Google语音对文本非常不准确，最后的结果包含了所有其他结果，而speakerTag只包含了最后的结果。
Google语音对文本非常不准确，最后的结果包含了所有其他结果，而speakerTag只包含了最后的结果。
提问于 2020-07-13 20:01:36
我正在使用google语音到文本，使用命令行并获得奇怪的结果。
这是我的命令
gcloud beta ml speech recognize-long-running gs://my_bucket_name/call0.mp3
--language-code=en-US --async --include-word-time-offsets --enable-speaker-diarization
--diarization-speaker-count=2这是音频文件：https://dcs.megaphone.fm/LIT9020259030.mp3?key=4b567156fd7bdfaa90992664d4bc667c
问题是：
- ，结果非常糟糕和不准确的
- ，最后的结果包含了所有其他结果组合的
- ，speakerTag只显示在最后的结果
- 中，我得到的speakerTag仅适用于扬声器1
G 211
下面是json的结果：
{
"done": true,
"metadata": {
"@type": "type.googleapis.com/google.cloud.speech.v1p1beta1.LongRunningRecognizeMetadata",
"lastUpdateTime": "2020-07-13T18:56:33.689140Z",
"progressPercent": 100,
"startTime": "2020-07-13T18:27:45.757871Z",
"uri": "gs://deepagent-db032.appspot.com/conmagi/call1.mp3"
},
"name": "398565854464473919",
"response": {
"@type": "type.googleapis.com/google.cloud.speech.v1p1beta1.LongRunningRecognizeResponse",
"results": [
{
"alternatives": [
{
"confidence": 0.87135065,
"transcript": "love",
"words": [
{
"endTime": "11.300s",
"startTime": "10.400s",
"word": "love"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.48216835,
"transcript": "you are",
"words": [
{
"endTime": "425.100s",
"startTime": "424.500s",
"word": "you"
},
{
"endTime": "425.400s",
"startTime": "425.100s",
"word": "are"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.9194219,
"transcript": "how far is it from",
"words": [
{
"endTime": "475.200s",
"startTime": "473.800s",
"word": "how"
},
{
"endTime": "475.500s",
"startTime": "475.200s",
"word": "far"
},
{
"endTime": "475.700s",
"startTime": "475.500s",
"word": "is"
},
{
"endTime": "475.800s",
"startTime": "475.700s",
"word": "it"
},
{
"endTime": "476.100s",
"startTime": "475.800s",
"word": "from"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.823343,
"transcript": "I want",
"words": [
{
"endTime": "629.200s",
"startTime": "626.700s",
"word": "I"
},
{
"endTime": "629.800s",
"startTime": "629.200s",
"word": "want"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.56559134,
"transcript": "Blue Ivy",
"words": [
{
"endTime": "990.100s",
"startTime": "989.500s",
"word": "Blue"
},
{
"endTime": "991.100s",
"startTime": "990.100s",
"word": "Ivy"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.78465956,
"transcript": "how old is Wawa",
"words": [
{
"endTime": "1599.700s",
"startTime": "1598.500s",
"word": "how"
},
{
"endTime": "1600.100s",
"startTime": "1599.700s",
"word": "old"
},
{
"endTime": "1600.200s",
"startTime": "1600.100s",
"word": "is"
},
{
"endTime": "1600.600s",
"startTime": "1600.200s",
"word": "Wawa"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.9475956,
"transcript": "how are you",
"words": [
{
"endTime": "2022.400s",
"startTime": "2020s",
"word": "how"
},
{
"endTime": "2022.500s",
"startTime": "2022.400s",
"word": "are"
},
{
"endTime": "2022.600s",
"startTime": "2022.500s",
"word": "you"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.7494768,
"transcript": "New York mall",
"words": [
{
"endTime": "2066.200s",
"startTime": "2065.800s",
"word": "New"
},
{
"endTime": "2066.500s",
"startTime": "2066.200s",
"word": "York"
},
{
"endTime": "2067s",
"startTime": "2066.500s",
"word": "mall"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.6706576,
"transcript": "call",
"words": [
{
"endTime": "2255.600s",
"startTime": "2254.500s",
"word": "call"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.87819797,
"transcript": "call Paul Wall",
"words": [
{
"endTime": "3041.500s",
"startTime": "3040.300s",
"word": "call"
},
{
"endTime": "3041.800s",
"startTime": "3041.500s",
"word": "Paul"
},
{
"endTime": "3042.300s",
"startTime": "3041.800s",
"word": "Wall"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.8331511,
"transcript": "no",
"words": [
{
"endTime": "3101.300s",
"startTime": "3100.800s",
"word": "no"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.62488914,
"transcript": "call Jeff",
"words": [
{
"endTime": "3473.100s",
"startTime": "3470.300s",
"word": "call"
},
{
"endTime": "3473.500s",
"startTime": "3473.100s",
"word": "Jeff"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.9074697,
"transcript": "call home",
"words": [
{
"endTime": "4166.100s",
"startTime": "4162.400s",
"word": "call"
},
{
"endTime": "4166.400s",
"startTime": "4166.100s",
"word": "home"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.7917781,
"transcript": "how old are you",
"words": [
{
"endTime": "4231.800s",
"startTime": "4231.300s",
"word": "how"
},
{
"endTime": "4232.200s",
"startTime": "4231.800s",
"word": "old"
},
{
"endTime": "4232.300s",
"startTime": "4232.200s",
"word": "are"
},
{
"endTime": "4232.400s",
"startTime": "4232.300s",
"word": "you"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.70297575,
"transcript": " Europe",
"words": [
{
"endTime": "4244.200s",
"startTime": "4243s",
"word": "Europe"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.84273374,
"transcript": " how are you",
"words": [
{
"endTime": "5121.500s",
"startTime": "5115.300s",
"word": "how"
},
{
"endTime": "5122.100s",
"startTime": "5121.500s",
"word": "are"
},
{
"endTime": "5122.300s",
"startTime": "5122.100s",
"word": "you"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.7561751,
"transcript": " the only one",
"words": [
{
"endTime": "6199.900s",
"startTime": "6199.600s",
"word": "the"
},
{
"endTime": "6200.400s",
"startTime": "6199.900s",
"word": "only"
},
{
"endTime": "6200.800s",
"startTime": "6200.400s",
"word": "one"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.6547922,
"transcript": " call",
"words": [
{
"endTime": "6258.800s",
"startTime": "6256.800s",
"word": "call"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.9402823,
"transcript": " Walgreens",
"words": [
{
"endTime": "6925s",
"startTime": "6912.300s",
"word": "Walgreens"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.5217668,
"transcript": " we want to watch",
"words": [
{
"endTime": "7155.900s",
"startTime": "7155.500s",
"word": "we"
},
{
"endTime": "7156.500s",
"startTime": "7155.900s",
"word": "want"
},
{
"endTime": "7156.600s",
"startTime": "7156.500s",
"word": "to"
},
{
"endTime": "7156.700s",
"startTime": "7156.600s",
"word": "watch"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.7971729,
"transcript": " I love you",
"words": [
{
"endTime": "7199.900s",
"startTime": "7199.200s",
"word": "I"
},
{
"endTime": "7202.900s",
"startTime": "7199.900s",
"word": "love"
},
{
"endTime": "7203.100s",
"startTime": "7202.900s",
"word": "you"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"confidence": 0.8566783,
"transcript": " how old is Moana",
"words": [
{
"endTime": "7483.800s",
"startTime": "7481.300s",
"word": "how"
},
{
"endTime": "7484s",
"startTime": "7483.800s",
"word": "old"
},
{
"endTime": "7484.200s",
"startTime": "7484s",
"word": "is"
},
{
"endTime": "7484.300s",
"startTime": "7484.200s",
"word": "Moana"
}
]
}
],
"languageCode": "en-us"
},
{
"alternatives": [
{
"words": [
{
"endTime": "11.300s",
"speakerTag": 1,
"startTime": "10.400s",
"word": "love"
},
{
"endTime": "425.100s",
"speakerTag": 1,
"startTime": "424.500s",
"word": "you"
},
{
"endTime": "425.400s",
"speakerTag": 1,
"startTime": "425.100s",
"word": "are"
},
{
"endTime": "475.200s",
"speakerTag": 1,
"startTime": "473.800s",
"word": "how"
},
{
"endTime": "475.500s",
"speakerTag": 1,
"startTime": "475.200s",
"word": "far"
},
{
"endTime": "475.700s",
"speakerTag": 1,
"startTime": "475.500s",
"word": "is"
},
{
"endTime": "475.800s",
"speakerTag": 1,
"startTime": "475.700s",
"word": "it"
},
{
"endTime": "476.100s",
"speakerTag": 1,
"startTime": "475.800s",
"word": "from"
},
{
"endTime": "629.200s",
"speakerTag": 1,
"startTime": "626.700s",
"word": "I"
},
{
"endTime": "629.800s",
"speakerTag": 1,
"startTime": "629.200s",
"word": "want"
},
{
"endTime": "990.100s",
"speakerTag": 1,
"startTime": "989.500s",
"word": "Blue"
},
{
"endTime": "991.100s",
"speakerTag": 1,
"startTime": "990.100s",
"word": "Ivy"
},
{
"endTime": "1599.700s",
"speakerTag": 1,
"startTime": "1598.500s",
"word": "how"
},
{
"endTime": "1600.100s",
"speakerTag": 1,
"startTime": "1599.700s",
"word": "old"
},
{
"endTime": "1600.200s",
"speakerTag": 1,
"startTime": "1600.100s",
"word": "is"
},
{
"endTime": "1600.600s",
"speakerTag": 1,
"startTime": "1600.200s",
"word": "Wawa"
},
{
"endTime": "2022.400s",
"speakerTag": 1,
"startTime": "2020s",
"word": "how"
},
{
"endTime": "2022.500s",
"speakerTag": 1,
"startTime": "2022.400s",
"word": "are"
},
{
"endTime": "2022.600s",
"speakerTag": 1,
"startTime": "2022.500s",
"word": "you"
},
{
"endTime": "2066.200s",
"speakerTag": 1,
"startTime": "2065.800s",
"word": "New"
},
{
"endTime": "2066.500s",
"speakerTag": 1,
"startTime": "2066.200s",
"word": "York"
},
{
"endTime": "2067s",
"speakerTag": 1,
"startTime": "2066.500s",
"word": "mall"
},
{
"endTime": "2255.600s",
"speakerTag": 1,
"startTime": "2254.500s",
"word": "call"
},
{
"endTime": "3041.500s",
"speakerTag": 1,
"startTime": "3040.300s",
"word": "call"
},
{
"endTime": "3041.800s",
"speakerTag": 1,
"startTime": "3041.500s",
"word": "Paul"
},
{
"endTime": "3042.300s",
"speakerTag": 1,
"startTime": "3041.800s",
"word": "Wall"
},
{
"endTime": "3101.300s",
"speakerTag": 1,
"startTime": "3100.800s",
"word": "no"
},
{
"endTime": "3473.100s",
"speakerTag": 1,
"startTime": "3470.300s",
"word": "call"
},
{
"endTime": "3473.500s",
"speakerTag": 1,
"startTime": "3473.100s",
"word": "Jeff"
},
{
"endTime": "4166.100s",
"speakerTag": 1,
"startTime": "4162.400s",
"word": "call"
},
{
"endTime": "4166.400s",
"speakerTag": 1,
"startTime": "4166.100s",
"word": "home"
},
{
"endTime": "4231.800s",
"speakerTag": 1,
"startTime": "4231.300s",
"word": "how"
},
{
"endTime": "4232.200s",
"speakerTag": 1,
"startTime": "4231.800s",
"word": "old"
},
{
"endTime": "4232.300s",
"speakerTag": 1,
"startTime": "4232.200s",
"word": "are"
},
{
"endTime": "4232.400s",
"speakerTag": 1,
"startTime": "4232.300s",
"word": "you"
},
{
"endTime": "4244.200s",
"speakerTag": 1,
"startTime": "4243s",
"word": "Europe"
},
{
"endTime": "5121.500s",
"speakerTag": 1,
"startTime": "5115.300s",
"word": "how"
},
{
"endTime": "5122.100s",
"speakerTag": 1,
"startTime": "5121.500s",
"word": "are"
},
{
"endTime": "5122.300s",
"speakerTag": 1,
"startTime": "5122.100s",
"word": "you"
},
{
"endTime": "6199.900s",
"speakerTag": 1,
"startTime": "6199.600s",
"word": "the"
},
{
"endTime": "6200.400s",
"speakerTag": 1,
"startTime": "6199.900s",
"word": "only"
},
{
"endTime": "6200.800s",
"speakerTag": 1,
"startTime": "6200.400s",
"word": "one"
},
{
"endTime": "6258.800s",
"speakerTag": 1,
"startTime": "6256.800s",
"word": "call"
},
{
"endTime": "6925s",
"speakerTag": 1,
"startTime": "6912.300s",
"word": "Walgreens"
},
{
"endTime": "7155.900s",
"speakerTag": 1,
"startTime": "7155.500s",
"word": "we"
},
{
"endTime": "7156.500s",
"speakerTag": 1,
"startTime": "7155.900s",
"word": "want"
},
{
"endTime": "7156.600s",
"speakerTag": 1,
"startTime": "7156.500s",
"word": "to"
},
{
"endTime": "7156.700s",
"speakerTag": 1,
"startTime": "7156.600s",
"word": "watch"
},
{
"endTime": "7199.900s",
"speakerTag": 1,
"startTime": "7199.200s",
"word": "I"
},
{
"endTime": "7202.900s",
"speakerTag": 1,
"startTime": "7199.900s",
"word": "love"
},
{
"endTime": "7203.100s",
"speakerTag": 1,
"startTime": "7202.900s",
"word": "you"
},
{
"endTime": "7483.800s",
"speakerTag": 1,
"startTime": "7481.300s",
"word": "how"
},
{
"endTime": "7484s",
"speakerTag": 1,
"startTime": "7483.800s",
"word": "old"
},
{
"endTime": "7484.200s",
"speakerTag": 1,
"startTime": "7484s",
"word": "is"
},
{
"endTime": "7484.300s",
"speakerTag": 1,
"startTime": "7484.200s",
"word": "Moana"
}
]
}
]
}
]
}
}回答 2
Stack Overflow用户
发布于 2020-08-19 20:11:51
我遇到了同样的问题，特别是与数字化相关的地方没有好的表现。我也尝试从AWS获得我的脚本，但我发现单词错误率更高，但更好地识别从人到人的转换。
如您所知，这是一个beta特性，处于这个阶段，他们没有SLA (服务级别协议)需要完成。我向谷歌团队报告了这个错误，他们回答说：
在beta版本中没有SLA或技术支持义务，除非在产品术语中另有规定。平均测试阶段持续六个月左右。
所以我相信团队需要一段时间才能正式发布这个特性。
https://cloud.google.com/speech-to-text/docs/multiple-voices
Stack Overflow用户
发布于 2020-07-21 08:15:03
发言人标签，在这个API中是不推荐的，而且speakerTag很难给出准确的结果，我建议您使用ChannelTag来代替SpeakerTag，比如result.channelTag，您可能会得到更好的结果。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/62883413
复制相关文章
相似问题
腾讯云开发者
Copyright © 2013 - 2026 Tencent Cloud. All Rights Reserved. 腾讯云 版权所有
深圳市腾讯计算机系统有限公司 ICP备案/许可证号：粤B2-20090059 
粤公网安备44030502008569号
腾讯云计算（北京）有限责任公司 京ICP证150476号 | 京ICP备11018762号