Speech recognition 如何获得';暂停';使用google Speech to Text为给定音频文件标记?
下面给出了从谷歌语音到音频文件文本的输出Speech recognition 如何获得';暂停';使用google Speech to Text为给定音频文件标记?,speech-recognition,speech-to-text,google-speech-api,google-cloud-speech,Speech Recognition,Speech To Text,Google Speech Api,Google Cloud Speech,下面给出了从谷歌语音到音频文件文本的输出 results { alternatives { transcript: "extremely grateful for the " confidence: 0.911402702331543 words { start_time { } end_time { nanos: 600000000 } word: "extre
results {
alternatives {
transcript: "extremely grateful for the "
confidence: 0.911402702331543
words {
start_time {
}
end_time {
nanos: 600000000
}
word: "extremely"
}
words {
start_time {
nanos: 600000000
}
end_time {
nanos: 900000000
}
word: "grateful"
}
words {
start_time {
nanos: 900000000
}
end_time {
seconds: 1
nanos: 100000000
}
word: "for"
}
words {
start_time {
seconds: 1
nanos: 100000000
}
end_time {
seconds: 1
nanos: 300000000
}
word: "the"
}
words {
start_time {
seconds: 1
nanos: 300000000
}
}
我想知道单词之间的停顿。下面的“极端”一词从0开始,以nano结尾:600000000。下一个单词“感激”的开始时间是Nano:600000000。但当我们说话时,字里行间会有空隙。我想要单词之间间隔持续时间的时间戳
有没有办法通过谷歌语音文本转换来获取这些信息?如果没有,请提出一些替代方案,以实现同样的目标