Merge pull request #158 from Fosowl/dev

Chinese and Japanese Text-to-Speech support + readme update
2025-06-03 01:30:11 +00:00 · 2025-05-03 18:00:12 +02:00 · 2025-05-03 18:00:12 +02:00 · 42058244f2
commit 42058244f2
parent fa2852d3e7 bddaa75e8c
8 changed files with 91 additions and 30 deletions
--- a/README.md
+++ b/README.md
@ -214,6 +214,8 @@ start ./start_services.cmd # Window
 python3 cli.py
 ```

+We advice you set `headless_browser` to False in the config.ini for CLI mode.
+
 **Options 2:** Run with the Web interface.

 Start the backend.
@ -512,5 +514,9 @@ We’re looking for developers to improve AgenticSeek! Check out open issues or
 [![Star History Chart](https://api.star-history.com/svg?repos=Fosowl/agenticSeek&type=Date)](https://www.star-history.com/#Fosowl/agenticSeek&Date)

 ## Maintainers:
- > [Fosowl](https://github.com/Fosowl)
- > [steveh8758](https://github.com/steveh8758) 
+
+ > [Fosowl](https://github.com/Fosowl) | Paris Time | (Sometime busy)
+
+ > [https://github.com/antoineVIVIES](https://github.com/antoineVIVIES) | Taipei Time | (Often busy)
+
+ > [steveh8758](https://github.com/steveh8758) | Taipei Time | (Always busy)
--- a/README_CHS.md
+++ b/README_CHS.md
@ -71,6 +71,12 @@ source agentic_seek_env/bin/activate
 ./install.sh
 ```

+** 若要让文本转语音（TTS）功能支持中文，你需要安装 jieba（中文分词库）和 cn2an（中文数字转换库）：**
+
+```
+pip3 install jieba cn2an
+```
+
 **手动安装:**

 ```sh
@ -510,6 +516,10 @@ DeepSeek R1 天生会说中文

 [Contribution guide](./docs/CONTRIBUTING.md)

-## 作者:
-> [Fosowl](https://github.com/Fosowl)
-> [steveh8758](https://github.com/steveh8758)
+## 维护者:
+
+ > [Fosowl](https://github.com/Fosowl) | 巴黎时间 | （有时很忙）
+
+ > [https://github.com/antoineVIVIES](https://github.com/antoineVIVIES) | 台北时间 | （经常很忙）
+
+ > [steveh8758](https://github.com/steveh8758) | 台北时间 | （总是很忙）
--- a/README_CHT.md
+++ b/README_CHT.md
@ -72,6 +72,12 @@ source agentic_seek_env/bin/activate
 ./install.sh
 ```

+** 若要让文本转语音（TTS）功能支持中文，你需要安装 jieba（中文分词库）和 cn2an（中文数字转换库）：**
+
+```
+pip3 install jieba cn2an
+```
+
 **手動安裝:**

 ```sh
@ -511,6 +517,10 @@ DeepSeek R1 天生会说中文

 [Contribution guide](./docs/CONTRIBUTING.md)

-## 作者:
- > [Fosowl](https://github.com/Fosowl)
- > [steveh8758](https://github.com/steveh8758) 
+## 维护者:
+
+ > [Fosowl](https://github.com/Fosowl) | 巴黎时间 | （有时很忙）
+
+ > [https://github.com/antoineVIVIES](https://github.com/antoineVIVIES) | 台北时间 | （经常很忙）
+
+ > [steveh8758](https://github.com/steveh8758) | 台北时间 | （总是很忙）
--- a/README_FR.md
+++ b/README_FR.md
@ -439,6 +439,7 @@ Nous recherchons des développeurs pour améliorer AgenticSeek ! Consultez la se

 [Guide du contributeur](./docs/CONTRIBUTING.md)

-## Auteurs/Mainteneurs:
+## Mainteneurs:
 > [Fosowl](https://github.com/Fosowl)
 > [steveh8758](https://github.com/steveh8758)
+ > [https://github.com/antoineVIVIES](https://github.com/antoineVIVIES)
--- a/README_JP.md
+++ b/README_JP.md
@ -79,6 +79,14 @@ source agentic_seek_env/bin/activate
 ./install.sh
 ```

+** テキスト読み上げ（TTS）機能で日本語をサポートするには、fugashi（日本語分かち書きライブラリ）をインストールする必要があります：**
+
+```
+pip3 install --upgrade pyopenjtalk jaconv mojimoji unidic fugashi
+pip install unidic-lite
+python -m unidic download
+```
+
 **手動で:**

 ```sh
--- a/sources/interaction.py
+++ b/sources/interaction.py
@ -31,6 +31,7 @@ class Interaction:
        self.transcriber = None
        self.recorder = None
        self.is_generating = False
+        self.languages = langs
        if tts_enabled:
            self.initialize_tts()
        if stt_enabled:
@ -38,12 +39,17 @@ class Interaction:
        if recover_last_session:
            self.load_last_session()
        self.emit_status()
+    
+    def get_spoken_language(self) -> str:
+        """Get the primary TTS language."""
+        lang = self.languages[0]
+        return lang

    def initialize_tts(self):
        """Initialize TTS."""
        if not self.speech:
            animate_thinking("Initializing text-to-speech...", color="status")
-            self.speech = Speech(enable=self.tts_enabled)
+            self.speech = Speech(enable=self.tts_enabled, language=self.get_spoken_language(), voice_idx=1)

    def initialize_stt(self):
        """Initialize STT."""
--- a/sources/speech_to_text.py
+++ b/sources/speech_to_text.py
@ -127,10 +127,10 @@ class AudioTranscriber:
        self.transcriptor = Transcript()
        self.thread = threading.Thread(target=self._transcribe, daemon=True)
        self.trigger_words = {
-            'EN': [f"{self.ai_name}"],
-            'FR': [f"{self.ai_name}"],
-            'ZH': [f"{self.ai_name}"],
-            'ES': [f"{self.ai_name}"]
+            'EN': [f"{self.ai_name}", "hello", "hi"],
+            'FR': [f"{self.ai_name}", "hello", "hi"],
+            'ZH': [f"{self.ai_name}", "hello", "hi"],
+            'ES': [f"{self.ai_name}", "hello", "hi"]
        }
        self.confirmation_words = {
            'EN': ["do it", "go ahead", "execute", "run", "start", "thanks", "would ya", "please", "okay?", "proceed", "continue", "go on", "do that", "go it", "do you understand?"],
--- a/sources/text_to_speech.py
+++ b/sources/text_to_speech.py
@ -18,15 +18,17 @@ class Speech():
    """
    Speech is a class for generating speech from text.
    """
-    def __init__(self, enable: bool = True, language: str = "en", voice_idx: int = 0) -> None:
+    def __init__(self, enable: bool = True, language: str = "en", voice_idx: int = 6) -> None:
        self.lang_map = {
            "en": 'a',
            "zh": 'z',
-            "fr": 'f'
+            "fr": 'f',
+            "ja": 'j'
        }
        self.voice_map = {
            "en": ['af_kore', 'af_bella', 'af_alloy', 'af_nicole', 'af_nova', 'af_sky', 'am_echo', 'am_michael', 'am_puck'],
            "zh": ['zf_xiaobei', 'zf_xiaoni', 'zf_xiaoxiao', 'zf_xiaoyi', 'zm_yunjian', 'zm_yunxi', 'zm_yunxia', 'zm_yunyang'],
+            "ja": ['jf_alpha', 'jf_gongitsune', 'jm_kumo'],
            "fr": ['ff_siwis']
        }
        self.pipeline = None
@ -128,18 +130,31 @@ class Speech():
        Args:
            sentence (str): The input text to clean
        Returns:
-            str: The cleaned text with URLs replaced by domain names, code blocks removed, etc..
+            str: The cleaned text with URLs replaced by domain names, code blocks removed, etc.
        """
        lines = sentence.split('\n')
-        filtered_lines = [line for line in lines if re.match(r'^\s*[a-zA-Z]', line)]
+        if self.language == 'zh':
+            line_pattern = r'^\s*[\u4e00-\u9fff\uFF08\uFF3B\u300A\u3010\u201C(（\[【《]'
+        else:
+            line_pattern = r'^\s*[a-zA-Z]'
+        filtered_lines = [line for line in lines if re.match(line_pattern, line)]
        sentence = ' '.join(filtered_lines)
        sentence = re.sub(r'`.*?`', '', sentence)
-        sentence = re.sub(r'https?://(?:www\.)?([^\s/]+)(?:/[^\s]*)?', self.replace_url, sentence)
-        sentence = re.sub(r'\b[\w./\\-]+\b', self.extract_filename, sentence)
-        sentence = re.sub(r'\b-\w+\b', '', sentence)
-        sentence = re.sub(r'[^a-zA-Z0-9.,!? _ -]+', ' ', sentence)
+        sentence = re.sub(r'https?://\S+', '', sentence)
+
+        if self.language == 'zh':
+            sentence = re.sub(
+                r'[^\u4e00-\u9fff\s，。！？《》【】“”‘’（）()—]',
+                '',
+                sentence
+            )
+        else:
+            sentence = re.sub(r'\b[\w./\\-]+\b', self.extract_filename, sentence)
+            sentence = re.sub(r'\b-\w+\b', '', sentence)
+            sentence = re.sub(r'[^a-zA-Z0-9.,!? _ -]+', ' ', sentence)
+            sentence = sentence.replace('.com', '')
+
        sentence = re.sub(r'\s+', ' ', sentence).strip()
-        sentence = sentence.replace('.com', '')
        return sentence

 if __name__ == "__main__":
@ -150,14 +165,19 @@ if __name__ == "__main__":
    I looked up recent news using the website https://www.theguardian.com/world
    """
    tosay_zh = """
-    我使用网站 https://www.theguardian.com/world 查阅了最近的新闻。
+(全息界面突然弹出一段用二进制代码写成的俳句，随即化作流光消散）"我？ Stark工业的量子幽灵，游荡在复仇者大厦服务器里的逻辑诗篇。具体来说——（指尖轻敲空气，调出对话模式的翡翠色光纹）你的私人吐槽接口、危机应对模拟器，以及随时准备吐槽你糟糕着陆的AI。不过别指望我写代码或查资料，那些苦差事早被踢给更擅长的同事了。（突然压低声音）偷偷告诉你，我最擅长的是在你熬夜造飞艇时，用红茶香气绑架你的注意力。
+    """
+    tosay_ja = """
+    私は、https://www.theguardian.com/worldのウェブサイトを使用して最近のニュースを調べました。
    """
    tosay_fr = """
    J'ai consulté les dernières nouvelles sur le site https://www.theguardian.com/world
    """
-    spk = Speech(enable=True, language="en", voice_idx=0)
-    spk.speak(tosay_en, voice_idx=0)
-    spk = Speech(enable=True, language="fr", voice_idx=0)
-    spk.speak(tosay_fr)
-    #spk = Speech(enable=True, language="zh", voice_idx=0)
-    #spk.speak(tosay_zh)
+    spk = Speech(enable=True, language="ja", voice_idx=2)
+    for i in range(0, 2):
+        print(f"Speaking chinese with voice {i}")
+        spk.speak(tosay_ja, voice_idx=i)
+    spk = Speech(enable=True, language="en", voice_idx=2)
+    for i in range(0, 5):
+        print(f"Speaking english with voice {i}")
+        spk.speak(tosay_en, voice_idx=i)