Files
javis_bot/tests/test_voice_worker_gate.py
javis-bot 628d89c4f1 feat(voice_worker): finals are also decoded with the recent conversation as Whisper's prompt
The words of the topic were the ones misheard live (화면공이 for 화면 공유, 계산지 for 계산기), and
five models made the same mistakes. Each final is decoded as before and again with the last 180 s
of the channel's conversation (everyone's finals and Jarvis's speech, at most context_chars=200
characters) as the previous-text prompt; the prompted text is used only when the plain one was kept,
stays within half its letters and keeps every hotword count, as for the hint.

Measured on the game PC (RTX 5070 Ti, 100 recordings of the user, 16 with their own text): CER
12.0% -> 7.5%, empty results unchanged, noise clips with text unchanged (16/108), final decode
p95 170 -> 253 ms. Finals with a context are decoded one clip at a time (ctranslate2 needs the
start token at one position in a batch).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-19 19:38:10 +09:00

135 lines
5.5 KiB
Python

"""Voice worker: which Whisper transcripts are kept (the hallucination gate), model-free."""
from __future__ import annotations
import pytest
from voice_worker.stt_whisper import MIN_MEAN_LOGPROB, choose_with_hint, compression_ratio, keep_transcript
@pytest.mark.unit
def test_a_confident_transcript_is_kept():
assert keep_transcript("자비스, 오늘 서울 날씨 어때?", -0.05)
@pytest.mark.unit
def test_low_confidence_is_rejected_even_for_a_short_output():
# A three-token hallucination on laughter scored a mean of -0.73 per token; the length
# correction used before (len / (len + 1)) lifted it to -0.55 and let it through.
assert not keep_transcript("자비스", MIN_MEAN_LOGPROB - 0.03)
assert keep_transcript("자비스", MIN_MEAN_LOGPROB + 0.03)
@pytest.mark.unit
def test_empty_and_punctuation_only_outputs_are_rejected():
assert not keep_transcript("", -0.01)
assert not keep_transcript(" . . ", -0.01)
@pytest.mark.unit
def test_a_repetition_loop_is_rejected():
loop = "자막 제공 및 " * 12
assert compression_ratio(loop) > 2.4
assert not keep_transcript(loop, -0.1)
assert compression_ratio("오늘 회의는 오후 세 시에 시작해서 다섯 시쯤 끝날 것 같아요.") < 2.4
HINT = ("자비스",)
ASK = "지금 두 번째 모니터에 뭐 떠 있는지 알려줄래?"
@pytest.mark.unit
def test_voice_like_noise_that_the_hint_turns_into_the_wake_word_gives_nothing():
# Laughter, decoded with the wake word as a hint and without it.
assert choose_with_hint("자비스", -0.4, "감사합니다.", -1.4, HINT) == ""
assert choose_with_hint("자비스", -0.4, "", -0.1, HINT) == ""
@pytest.mark.unit
def test_a_wake_word_the_hint_adds_to_real_speech_is_dropped():
assert choose_with_hint(ASK + " 자비스", -0.1, ASK, -0.1, HINT) == ASK
@pytest.mark.unit
def test_a_one_letter_wake_word_the_hint_adds_is_dropped():
assert choose_with_hint("봇 오늘 날씨 알려 줘", -0.1, "오늘 날씨 알려 줘", -0.1, ("봇",)) == "오늘 날씨 알려 줘"
@pytest.mark.unit
def test_the_hint_may_not_turn_a_similar_real_word_into_the_wake_word():
assert choose_with_hint("자비스 신청해 줘", -0.1, "서비스 신청해 줘", -0.1, HINT) == "서비스 신청해 줘"
@pytest.mark.unit
def test_a_near_miss_spelling_is_left_as_heard_rather_than_guessed():
# "자비수" may be the wake word or another word; text alone cannot tell, so the plain decode stands
# and fuzzy wake word matching is left to the call detection that reads it.
plain = "자비수, 오늘 서울 날씨 어때?"
assert choose_with_hint("자비스, 오늘 서울 날씨 어때?", -0.1, plain, -0.2, HINT) == plain
@pytest.mark.unit
def test_the_hint_is_used_when_it_keeps_the_wake_words_as_they_were():
hinted = "자비스, 철수 화면 공유 보여 줘"
assert choose_with_hint(hinted, -0.1, "자비스 철수 화면공유 보여줘", -0.15, HINT) == hinted
@pytest.mark.unit
def test_a_wake_word_the_hint_loses_is_kept_from_the_plain_decode():
plain = "자비스, 오늘 서울 날씨 어때?"
assert choose_with_hint("오늘 서울 날씨 어때?", -0.2, plain, -0.07, HINT) == plain
@pytest.mark.unit
def test_an_unsure_hint_decode_falls_back_to_the_plain_one():
assert choose_with_hint(ASK, MIN_MEAN_LOGPROB - 0.2, ASK, -0.1, HINT) == ASK
assert choose_with_hint("zzz", -0.1, ASK, -0.1, HINT) == ASK
@pytest.mark.unit
def test_wake_word_matching_ignores_case_spacing_and_punctuation():
assert choose_with_hint("Hey Jarvis, lights off.", -0.1, "hey jarvis lights off", -0.1, ("jarvis",)) \
== "Hey Jarvis, lights off."
@pytest.mark.unit
def test_spacing_and_punctuation_differences_do_not_change_the_choice():
assert choose_with_hint("자비스 오늘 서울 날씨 어때", -0.1, "자비스, 오늘 서울 날씨 어때?", -0.1, HINT) \
== "자비스 오늘 서울 날씨 어때"
# The recent conversation as Whisper's previous-text prompt (voice_worker.spec.md, "Conversation
# context"). Live 2026-11-19 the prompt fixed words of the topic ("화면공이" -> "화면 공유", "계산지" ->
# "계산기"); on noise it wrote words of the prompt. The decode without it decides, as with the hint.
from voice_worker.stt_whisper import choose_with_context # noqa: E402
@pytest.mark.unit
def test_the_context_may_fix_words_of_what_was_said():
assert choose_with_context("내 화면공이 안 보여?", "내 화면 공유 안 보여?", HINT) == "내 화면 공유 안 보여?"
@pytest.mark.unit
def test_nothing_heard_without_the_context_stays_nothing():
# Noise: the prompted decode wrote words of the conversation.
assert choose_with_context("", "화면에 디스코드", HINT) == ""
@pytest.mark.unit
def test_a_prompted_decode_far_from_what_was_heard_is_not_used():
heard = "가상화면을 못 봐"
copied = "네, 현재 화면에 디스코드 채팅 창과 여러 프로그램이 정상적으로 보입니다."
assert choose_with_context(heard, copied, HINT) == heard
@pytest.mark.unit
def test_the_context_never_changes_how_many_wake_words_were_heard():
assert choose_with_context("라비스 지금 영상 재생되고 있어?", "자비스 지금 영상 재생되고 있어?", HINT) \
== "라비스 지금 영상 재생되고 있어?"
assert choose_with_context("자비스 날씨 알려 줘", "날씨 알려 줘", HINT) == "자비스 날씨 알려 줘"
@pytest.mark.unit
def test_an_empty_prompted_decode_keeps_what_was_heard():
assert choose_with_context("네.", "", HINT) == "네."