Google 云视频智能语音转录
Google Cloud Video Intelligence Speech Transcription
我尝试通过 Video Inteligence 使用语音转录,但出现以下错误:
input_uri: "/supereye1.appspot.com/video/8rsxVe23pzQ/videofile.mp4"
error {
code: 3
message: "Invalid SpeechTranscription request argument(s)."
}
segment {
start_time_offset {
}
end_time_offset {
nanos: 673378000
}
}
这是我的代码:
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.enums.Feature.OBJECT_TRACKING,
videointelligence.enums.Feature.TEXT_DETECTION,
videointelligence.enums.Feature.SPEECH_TRANSCRIPTION,
videointelligence.enums.Feature.SHOT_CHANGE_DETECTION]
operation = video_client.annotate_video(gs_video_path, features=features)
我该如何解决这个问题?
以下设置是使用 Google Cloud 进行语音转录的先决条件。
现在,我在调用之前设置它们,我可以成功执行视频情报调用。
config = videointelligence.types.SpeechTranscriptionConfig(
language_code = "en-GB",
enable_automatic_punctuation=True,
)
context = videointelligence.types.VideoContext(
segments=None,
speech_transcription_config=config,
)
我尝试通过 Video Inteligence 使用语音转录,但出现以下错误:
input_uri: "/supereye1.appspot.com/video/8rsxVe23pzQ/videofile.mp4"
error {
code: 3
message: "Invalid SpeechTranscription request argument(s)."
}
segment {
start_time_offset {
}
end_time_offset {
nanos: 673378000
}
}
这是我的代码:
video_client = videointelligence.VideoIntelligenceServiceClient()
features = [videointelligence.enums.Feature.OBJECT_TRACKING,
videointelligence.enums.Feature.TEXT_DETECTION,
videointelligence.enums.Feature.SPEECH_TRANSCRIPTION,
videointelligence.enums.Feature.SHOT_CHANGE_DETECTION]
operation = video_client.annotate_video(gs_video_path, features=features)
我该如何解决这个问题?
以下设置是使用 Google Cloud 进行语音转录的先决条件。
现在,我在调用之前设置它们,我可以成功执行视频情报调用。
config = videointelligence.types.SpeechTranscriptionConfig(
language_code = "en-GB",
enable_automatic_punctuation=True,
)
context = videointelligence.types.VideoContext(
segments=None,
speech_transcription_config=config,
)