mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-06-12 20:18:08 +00:00
* 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
137 lines
3.7 KiB
Ruby
137 lines
3.7 KiB
Ruby
require_relative "helper"
|
|
|
|
class TestSegment < TestBase
|
|
def test_iteration
|
|
whisper.each_segment do |segment|
|
|
assert_instance_of Whisper::Segment, segment
|
|
end
|
|
end
|
|
|
|
def test_enumerator
|
|
enum = whisper.each_segment
|
|
assert_instance_of Enumerator, enum
|
|
enum.to_a.each_with_index do |segment, index|
|
|
assert_instance_of Whisper::Segment, segment
|
|
assert_kind_of Integer, index
|
|
end
|
|
end
|
|
|
|
def test_start_time
|
|
i = 0
|
|
whisper.each_segment do |segment|
|
|
assert_equal 0, segment.start_time if i == 0
|
|
i += 1
|
|
end
|
|
end
|
|
|
|
def test_end_time
|
|
i = 0
|
|
whisper.each_segment do |segment|
|
|
assert_equal whisper.full_get_segment_t1(i) * 10, segment.end_time
|
|
i += 1
|
|
end
|
|
end
|
|
|
|
def test_no_speech_prob
|
|
no_speech_prob = nil
|
|
whisper.each_segment do |segment|
|
|
no_speech_prob = segment.no_speech_prob
|
|
end
|
|
assert no_speech_prob > 0.0
|
|
end
|
|
|
|
def test_on_new_segment
|
|
params = Whisper::Params.new
|
|
seg = nil
|
|
index = 0
|
|
params.on_new_segment do |segment|
|
|
assert_instance_of Whisper::Segment, segment
|
|
if index == 0
|
|
seg = segment
|
|
assert_equal 0, segment.start_time
|
|
assert_match(/ask not what your country can do for you, ask what you can do for your country/, segment.text)
|
|
end
|
|
index += 1
|
|
end
|
|
whisper.transcribe(AUDIO, params)
|
|
assert_equal 0, seg.start_time
|
|
assert_match(/ask not what your country can do for you, ask what you can do for your country/, seg.text)
|
|
end
|
|
|
|
def test_on_new_segment_twice
|
|
params = Whisper::Params.new
|
|
seg = nil
|
|
params.on_new_segment do |segment|
|
|
seg = segment
|
|
return
|
|
end
|
|
params.on_new_segment do |segment|
|
|
assert_same seg, segment
|
|
return
|
|
end
|
|
whisper.transcribe(AUDIO, params)
|
|
end
|
|
|
|
def test_pattern_matching
|
|
segment = whisper.each_segment.first
|
|
segment => {start_time:, end_time:, text:, no_speech_prob:, speaker_turn_next:}
|
|
|
|
assert_equal segment.start_time, start_time
|
|
assert_equal segment.end_time, end_time
|
|
assert_equal segment.text, text
|
|
assert_equal segment.no_speech_prob, no_speech_prob
|
|
assert_equal segment.speaker_turn_next?, speaker_turn_next
|
|
end
|
|
|
|
def test_pattern_matching_partial
|
|
segment = whisper.each_segment.first
|
|
segment => {start_time:, end_time:, text:}
|
|
|
|
assert_equal segment.start_time, start_time
|
|
assert_equal segment.end_time, end_time
|
|
assert_equal segment.text, text
|
|
end
|
|
|
|
def test_deconstruct_keys
|
|
segment = whisper.each_segment.first
|
|
expected = {
|
|
start_time: segment.start_time,
|
|
end_time: segment.end_time,
|
|
text: segment.text,
|
|
no_speech_prob: segment.no_speech_prob,
|
|
speaker_turn_next: segment.speaker_turn_next?
|
|
}
|
|
assert_equal expected, segment.deconstruct_keys([:start_time, :end_time, :text, :no_speech_prob, :speaker_turn_next])
|
|
end
|
|
|
|
def test_deconstruct_keys_non_existent
|
|
omit "Undefined behavior"
|
|
|
|
segment = whisper.each_segment.first
|
|
|
|
assert_equal({}, segment.deconstruct_keys([:non_existent]))
|
|
end
|
|
|
|
def test_deconstruct_keys_too_many_keys
|
|
omit "Undefined behavior"
|
|
|
|
segment = whisper.each_segment.first
|
|
|
|
assert_equal({}, segment.deconstruct_keys([:start_time, :end_time, :text, :no_speech_prob, :speaker_turn_next, :extra_key]))
|
|
end
|
|
|
|
def test_deconstruct_keys_includes_non_existent_keys_not_too_many
|
|
omit "Undefined behavior"
|
|
|
|
segment = whisper.each_segment.first
|
|
|
|
expected = {
|
|
start_time: segment.start_time,
|
|
end_time: segment.end_time,
|
|
text: segment.text,
|
|
no_speech_prob: segment.no_speech_prob
|
|
}
|
|
assert_equal(expected, segment.deconstruct_keys([:start_time, :end_time, :text, :no_speech_prob, :non_existent]))
|
|
end
|
|
end
|