feat: optimize document and model usage

voice/ali/ali_voice.py

@@ -15,11 +15,15 @@ import time
 
 from bridge.reply import Reply, ReplyType
 from common.log import logger
-from voice.audio_convert import get_pcm_from_wav
 from voice.voice import Voice
 from voice.ali.ali_api import AliyunTokenGenerator, speech_to_text_aliyun, text_to_speech_aliyun
 from config import conf
 
+try:
+    from voice.audio_convert import get_pcm_from_wav
+except ImportError as e:
+    logger.debug("import voice.audio_convert failed: {}".format(e))
+
 
 class AliVoice(Voice):
     def __init__(self):

voice/audio_convert.py

@@ -8,7 +8,13 @@ try:
 except ImportError:
     logger.debug("import pysilk failed, wechaty voice message will not be supported.")
 
-from pydub import AudioSegment
+try:
+    from pydub import AudioSegment
+    _pydub_available = True
+except ImportError:
+    logger.debug("import pydub failed, voice conversion features will not be supported.")
+    AudioSegment = None
+    _pydub_available = False
 
 sil_supports = [8000, 12000, 16000, 24000, 32000, 44100, 48000]  # slk转wav时，支持的采样率
 
@@ -44,6 +50,8 @@ def any_to_mp3(any_path, mp3_path):
     """
     把任意格式转成mp3文件
     """
+    if not _pydub_available:
+        raise ImportError("pydub is required for audio conversion. Please install it with: pip install pydub")
     if any_path.endswith(".mp3"):
         shutil.copy2(any_path, mp3_path)
         return
@@ -58,6 +66,8 @@ def any_to_wav(any_path, wav_path):
     """
     把任意格式转成wav文件
     """
+    if not _pydub_available:
+        raise ImportError("pydub is required for audio conversion. Please install it with: pip install pydub")
     if any_path.endswith(".wav"):
         shutil.copy2(any_path, wav_path)
         return
@@ -73,6 +83,8 @@ def any_to_sil(any_path, sil_path):
     """
     把任意格式转成sil文件
     """
+    if not _pydub_available:
+        raise ImportError("pydub is required for audio conversion. Please install it with: pip install pydub")
     if any_path.endswith(".sil") or any_path.endswith(".silk") or any_path.endswith(".slk"):
         shutil.copy2(any_path, sil_path)
         return 10000
@@ -92,6 +104,8 @@ def any_to_amr(any_path, amr_path):
     """
     把任意格式转成amr文件
     """
+    if not _pydub_available:
+        raise ImportError("pydub is required for audio conversion. Please install it with: pip install pydub")
     if any_path.endswith(".amr"):
         shutil.copy2(any_path, amr_path)
         return
@@ -116,6 +130,8 @@ def split_audio(file_path, max_segment_length_ms=60000):
     """
     分割音频文件
     """
+    if not _pydub_available:
+        raise ImportError("pydub is required for audio conversion. Please install it with: pip install pydub")
     audio = AudioSegment.from_file(file_path)
     audio_length_ms = len(audio)
     if audio_length_ms <= max_segment_length_ms:

voice/baidu/baidu_voice.py

@@ -13,9 +13,13 @@ from bridge.reply import Reply, ReplyType
 from common.log import logger
 from common.tmp_dir import TmpDir
 from config import conf
-from voice.audio_convert import get_pcm_from_wav
 from voice.voice import Voice
 
+try:
+    from voice.audio_convert import get_pcm_from_wav
+except ImportError as e:
+    logger.debug("import voice.audio_convert failed: {}".format(e))
+
 class BaiduVoice(Voice):
     def __init__(self):
         try:

voice/xunfei/xunfei_voice.py

@@ -28,9 +28,15 @@ from config import conf
 from voice.voice import Voice
 from .xunfei_asr import xunfei_asr
 from .xunfei_tts import xunfei_tts
-from voice.audio_convert import any_to_mp3
 import shutil
-from pydub import AudioSegment
+
+try:
+    from voice.audio_convert import any_to_mp3
+    from pydub import AudioSegment
+    _audio_available = True
+except ImportError as e:
+    logger.debug("import audio libraries failed: {}".format(e))
+    _audio_available = False
 
 
 class XunfeiVoice(Voice):