public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Address document comment for RDoc

This commit is contained in:
Kitaiti Makoto 2026-04-23 07:07:35 +09:00
parent b89917298e
commit 63caba664d
1 changed files with 39 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

78
bindings/ruby/sig/whisper.rbs
View File

@ -52,7 +52,7 @@ module Whisper
# puts text
# end
#
# If n_processors is greater than 1, you cannot set any callbacks including
# If `n_processors` is greater than 1, you cannot set any callbacks including
# new_segment_callback, progress_callback, encoder_begin_callback, abort_callback,
# and log_callback set by Whisper.log_set
def transcribe: (path, Params, ?n_processors: Integer) -> self
@ -74,7 +74,7 @@ module Whisper
# puts segment.text
# end
#
# Returns an Enumerator if no block given:
# Returns an `Enumerator` if no block given:
#
# whisper.transcribe("path/to/audio.wav", params)
# enum = whisper.each_segment
@ -91,25 +91,25 @@ module Whisper
#
def full_lang_id: () -> Integer
# Start time of a segment indexed by +segment_index+ in centiseconds (10 times milliseconds).
# Start time of a segment indexed by `segment_index` in centiseconds (10 times milliseconds).
#
# full_get_segment_t0(3) # => 1668 (16680 ms)
#
def full_get_segment_t0: (Integer) -> Integer
# End time of a segment indexed by +segment_index+ in centiseconds (10 times milliseconds).
# End time of a segment indexed by `segment_index` in centiseconds (10 times milliseconds).
#
# full_get_segment_t1(3) # => 1668 (16680 ms)
#
def full_get_segment_t1: (Integer) -> Integer
# Whether the next segment indexed by +segment_index+ is predicated as a speaker turn.
# Whether the next segment indexed by `segment_index` is predicated as a speaker turn.
#
# full_get_segment_speacker_turn_next(3) # => true
#
def full_get_segment_speaker_turn_next: (Integer) -> (true | false)
# Text of a segment indexed by +segment_index+.
# Text of a segment indexed by `segment_index`.
#
# full_get_segment_text(3) # => "ask not what your country can do for you, ..."
#
@ -117,22 +117,22 @@ module Whisper
def full_get_segment_no_speech_prob: (Integer) -> Float
# Run the entire model: PCM -> log mel spectrogram -> encoder -> decoder -> text
# Not thread safe for same context
# Run the entire model: PCM -> log mel spectrogram -> encoder -> decoder -> text
# Not thread safe for same context
# Uses the specified decoding strategy to obtain the text.
#
# The second argument +samples+ must be an array of samples, respond to :length, or be a MemoryView of an array of float. It must be 32 bit float PCM audio data.
# The second argument `samples` must be an array of samples, respond to `:length`, or be a MemoryView of an array of float. It must be 32 bit float PCM audio data.
#
def full: (Params, Array[Float] samples, ?Integer n_samples) -> self
| (Params, _Samples, ?Integer n_samples) -> self
# Split the input audio in chunks and process each chunk separately using whisper_full_with_state()
# Result is stored in the default state of the context
# Not thread safe if executed in parallel on the same context.
# It seems this approach can offer some speedup in some cases.
# Split the input audio in chunks and process each chunk separately using `whisper_full_with_state()`
# Result is stored in the default state of the context
# Not thread safe if executed in parallel on the same context.
# It seems this approach can offer some speedup in some cases.
# However, the transcription accuracy can be worse at the beginning and end of each chunk.
#
# If n_processors is greater than 1, you cannot set any callbacks including
# If `n_processors` is greater than 1, you cannot set any callbacks including
# new_segment_callback, progress_callback, encoder_begin_callback, abort_callback,
# and log_callback set by Whisper.log_set
def full_parallel: (Params, Array[Float], ?Integer n_samples) -> self
@ -217,35 +217,35 @@ module Whisper
def translate: () -> (true | false)
def no_context=: (boolish) -> boolish
# If true, does not use past transcription (if any) as initial prompt for the decoder.
# If `true`, does not use past transcription (if any) as initial prompt for the decoder.
#
def no_context: () -> (true | false)
def single_segment=: (boolish) -> boolish
# If true, forces single segment output (useful for streaming).
# If `true`, forces single segment output (useful for streaming).
#
def single_segment: () -> (true | false)
def print_special=: (boolish) -> boolish
# If true, prints special tokens (e.g. <SOT>, <EOT>, <BEG>, etc.).
# If `true`, prints special tokens (e.g. <SOT>, <EOT>, <BEG>, etc.).
#
def print_special: () -> (true | false)
def print_progress=: (boolish) -> boolish
# If true, prints progress information.
# If `true`, prints progress information.
#
def print_progress: () -> (true | false)
def print_realtime=: (boolish) -> boolish
# If true, prints results from within whisper.cpp. (avoid it, use callback instead)
# If `true`, prints results from within whisper.cpp. (avoid it, use callback instead)
#
def print_realtime: () -> (true | false)
# If true, prints timestamps for each text segment when printing realtime.
# If `true`, prints timestamps for each text segment when printing realtime.
#
def print_timestamps=: (boolish) -> boolish
@ -253,19 +253,19 @@ module Whisper
def suppress_blank=: (boolish) -> boolish
# If true, suppresses blank outputs.
# If `true`, suppresses blank outputs.
#
def suppress_blank: () -> (true | false)
def suppress_nst=: (boolish) -> boolish
# If true, suppresses non-speech-tokens.
# If `true`, suppresses non-speech-tokens.
#
def suppress_nst: () -> (true | false)
def token_timestamps=: (boolish) -> boolish
# If true, enables token-level timestamps.
# If `true`, enables token-level timestamps.
#
def token_timestamps: () -> (true | false)
@ -277,16 +277,16 @@ module Whisper
def split_on_word=: (boolish) -> boolish
# If true, split on word rather than on token (when used with max_len).
# If `true`, split on word rather than on token (when used with max_len).
#
def split_on_word: () -> (true | false)
def initial_prompt=: (_ToS) -> _ToS
def carry_initial_prompt=: (boolish) -> boolish
# Tokens to provide to the whisper decoder as initial prompt
# these are prepended to any existing text context from a previous call
# use whisper_tokenize() to convert text to tokens.
# Tokens to provide to the whisper decoder as initial prompt
# these are prepended to any existing text context from a previous call
# use whisper_tokenize() to convert text to tokens.
# Maximum of whisper_n_text_ctx()/2 tokens are used (typically 224).
#
def initial_prompt: () -> (String | nil)
@ -294,7 +294,7 @@ module Whisper
def diarize=: (boolish) -> boolish
# If true, enables diarization.
# If `true`, enables diarization.
#
def diarize: () -> (true | false)
@ -423,7 +423,7 @@ module Whisper
#
def on_new_segment: { (Segment) -> void } -> void
# Hook called on progress update. Yields each progress Integer between 0 and 100.
# Hook called on progress update. Yields each progress `Integer` between 0 and 100.
#
def on_progress: { (Integer progress) -> void } -> void
@ -431,7 +431,7 @@ module Whisper
#
def on_encoder_begin: { () -> void } -> void
# Call block to determine whether abort or not. Return +true+ when you want to abort.
# Call block to determine whether abort or not. Return `true` when you want to abort.
#
# params.abort_on do
# if some_condition
@ -504,13 +504,13 @@ module Whisper
# Yields each Whisper::Token:
#
# whisper.each_segment.first.each_token do |token|
# p token
# end
# whisper.each_segment.first.each_token do |token|
# p token
# end
#
# Returns an Enumerator if no block is given:
# Returns an `Enumerator` if no block is given:
#
# whisper.each_segment.first.each_token.to_a # => [#<Whisper::Token>, ...]
# whisper.each_segment.first.each_token.to_a # => [#<Whisper::Token>, ...]
#
def each_token: { (Token) -> void } -> void
| () -> Enumerator[Token]
@ -518,7 +518,7 @@ module Whisper
def to_webvtt_cue: () -> String
# Possible keys: :start_time, :end_time, :text, :no_speech_prob, :speaker_turn_next
# Possible keys: `:start_time`, `:end_time`, `:text`, `:no_speech_prob`, `:speaker_turn_next`
#
# whisper.each_segment do |segment|
# segment => {start_time:, end_time:, text:, no_speech_prob:, speaker_turn_next:}
@ -569,7 +569,7 @@ module Whisper
# [EXPERIMENTAL] Token-level timestamps with DTW
#
# Do not use if you haven't computed token-level timestamps with dtw.
# Do not use if you haven't computed token-level timestamps with dtw.
# Roughly corresponds to the moment in audio in which the token was output.
#
def t_dtw: () -> Integer
@ -580,14 +580,14 @@ module Whisper
# Start time of the token.
#
# Token-level timestamp data.
# Token-level timestamp data.
# Do not use if you haven't computed token-level timestamps.
#
def start_time: () -> Integer
# End time of the token.
#
# Token-level timestamp data.
# Token-level timestamp data.
# Do not use if you haven't computed token-level timestamps.
#
def end_time: () -> Integer