feat(python-subprocess): 尝试字幕显示新解决方案

- 使用 python 子进程解析字幕
- 通过 websocket 通信将字幕传递给软件

python-subprocess/sysaudio/win.py

@@ -1,6 +1,8 @@
 """获取 Windows 系统音频输出流"""
 
 import pyaudiowpatch as pyaudio
+import numpy as np
+
 
 def getDefaultLoopbackDevice(mic: pyaudio.PyAudio, info = True)->dict:
     """
@@ -38,16 +40,77 @@ def getDefaultLoopbackDevice(mic: pyaudio.PyAudio, info = True)->dict:
     return default_speaker
 
 
-def getOutputStream():
-    mic = pyaudio.PyAudio()
-    default_speaker = getDefaultLoopbackDevice(mic, False)
+def mergeStreamChannels(data, channels):
+    """
+    将当前多通道流数据合并为单通道流数据
 
-    stream = mic.open(
-        format = pyaudio.paInt16,
-        channels = default_speaker["maxInputChannels"],
-        rate = int(default_speaker["defaultSampleRate"]),
-        input = True,
-        input_device_index = default_speaker["index"]
-    )
+    Args:
+        data: 多通道数据
+        channels: 通道数
 
-    return stream
+    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 LoopbackStream:
+    def __init__(self):
+        self.mic = pyaudio.PyAudio()
+        self.loopback = getDefaultLoopbackDevice(self.mic, False)
+        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.CHUNK = self.RATE // 10
+        self.INDEX = self.loopback["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']}
+
+        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