ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-21 16:09:55 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

ruby : output format (#3237)

Browse Source 
* Fix a typo

* Don't allocate output string unless needed

* Add methods to output SRT and WebVTT

* Add tests for output methods

* Make constants for output private

* Add signatures for output methods

* Add document on output methods

* Fix method name: Segment#speaker_next_turn? -> #speacker_turn_next?

* Add Whisper::Segment#descotruct_keys

* Add test for Whisper::Context#descotruct_keys

* Add signature of Whisper::Segment#deconstruct_keys

* Use parentheses to suppress warning

* Update date
This commit is contained in:
KITAITI Makoto
2025-06-10 13:10:17 +09:00
committed by GitHub
parent d78f081423
commit fbead67549
11 changed files with 317 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
bindings/ruby/sig/whisper.rbs
View File

@ -116,6 +116,9 @@ module Whisper
def full_parallel: (Params, Array[Float], ?Integer n_samples) -> self
| (Params, _Samples, ?Integer n_samples) -> self
| (Params, _Samples, ?Integer? n_samples, Integer n_processors) -> self
def to_srt: () -> String
def to_webvtt: () -> String
end
class Params
@ -415,6 +418,14 @@ module Whisper
end
class Segment
type deconstructed_keys = {
start_time: (Integer | nil),
end_time: (Integer | nil),
text: (String | nil),
no_speech_prob: (Float | nil),
speaker_turn_next: (true | false | nil)
}
# Start time in milliseconds.
#
def start_time: () -> Integer
@ -424,10 +435,21 @@ module Whisper
def end_time: () -> Integer
# Whether the next segment is predicted as a speaker turn.
def speaker_next_turn?: () -> (true | false)
def speaker_turn_next?: () -> (true | false)
def text: () -> String
def no_speech_prob: () -> Float
def to_srt_cue: () -> String
def to_webvtt_cue: () -> String
# 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:}
#
# puts "[#{start_time} --> #{end_time}] #{text} (no speech prob: #{no_speech_prob}#{speaker_turn_next ? ', speaker turns next' : ''})"
# end
def deconstruct_keys: (Array[:start_time | :end_time | :text | :no_speech_prob | :speaker_turn_next] | nil) -> deconstructed_keys
end
module VAD