Azure 语音工具规范。
源代码位于 llama-index-integrations/tools/llama-index-tools-azure-speech/llama_index/tools/azure_speech/base.py
text_to_speech
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86 | class AzureSpeechToolSpec(BaseToolSpec):
"""Azure Speech tool spec."""
spec_functions = ["speech_to_text", "text_to_speech"]
def __init__(
self, region: str, speech_key: str, language: Optional[str] = "en-US"
) -> None:
import azure.cognitiveservices.speech as speechsdk
"""Initialize with parameters."""
self.config = speechsdk.SpeechConfig(subscription=speech_key, region=region)
self.config.speech_recognition_language = language
def text_to_speech(self, text: str) -> None:
"""
This tool accepts a natural language string and will use Azure speech services to create an
audio version of the text, and play it on the users computer.
Args:
text (str): The text to play
"""
import azure.cognitiveservices.speech as speechsdk
speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=self.config)
result = speech_synthesizer.speak_text(text)
if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
speechsdk.AudioDataStream(result)
return "Audio playback complete."
elif result.reason == speechsdk.ResultReason.Canceled:
cancellation_details = result.cancellation_details
print(f"Speech synthesis canceled: {cancellation_details.reason}")
if cancellation_details.reason == speechsdk.CancellationReason.Error:
print(f"Error details: {cancellation_details.error_details}")
return None
return None
return None
def _transcribe(self, speech_recognizer) -> List[str]:
done = False
results = []
def stop_cb(evt) -> None:
"""Callback that stop continuous recognition."""
speech_recognizer.stop_continuous_recognition_async()
nonlocal done
done = True
speech_recognizer.recognized.connect(
lambda evt, results=results: results.append(evt.result.text)
)
speech_recognizer.session_stopped.connect(stop_cb)
speech_recognizer.canceled.connect(stop_cb)
# Start continuous speech recognition
speech_recognizer.start_continuous_recognition_async()
while not done:
time.sleep(0.5)
return results
def speech_to_text(self, filename: str) -> List[str]:
"""
This tool accepts a filename for a speech audio file and uses Azure to transcribe it into text.
Args:
filename (str): The name of the file to transcribe
"""
import azure.cognitiveservices.speech as speechsdk
speech_recognizer = speechsdk.SpeechRecognizer(
speech_config=self.config,
audio_config=speechsdk.audio.AudioConfig(filename=filename),
)
return self._transcribe(speech_recognizer)
|
此工具接受自然语言字符串，并将使用 Azure 语音服务创建文本的音频版本，并在用户的计算机上播放。
text_to_speech(text: str) -> None
参数
名称
| 类型 |
描述 |
默认值 |
text |
str
|
要播放的文本
|
|
speech_to_text
|
text_to_speech
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47 | def text_to_speech(self, text: str) -> None:
"""
This tool accepts a natural language string and will use Azure speech services to create an
audio version of the text, and play it on the users computer.
Args:
text (str): The text to play
"""
import azure.cognitiveservices.speech as speechsdk
speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=self.config)
result = speech_synthesizer.speak_text(text)
if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
speechsdk.AudioDataStream(result)
return "Audio playback complete."
elif result.reason == speechsdk.ResultReason.Canceled:
cancellation_details = result.cancellation_details
print(f"Speech synthesis canceled: {cancellation_details.reason}")
if cancellation_details.reason == speechsdk.CancellationReason.Error:
print(f"Error details: {cancellation_details.error_details}")
return None
return None
return None
|
此工具接受语音音频文件的文件名，并使用 Azure 将其转录为文本。
speech_to_text(filename: str) -> List[str]
filename
名称
| 类型 |
描述 |
默认值 |
text |
要转录的文件名
|
要播放的文本
|
|
speech_to_text
|
text_to_speech
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86 | def speech_to_text(self, filename: str) -> List[str]:
"""
This tool accepts a filename for a speech audio file and uses Azure to transcribe it into text.
Args:
filename (str): The name of the file to transcribe
"""
import azure.cognitiveservices.speech as speechsdk
speech_recognizer = speechsdk.SpeechRecognizer(
speech_config=self.config,
audio_config=speechsdk.audio.AudioConfig(filename=filename),
)
return self._transcribe(speech_recognizer)
|
