feat: 增加了音频输入选项，并优化了字幕引擎的构建和运行流程。

- 新增了系统音频输入（麦克风）的选择功能
- 重构了字幕引擎的构建流程，使用 PyInstaller 打包为可执行文件
- 优化了字幕引擎的启动和停止逻辑
- 更新了用户界面，增加了音频选择的控制选项
- 修改了相关的文件路径和构建配置

python-subprocess/main-gummy.py

@@ -0,0 +1,48 @@
+import sys
+
+if sys.platform == 'win32':
+    from sysaudio.win import AudioStream, mergeStreamChannels
+elif sys.platform == 'linux':
+    from sysaudio.linux import AudioStream, mergeStreamChannels
+else:
+    raise NotImplementedError(f"Unsupported platform: {sys.platform}")
+
+from audio2text.gummy import GummyTranslator
+import sys
+import argparse
+
+def convert_audio_to_text(s_lang, t_lang, audio_type):
+    sys.stdout.reconfigure(line_buffering=True)
+    stream = AudioStream(audio_type)
+    stream.openStream()
+
+    if t_lang == 'none':
+        gummy = GummyTranslator(stream.RATE, s_lang, None)
+    else:
+        gummy = GummyTranslator(stream.RATE, s_lang, t_lang)
+    gummy.translator.start()
+
+    while True:
+        try:
+            if not stream.stream: continue
+            data = stream.stream.read(stream.CHUNK)
+            data = mergeStreamChannels(data, stream.CHANNELS)
+            gummy.translator.send_audio_frame(data)
+        except KeyboardInterrupt:
+            stream.closeStream()
+            gummy.translator.stop()
+            break
+
+
+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')
+    args = parser.parse_args()
+    convert_audio_to_text(
+        args.source_language,
+        args.target_language,
+        0 if args.audio_type == '0' else 1
+    )
+    

python-subprocess/main-gummy.spec

@@ -2,7 +2,7 @@
 
 
 a = Analysis(
-    ['main.py'],
+    ['main-gummy.py'],
     pathex=[],
     binaries=[],
     datas=[],
@@ -22,7 +22,7 @@ exe = EXE(
     a.binaries,
     a.datas,
     [],
-    name='main',
+    name='main-gummy',
     debug=False,
     bootloader_ignore_signals=False,
     strip=False,

python-subprocess/main.py

@@ -1,27 +0,0 @@
-from sysaudio.win import LoopbackStream, mergeStreamChannels
-from audio2text.gummy import GummyTranslator
-import sys
-import argparse
-
-def convert_audio_to_text(s_lang, t_lang, audio_source):
-    sys.stdout.reconfigure(line_buffering=True)
-    loopback = LoopbackStream()
-    loopback.openStream()
-
-    gummy = GummyTranslator(loopback.RATE, s_lang, t_lang)
-    gummy.translator.start()
-
-    while True:
-        if not loopback.stream: continue
-        data = loopback.stream.read(loopback.CHUNK)
-        data = mergeStreamChannels(data, loopback.CHANNELS)
-        gummy.translator.send_audio_frame(data)
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description='Convert system audio stream to text')
-    parser.add_argument('-s', '--s_lang', default='en', help='Source language code')
-    parser.add_argument('-t', '--t_lang', default='zh', help='Target language code')
-    parser.add_argument('-a', '--audio', default=0, help='Audio stream source: 0 for output audio stream, 1 for input audio stream')
-    args = parser.parse_args()
-    convert_audio_to_text(args.s_lang, args.t_lang, args.audio)

python-subprocess/sysaudio/linux.py

@@ -0,0 +1,79 @@
+import pyaudio
+import numpy as np
+
+def mergeStreamChannels(data, channels):
+    """
+    将当前多通道流数据合并为单通道流数据
+
+    Args:
+        data: 多通道数据
+        channels: 通道数
+
+    Returns:
+        mono_data_bytes: 单通道数据
+    """
+    # (length * channels,)
+    data_np = np.frombuffer(data, dtype=np.int16)
+    # (length, channels)
+    data_np_r = data_np.reshape(-1, channels)
+    # (length,)
+    mono_data = np.mean(data_np_r.astype(np.float32), axis=1)
+    mono_data = mono_data.astype(np.int16)
+    mono_data_bytes = mono_data.tobytes()
+    return mono_data_bytes
+
+
+class AudioStream:
+    def __init__(self, audio_type=1):
+        self.audio_type = audio_type
+        self.mic = pyaudio.PyAudio()
+        self.device = self.mic.get_default_input_device_info()
+        self.stream = None
+        self.SAMP_WIDTH = pyaudio.get_sample_size(pyaudio.paInt16)
+        self.FORMAT = pyaudio.paInt16
+        self.CHANNELS = self.device["maxInputChannels"]
+        self.RATE = int(self.device["defaultSampleRate"])
+        self.CHUNK = self.RATE // 20
+        self.INDEX = self.device["index"]
+
+    def printInfo(self):
+        dev_info = f"""
+        采样输入设备：
+            - 设备类型：{ "音频输入（Linux平台目前仅支持该项）" }
+            - 序号：{self.device['index']}
+            - 名称：{self.device['name']}
+            - 最大输入通道数：{self.device['maxInputChannels']}
+            - 默认低输入延迟：{self.device['defaultLowInputLatency']}s
+            - 默认高输入延迟：{self.device['defaultHighInputLatency']}s
+            - 默认采样率：{self.device['defaultSampleRate']}Hz
+
+        音频样本块大小：{self.CHUNK}
+        样本位宽：{self.SAMP_WIDTH}
+        音频数据格式：{self.FORMAT}
+        音频通道数：{self.CHANNELS}
+        音频采样率：{self.RATE}
+        """
+        print(dev_info)
+
+    def openStream(self):
+        """
+        打开并返回系统音频输出流
+        """
+        if self.stream: return self.stream
+        self.stream = self.mic.open(
+            format = self.FORMAT,
+            channels = self.CHANNELS,
+            rate = self.RATE,
+            input = True,
+            input_device_index = self.INDEX
+        )
+        return self.stream
+    
+    def closeStream(self):
+        """
+        关闭系统音频输出流
+        """
+        if self.stream is None: return
+        self.stream.stop_stream()
+        self.stream.close()
+        self.stream = None

python-subprocess/sysaudio/win.py

@@ -61,28 +61,39 @@ def mergeStreamChannels(data, channels):
     mono_data_bytes = mono_data.tobytes()
     return mono_data_bytes
 
-class LoopbackStream:
-    def __init__(self):
+class AudioStream:
+    """
+    获取系统音频流
+    
+    参数：
+        audio_type: （默认）0-系统音频输出流，1-系统音频输入流
+    """
+    def __init__(self, audio_type=0):
+        self.audio_type = audio_type
         self.mic = pyaudio.PyAudio()
-        self.loopback = getDefaultLoopbackDevice(self.mic, False)
+        if self.audio_type == 0:
+            self.device = getDefaultLoopbackDevice(self.mic, False)
+        else:
+            self.device = self.mic.get_default_input_device_info()
         self.stream = None
         self.SAMP_WIDTH = pyaudio.get_sample_size(pyaudio.paInt16)
         self.FORMAT = pyaudio.paInt16
-        self.CHANNELS = self.loopback["maxInputChannels"]
-        self.RATE = int(self.loopback["defaultSampleRate"])
+        self.CHANNELS = self.device["maxInputChannels"]
+        self.RATE = int(self.device["defaultSampleRate"])
         self.CHUNK = self.RATE // 20
-        self.INDEX = self.loopback["index"]
+        self.INDEX = self.device["index"]
 
     def printInfo(self):
         dev_info = f"""
-        采样输入设备：
-            - 序号：{self.loopback['index']}
-            - 名称：{self.loopback['name']}
-            - 最大输入通道数：{self.loopback['maxInputChannels']}
-            - 默认低输入延迟：{self.loopback['defaultLowInputLatency']}s
-            - 默认高输入延迟：{self.loopback['defaultHighInputLatency']}s
-            - 默认采样率：{self.loopback['defaultSampleRate']}Hz
-            - 是否回环设备：{self.loopback['isLoopbackDevice']}
+        采样设备：
+            - 设备类型：{ "音频输入" if self.audio_type == 0 else "音频输出" }
+            - 序号：{self.device['index']}
+            - 名称：{self.device['name']}
+            - 最大输入通道数：{self.device['maxInputChannels']}
+            - 默认低输入延迟：{self.device['defaultLowInputLatency']}s
+            - 默认高输入延迟：{self.device['defaultHighInputLatency']}s
+            - 默认采样率：{self.device['defaultSampleRate']}Hz
+            - 是否回环设备：{self.device['isLoopbackDevice']}
 
         音频样本块大小：{self.CHUNK}
         样本位宽：{self.SAMP_WIDTH}