使用IBM STT。使用timestamps=true，当系统检测到它们被说出时，你会得到这个词。
还有很多其他很酷的功能，例如word_alternatives_threshold 可以获取单词的其他可能性，word_confidence 可以获取系统预测单词的信心。将word_alternatives_threshold 设置在（0.1 和 0.01）之间以获得真正的想法。
这需要登录，然后您可以使用生成的用户名和密码。
IBM STT 已经是上述语音识别模块的一部分，但要获取单词时间戳，您需要修改函数。
提取和修改的表单如下所示：
def extracted_from_sr_recognize_ibm(audio_data, username=IBM_USERNAME, password=IBM_PASSWORD, language="en-US", show_all=False, timestamps=False,
word_confidence=False, word_alternatives_threshold=0.1):
assert isinstance(username, str), "``username`` must be a string"
assert isinstance(password, str), "``password`` must be a string"
flac_data = audio_data.get_flac_data(
convert_rate=None if audio_data.sample_rate >= 16000 else 16000, # audio samples should be at least 16 kHz
convert_width=None if audio_data.sample_width >= 2 else 2 # audio samples should be at least 16-bit
)
url = "https://stream-fra.watsonplatform.net/speech-to-text/api/v1/recognize?{}".format(urlencode({
"profanity_filter": "false",
"continuous": "true",
"model": "{}_BroadbandModel".format(language),
"timestamps": "{}".format(str(timestamps).lower()),
"word_confidence": "{}".format(str(word_confidence).lower()),
"word_alternatives_threshold": "{}".format(word_alternatives_threshold)
}))
request = Request(url, data=flac_data, headers={
"Content-Type": "audio/x-flac",
"X-Watson-Learning-Opt-Out": "true", # prevent requests from being logged, for improved privacy
})
authorization_value = base64.standard_b64encode("{}:{}".format(username, password).encode("utf-8")).decode("utf-8")
request.add_header("Authorization", "Basic {}".format(authorization_value))
try:
response = urlopen(request, timeout=None)
except HTTPError as e:
raise sr.RequestError("recognition request failed: {}".format(e.reason))
except URLError as e:
raise sr.RequestError("recognition connection failed: {}".format(e.reason))
response_text = response.read().decode("utf-8")
result = json.loads(response_text)
# return results
if show_all: return result
if "results" not in result or len(result["results"]) < 1 or "alternatives" not in result["results"][0]:
raise Exception("Unknown Value Exception")
transcription = []
for utterance in result["results"]:
if "alternatives" not in utterance:
raise Exception("Unknown Value Exception. No Alternatives returned")
for hypothesis in utterance["alternatives"]:
if "transcript" in hypothesis:
transcription.append(hypothesis["transcript"])
return "\n".join(transcription)