0

我正在尝试开始在 python 中使用语音识别。首先，我使用以下代码尝试了 PySpeech ( https://code.google.com/p/pyspeech/ )：

def listen():
    while 1:
        said = speech.input()
        print said
        if said == "off":
            break

并得到以下回溯：

Traceback (most recent call last):
  File "C:/Users/REDACTED/Documents/Python Projects/listen.py", line 59, in <module> useful.listen()

  File "C:/Users/REDACTED/Documents/Python Projects/listen.py", line 48, in listen 
said = speech.input()

  File "C:\Python27\lib\site-packages\speech.py", line 162, in input
    listener = listenforanything(response)

  File "C:\Python27\lib\site-packages\speech.py", line 193, in listenforanything
    return _startlistening(None, callback)

  File "C:\Python27\lib\site-packages\speech.py", line 223, in _startlistening
    grammar = context.CreateGrammar()

  File "C:\Users\REDACTED\AppData\Local\Temp\gen_py\2.7\C866CA3A-32F7-11D2-9602-00C04F8EE628x0x5x4.py", line 2298, in CreateGrammar
ret = self._oleobj_.InvokeTypes(14, LCID, 1, (9, 0), ((12, 49),),GrammarId

AttributeError: 'module' object has no attribute 'VARIANT'

然后我按照 PySpeech 的 GoogleCode 页面顶部的建议尝试了蜻蜓，使用蜻蜓文档上常见的以下示例代码：

from dragonfly.all import Grammar, CompoundRule

# Voice command rule combining spoken form and recognition processing.
class ExampleRule(CompoundRule):
   spec = "do something computer"                  # Spoken form of command.
   def _process_recognition(self, node, extras):   # Callback when command is spoken.
       print "Voice command spoken."

# Create a grammar which contains and loads the command rule.
grammar = Grammar("example grammar")                # Create a grammar to contain the command        rule.
grammar.add_rule(ExampleRule())                     # Add the command rule to the grammar.
grammar.load()                                      # Load the grammar.

并得到了这个非常相似的回溯：

Traceback (most recent call last):

  File "C:/Users/REDACTED/Documents/Python Projects/listen.py", line 14, in <module>
    grammar.load()                                      # Load the grammar.

  File "C:\Python27\lib\site-packages\dragonfly\grammar\grammar_base.py", line 302, in load
    self._engine.load_grammar(self)

  File "C:\Python27\lib\site-packages\dragonfly\engines\engine_sapi5.py", line 79, in load_grammar
    handle = self._compiler.compile_grammar(grammar, context)

  File "C:\Python27\lib\site-packages\dragonfly\engines\compiler_sapi5.py", line 68, in compile_grammar
    grammar_handle = context.CreateGrammar()

  File "C:\Users\REDACTED\AppData\Local\Temp\gen_py\2.7\C866CA3A-32F7-11D2-9602-00C04F8EE628x0x5x4.py", line 2298, in CreateGrammar
    ret = self._oleobj_.InvokeTypes(14, LCID, 1, (9, 0), ((12, 49),),GrammarId

AttributeError: 'module' object has no attribute 'VARIANT'

这两个模块都使用 PIP 安装并使用 python 2.7 解释器运行。对我来说，这似乎是一个 python 版本问题，因为两个不同的模块会抛出相同的错误来实现相同的东西，但我很困惑如何继续。

非常感谢任何帮助，我很乐意根据要求提供更多代码/信息。谢谢！

编辑 1：对于碰巧偶然发现这篇文章的任何遇到类似问题的人，请尝试https://pypi.python.org/pypi/SpeechRecognition/作为 py2.7 的替代方案。如果它运行没有错误但行为不一致或无限循环，请尝试在第 100 行附近修改init .py中识别器类的 init 方法。能量阈值需要对我进行一些修改（100-> 300），这可能是由于具体情况你的麦克风设置。我还增加了我的安静时间（0.5->0.7），因为它有时会打断我。在这些更改之后，它对我来说效果很好，在捕获结束后约 2 秒内返回输入语音的非常准确的文本。

4

0 回答 0