feat(sysaudio): 支持 macOS 系统音频流采集

- 新增 darwin.py 文件实现 macOS 音频流采集功能
- 修改 main-gummy.py 以支持 macOS 平台
- 更新 AllConfig 和 CaptionEngine 以适配新平台

caption-engine/main-gummy.py

@@ -3,6 +3,8 @@ import argparse
 
 if sys.platform == 'win32':
     from sysaudio.win import AudioStream
+elif sys.platform == 'darwin':
+    from sysaudio.darwin import AudioStream
 elif sys.platform == 'linux':
     from sysaudio.linux import AudioStream
 else:
@@ -12,9 +14,9 @@ from audioprcs import mergeChunkChannels
 from audio2text import InvalidParameter, GummyTranslator
 
 
-def convert_audio_to_text(s_lang, t_lang, audio_type):
+def convert_audio_to_text(s_lang, t_lang, audio_type, chunk_rate):
     sys.stdout.reconfigure(line_buffering=True) # type: ignore
-    stream = AudioStream(audio_type)
+    stream = AudioStream(audio_type, chunk_rate)
 
     if t_lang == 'none':
         gummy = GummyTranslator(stream.RATE, s_lang, None)
@@ -43,10 +45,12 @@ if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='Convert system audio stream to text')
     parser.add_argument('-s', '--source_language', default='en', help='Source language code')
     parser.add_argument('-t', '--target_language', default='zh', help='Target language code')
-    parser.add_argument('-a', '--audio_type', default='0', help='Audio stream source: 0 for output audio stream, 1 for input audio stream')
+    parser.add_argument('-a', '--audio_type', default=0, help='Audio stream source: 0 for output audio stream, 1 for input audio stream')
+    parser.add_argument('-c', '--chunk_rate', default=20, help='The number of audio stream chunks collected per second.')
     args = parser.parse_args()
     convert_audio_to_text(
         args.source_language,
         args.target_language,
-        int(args.audio_type)
+        int(args.audio_type),
+        int(args.chunk_rate)
     )