Class: OpenAI::Models::Audio::TranscriptionSegment

Inherits:
Internal::Type::BaseModel show all
Defined in:
lib/openai/models/audio/transcription_segment.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods inherited from Internal::Type::BaseModel

==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, #inspect, inspect, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize(id: , avg_logprob: , compression_ratio: , end_: , no_speech_prob: , seek: , start: , temperature: , text: , tokens: ) ⇒ Object

Some parameter documentations has been truncated, see OpenAI::Models::Audio::TranscriptionSegment for more details.

Parameters:

  • id (Integer) (defaults to: ) —

    Unique identifier of the segment.

  • avg_logprob (Float) (defaults to: ) —

    Average logprob of the segment. If the value is lower than -1, consider the logp

  • compression_ratio (Float) (defaults to: ) —

    Compression ratio of the segment. If the value is greater than 2.4, consider the

  • end_ (Float) (defaults to: ) —

    End time of the segment in seconds.

  • no_speech_prob (Float) (defaults to: ) —

    Probability of no speech in the segment. If the value is higher than 1.0 and the

  • seek (Integer) (defaults to: ) —

    Seek offset of the segment.

  • start (Float) (defaults to: ) —

    Start time of the segment in seconds.

  • temperature (Float) (defaults to: ) —

    Temperature parameter used for generating the segment.

  • text (String) (defaults to: ) —

    Text content of the segment.

  • tokens (Array<Integer>) (defaults to: ) —

    Array of token IDs for the text content.




# File 'lib/openai/models/audio/transcription_segment.rb', line 70

Instance Attribute Details

#avg_logprob ⇒ Float

Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.

Returns:

  • (Float) 


18
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 18

required :avg_logprob, Float

#compression_ratio ⇒ Float

Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.

Returns:

  • (Float) 


25
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 25

required :compression_ratio, Float

#end_ ⇒ Float

End time of the segment in seconds.

Returns:

  • (Float) 


31
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 31

required :end_, Float, api_name: :end

#id ⇒ Integer

Unique identifier of the segment.

Returns:

  • (Integer) 


11
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 11

required :id, Integer

#no_speech_prob ⇒ Float

Probability of no speech in the segment. If the value is higher than 1.0 and the ‘avg_logprob` is below -1, consider this segment silent.

Returns:

  • (Float) 


38
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 38

required :no_speech_prob, Float

#seek ⇒ Integer

Seek offset of the segment.

Returns:

  • (Integer) 


44
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 44

required :seek, Integer

#start ⇒ Float

Start time of the segment in seconds.

Returns:

  • (Float) 


50
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 50

required :start, Float

#temperature ⇒ Float

Temperature parameter used for generating the segment.

Returns:

  • (Float) 


56
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 56

required :temperature, Float

#text ⇒ String

Text content of the segment.

Returns:

  • (String) 


62
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 62

required :text, String

#tokens ⇒ Array<Integer>

Array of token IDs for the text content.

Returns:

  • (Array<Integer>) 


68
 
# File 'lib/openai/models/audio/transcription_segment.rb', line 68

required :tokens, OpenAI::Internal::Type::ArrayOf[Integer]