The small local model heard the two-word hallo welt clip as English, both the recording and an espeak-ng rendering; the espeak-ng sentence Hallo Welt, heute teste ich die Spracheingabe. is detected as German. The integration test checks the language and the start of the transcript, and 013 decision 8 records the change (operator 2026-11-17). 🎯 Fix: 95 % 💥 Break: 2 % 💸 Tokens: 100 % ⏱️ Velocity: 100 % 🛡️ Security: 100 % (the WAV fixture is binary, not scanned) 🏆 Score: 93 🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 % Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
38 lines
1.6 KiB
Python
38 lines
1.6 KiB
Python
from __future__ import annotations
|
|
|
|
import dataclasses
|
|
import json
|
|
import os
|
|
import unittest
|
|
from pathlib import Path
|
|
from unittest import mock
|
|
|
|
from hub_case import HubCase
|
|
from test_hub_voice_input import FIXTURES, spoken
|
|
|
|
WHISPER = Path(os.environ.get("KVB_WHISPER_CLI", "/nonexistent/whisper-cli"))
|
|
MODEL = Path(os.environ.get("KVB_WHISPER_MODEL", "/nonexistent/ggml-small-q8_0.bin"))
|
|
QUEUED = os.environ.get("KVB_VOICE_INTEGRATION") == "1"
|
|
READY = os.access(WHISPER, os.X_OK) and MODEL.is_file()
|
|
REASON = (
|
|
"real Whisper run: needs KVB_WHISPER_CLI and KVB_WHISPER_MODEL from the operator rows of requirement 013 "
|
|
"and KVB_VOICE_INTEGRATION=1, which only the queue.py hold command line sets"
|
|
)
|
|
|
|
|
|
@unittest.skipUnless(QUEUED and READY, REASON)
|
|
class TestVoiceModel(HubCase):
|
|
def test_the_real_model_transcribes_the_german_and_the_english_fixture(self):
|
|
speech = self.httpd.hub.speech
|
|
with mock.patch.object(speech, "engines", dataclasses.replace(speech.engines, whisper=WHISPER, whisper_model=MODEL)):
|
|
for name, language, words in (("hallo-welt.wav", "de", "hallo welt"), ("hello-world.wav", "en", "hello world")):
|
|
with self.subTest(name=name):
|
|
status, _, body = self.call("POST", "/api/stt", (FIXTURES / name).read_bytes(), {**self.guard(self.host), "Content-Type": "audio/wav"})
|
|
self.assertEqual(status, 200, body)
|
|
found = json.loads(body)
|
|
self.assertEqual((found["language"], spoken(found["text"]).startswith(words)), (language, True), found)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|