Class: Google::Cloud::Speech::V2::WordInfo
- Inherits:
-
Object
- Object
- Google::Cloud::Speech::V2::WordInfo
- Extended by:
- Protobuf::MessageExts::ClassMethods
- Includes:
- Protobuf::MessageExts
- Defined in:
- proto_docs/google/cloud/speech/v2/cloud_speech.rb
Overview
Word-specific information for recognized words.
Instance Attribute Summary collapse
-
#confidence ⇒ ::Float
The confidence estimate between 0.0 and 1.0.
-
#end_offset ⇒ ::Google::Protobuf::Duration
Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word.
-
#speaker_label ⇒ ::String
A distinct label is assigned for every speaker within the audio.
-
#start_offset ⇒ ::Google::Protobuf::Duration
Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word.
-
#word ⇒ ::String
The word corresponding to this set of information.
Instance Attribute Details
#confidence ⇒ ::Float
Returns The confidence estimate between 0.0 and 1.0. A higher number
indicates an estimated greater likelihood that the recognized words are
correct. This field is set only for the top alternative of a non-streaming
result or, of a streaming result where
is_final is
set to true
. This field is not guaranteed to be accurate and users should
not rely on it to be always provided. The default of 0.0 is a sentinel
value indicating confidence
was not set.
797 798 799 800 |
# File 'proto_docs/google/cloud/speech/v2/cloud_speech.rb', line 797 class WordInfo include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#end_offset ⇒ ::Google::Protobuf::Duration
Returns Time offset relative to the beginning of the audio,
and corresponding to the end of the spoken word.
This field is only set if
enable_word_time_offsets
is true
and only in the top hypothesis. This is an experimental feature
and the accuracy of the time offset can vary.
797 798 799 800 |
# File 'proto_docs/google/cloud/speech/v2/cloud_speech.rb', line 797 class WordInfo include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#speaker_label ⇒ ::String
Returns A distinct label is assigned for every speaker within the audio. This field
specifies which one of those speakers was detected to have spoken this
word. speaker_label
is set if
SpeakerDiarizationConfig
is given and only in the top alternative.
797 798 799 800 |
# File 'proto_docs/google/cloud/speech/v2/cloud_speech.rb', line 797 class WordInfo include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#start_offset ⇒ ::Google::Protobuf::Duration
Returns Time offset relative to the beginning of the audio,
and corresponding to the start of the spoken word.
This field is only set if
enable_word_time_offsets
is true
and only in the top hypothesis. This is an experimental feature
and the accuracy of the time offset can vary.
797 798 799 800 |
# File 'proto_docs/google/cloud/speech/v2/cloud_speech.rb', line 797 class WordInfo include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |