epub_name)
         self.p_to_save = []
         self.resume = resume
@@ -236,6 +240,14 @@ if __name__ == "__main__":
         choices=["chatgpt", "gpt3"],  # support DeepL later
         help="Use which model",
     )
+    parser.add_argument(
+        "--language",
+        type=str,
+        choices=sorted(LANGUAGES.keys())
+        + sorted([k.title() for k in TO_LANGUAGE_CODE.keys()]),
+        default="zh-hans",
+        help="language to translate to",
+    )
     parser.add_argument(
         "--resume",
         dest="resume",
@@ -253,5 +265,10 @@ if __name__ == "__main__":
     if not options.book_name.endswith(".epub"):
         raise Exception("please use epub file")
     model = MODEL_DICT.get(options.model, "chatgpt")
-    e = BEPUB(options.book_name, model, OPENAI_API_KEY, RESUME)
+    language = options.language
+    if options.language in LANGUAGES:
+        # use the value for prompt
+        language = LANGUAGES.get(language, language)
+
+    e = BEPUB(options.book_name, model, OPENAI_API_KEY, RESUME, language=language)
     e.make_bilingual_book()

utils.py

@@ -0,0 +1,119 @@
+# Borrowed from : https://github.com/openai/whisper
+LANGUAGES = {
+    "en": "english",
+    "zh-hans": "simplified chinese",
+    "zh-hant": "traditional chinese",
+    "de": "german",
+    "es": "spanish",
+    "ru": "russian",
+    "ko": "korean",
+    "fr": "french",
+    "ja": "japanese",
+    "pt": "portuguese",
+    "tr": "turkish",
+    "pl": "polish",
+    "ca": "catalan",
+    "nl": "dutch",
+    "ar": "arabic",
+    "sv": "swedish",
+    "it": "italian",
+    "id": "indonesian",
+    "hi": "hindi",
+    "fi": "finnish",
+    "vi": "vietnamese",
+    "he": "hebrew",
+    "uk": "ukrainian",
+    "el": "greek",
+    "ms": "malay",
+    "cs": "czech",
+    "ro": "romanian",
+    "da": "danish",
+    "hu": "hungarian",
+    "ta": "tamil",
+    "no": "norwegian",
+    "th": "thai",
+    "ur": "urdu",
+    "hr": "croatian",
+    "bg": "bulgarian",
+    "lt": "lithuanian",
+    "la": "latin",
+    "mi": "maori",
+    "ml": "malayalam",
+    "cy": "welsh",
+    "sk": "slovak",
+    "te": "telugu",
+    "fa": "persian",
+    "lv": "latvian",
+    "bn": "bengali",
+    "sr": "serbian",
+    "az": "azerbaijani",
+    "sl": "slovenian",
+    "kn": "kannada",
+    "et": "estonian",
+    "mk": "macedonian",
+    "br": "breton",
+    "eu": "basque",
+    "is": "icelandic",
+    "hy": "armenian",
+    "ne": "nepali",
+    "mn": "mongolian",
+    "bs": "bosnian",
+    "kk": "kazakh",
+    "sq": "albanian",
+    "sw": "swahili",
+    "gl": "galician",
+    "mr": "marathi",
+    "pa": "punjabi",
+    "si": "sinhala",
+    "km": "khmer",
+    "sn": "shona",
+    "yo": "yoruba",
+    "so": "somali",
+    "af": "afrikaans",
+    "oc": "occitan",
+    "ka": "georgian",
+    "be": "belarusian",
+    "tg": "tajik",
+    "sd": "sindhi",
+    "gu": "gujarati",
+    "am": "amharic",
+    "yi": "yiddish",
+    "lo": "lao",
+    "uz": "uzbek",
+    "fo": "faroese",
+    "ht": "haitian creole",
+    "ps": "pashto",
+    "tk": "turkmen",
+    "nn": "nynorsk",
+    "mt": "maltese",
+    "sa": "sanskrit",
+    "lb": "luxembourgish",
+    "my": "myanmar",
+    "bo": "tibetan",
+    "tl": "tagalog",
+    "mg": "malagasy",
+    "as": "assamese",
+    "tt": "tatar",
+    "haw": "hawaiian",
+    "ln": "lingala",
+    "ha": "hausa",
+    "ba": "bashkir",
+    "jw": "javanese",
+    "su": "sundanese",
+}
+
+# language code lookup by name, with a few language aliases
+TO_LANGUAGE_CODE = {
+    **{language: code for code, language in LANGUAGES.items()},
+    "burmese": "my",
+    "valencian": "ca",
+    "flemish": "nl",
+    "haitian": "ht",
+    "letzeburgesch": "lb",
+    "pushto": "ps",
+    "panjabi": "pa",
+    "moldavian": "ro",
+    "moldovan": "ro",
+    "sinhalese": "si",
+    "castilian": "es",
+}