合并多个更新 (#68)

* 🐳 chore: 优化打包速度

使用国内镜像

* 🎈 perf: 优化打包速度

注释日志的时间信息

* 🐳 chore: 改用docker hub

* 🐎 ci(ci): 自动打包docker

* 🐳 chore: 更新文档

* 🎈 perf: 改用opuslib_next

* 🌈 style: 统一log

core/utils/asr.py

@@ -1,18 +1,36 @@
 import time
 import wave
 import os
+import sys
+import io
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
 from typing import Optional, Tuple, List
 import uuid
 
-import opuslib
+import opuslib_next
 from funasr import AutoModel
 from funasr.utils.postprocess_utils import rich_transcription_postprocess
 
 TAG = __name__
 logger = setup_logging()
 
+# 捕获标准输出
+class CaptureOutput:
+    def __enter__(self):
+        self._output = io.StringIO()
+        self._original_stdout = sys.stdout
+        sys.stdout = self._output
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        sys.stdout = self._original_stdout
+        self.output = self._output.getvalue()
+        self._output.close()
+
+        # 将捕获到的内容通过 logger 输出
+        if self.output:
+            logger.bind(tag=TAG).info(self.output.strip())
+
 class ASR(ABC):
     @abstractmethod
     def save_audio_to_file(self, opus_data: List[bytes], session_id: str) -> str:
@@ -33,28 +51,28 @@ class FunASR(ASR):
 
         # 确保输出目录存在
         os.makedirs(self.output_dir, exist_ok=True)
-
-        self.model = AutoModel(
-            model=self.model_dir,
-            vad_kwargs={"max_single_segment_time": 30000},
-            disable_update=True,
-            hub="hf"
-            # device="cuda:0",  # 启用GPU加速
-        )
+        with CaptureOutput():
+            self.model = AutoModel(
+                model=self.model_dir,
+                vad_kwargs={"max_single_segment_time": 30000},
+                disable_update=True,
+                hub="hf"
+                # device="cuda:0",  # 启用GPU加速
+            )
 
     def save_audio_to_file(self, opus_data: List[bytes], session_id: str) -> str:
         """将Opus音频数据解码并保存为WAV文件"""
         file_name = f"asr_{session_id}_{uuid.uuid4()}.wav"
         file_path = os.path.join(self.output_dir, file_name)
 
-        decoder = opuslib.Decoder(16000, 1)  # 16kHz, 单声道
+        decoder = opuslib_next.Decoder(16000, 1)  # 16kHz, 单声道
         pcm_data = []
 
         for opus_packet in opus_data:
             try:
                 pcm_frame = decoder.decode(opus_packet, 960)  # 960 samples = 60ms
                 pcm_data.append(pcm_frame)
-            except opuslib.OpusError as e:
+            except opuslib_next.OpusError as e:
                 logger.bind(tag=TAG).error(f"Opus解码错误: {e}", exc_info=True)
 
         with wave.open(file_path, "wb") as wf:

core/utils/vad.py

@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
-import opuslib
+import opuslib_next
 import time
 import numpy as np
 import torch
@@ -24,7 +24,7 @@ class SileroVAD(VAD):
                                                 force_reload=False)
         (get_speech_timestamps, _, _, _, _) = self.utils
 
-        self.decoder = opuslib.Decoder(16000, 1)
+        self.decoder = opuslib_next.Decoder(16000, 1)
         self.vad_threshold = config.get("threshold")
         self.silence_threshold_ms = config.get("min_silence_duration_ms")
 
@@ -59,7 +59,7 @@ class SileroVAD(VAD):
                     conn.client_have_voice_last_time = time.time() * 1000
 
             return client_have_voice
-        except opuslib.OpusError as e:
+        except opuslib_next.OpusError as e:
             logger.bind(tag=TAG).info(f"解码错误: {e}")
         except Exception as e:
             logger.bind(tag=TAG).error(f"Error processing audio packet: {e}")