refactor(engine): 重构字幕引擎

- 更新 GummyTranslator 类，优化字幕生成逻辑
- 移除 audioprcs 模块，音频处理功能转移到 utils 模块
- 重构 sysaudio 模块，提高音频流管理的灵活性和稳定性
- 修改 TODO.md，完成按时间降序排列字幕记录的功能
- 更新文档，说明因资源限制将不再维护英文和日文文档

engine/utils/__init__.py

@@ -0,0 +1,2 @@
+from .process import merge_chunk_channels, resample_chunk_mono, resample_mono_chunk
+from .sysout import stdout, stdout_cmd, stdout_obj, stderr

engine/utils/process.py

@@ -0,0 +1,70 @@
+import samplerate
+import numpy as np
+
+
+def merge_chunk_channels(chunk: bytes, channels: int) -> bytes:
+    """
+    将当前多通道音频数据块转换为单通道音频数据块
+
+    Args:
+        chunk: 多通道音频数据块
+        channels: 通道数
+
+    Returns:
+        单通道音频数据块
+    """
+    # (length * channels,)
+    chunk_np = np.frombuffer(chunk, dtype=np.int16)
+    # (length, channels)
+    chunk_np = chunk_np.reshape(-1, channels)
+    # (length,)
+    chunk_mono_f = np.mean(chunk_np.astype(np.float32), axis=1)
+    chunk_mono = np.round(chunk_mono_f).astype(np.int16)
+    return chunk_mono.tobytes()
+
+
+def resample_chunk_mono(chunk: bytes, channels: int, orig_sr: int, target_sr: int, mode="sinc_best") -> bytes:
+    """
+    将当前多通道音频数据块转换成单通道音频数据块，然后进行重采样
+
+    Args:
+        chunk: 多通道音频数据块
+        channels: 通道数
+        orig_sr: 原始采样率
+        target_sr: 目标采样率
+        mode: 重采样模式，可选：'sinc_best' | 'sinc_medium' | 'sinc_fastest' | 'zero_order_hold' | 'linear'
+
+    Return:
+        单通道音频数据块
+    """
+    # (length * channels,)
+    chunk_np = np.frombuffer(chunk, dtype=np.int16)
+    # (length, channels)
+    chunk_np = chunk_np.reshape(-1, channels)
+    # (length,)
+    chunk_mono_f = np.mean(chunk_np.astype(np.float32), axis=1)
+    chunk_mono = chunk_mono_f.astype(np.int16)
+    ratio = target_sr / orig_sr
+    chunk_mono_r = samplerate.resample(chunk_mono, ratio, converter_type=mode)
+    chunk_mono_r = np.round(chunk_mono_r).astype(np.int16)
+    return chunk_mono_r.tobytes()
+
+
+def resample_mono_chunk(chunk: bytes, orig_sr: int, target_sr: int, mode="sinc_best") -> bytes:
+    """
+    将当前单通道音频块进行重采样
+
+    Args:
+        chunk: 单通道音频数据块
+        orig_sr: 原始采样率
+        target_sr: 目标采样率
+        mode: 重采样模式，可选：'sinc_best' | 'sinc_medium' | 'sinc_fastest' | 'zero_order_hold' | 'linear'
+
+    Return:
+        单通道音频数据块
+    """
+    chunk_np = np.frombuffer(chunk, dtype=np.int16)
+    ratio = target_sr / orig_sr
+    chunk_r =  samplerate.resample(chunk_np, ratio, converter_type=mode)
+    chunk_r = np.round(chunk_r).astype(np.int16)
+    return chunk_r.tobytes()

engine/utils/sysout.py

@@ -0,0 +1,18 @@
+import sys
+import json
+
+def stdout(text: str):
+    stdout_cmd("print", text)
+
+def stdout_cmd(command: str, content = ""):
+    msg = { "command": command, "content": content }
+    sys.stdout.write(json.dumps(msg) + "\n")
+    sys.stdout.flush()
+
+def stdout_obj(obj):
+    sys.stdout.write(json.dumps(obj) + "\n")
+    sys.stdout.flush()
+
+def stderr(text: str):
+    sys.stderr.write(text + "\n")
+    sys.stderr.flush()