ddidderr
a5c535cfb9
Sending entire recordings in one request can exceed provider limits. Decode audio once to a shared PCM sample clock and split uploads at a configurable maximum of 1 to 30 minutes, defaulting to 30 minutes. Prefer nearby pauses and include six seconds of overlap to protect words at audio cuts while keeping each encoded MP3 within the duration cap. Request word timestamps for chunked text and SRT output. Match overlapping words and times to retain each passage once, warn when a join falls back to timestamps, and generate SRT cues on the original recording timeline. Reuse subtitle timestamp validation without reordering regressing words. Only emit output after every request and conversion succeeds. Document the Python dependency, temporary storage, boundary limitations, and lack of automatic retry or resume. Keep single-request text formatting. Test Plan: - python3 -B -m unittest -v: all 29 tests passed, including mocked provider failures, native MP3 payload checks, boundary stitching, and SRT timing. - bash -n transcribe and shellcheck transcribe: passed. - git diff --cached --check: passed. - Locally decoded and encoded the supplied 74-minute WebM into three MP3 chunks; ffprobe confirmed each duration was below 30 minutes. - Live transcription was not verified: the configured 1Password credential was unavailable.
96 lines
4.1 KiB
Python
96 lines
4.1 KiB
Python
import json
|
|
import os
|
|
from pathlib import Path
|
|
import shutil
|
|
import subprocess
|
|
import tempfile
|
|
import unittest
|
|
|
|
from test_chunks import make_audio
|
|
|
|
ROOT = Path(__file__).resolve().parent
|
|
TOOLS = ("bash", "ffmpeg", "ffprobe", "jq", "base64", "mktemp", "realpath")
|
|
|
|
|
|
@unittest.skipUnless(all(shutil.which(tool) for tool in TOOLS), "CLI media dependencies missing")
|
|
class TranscribeTests(unittest.TestCase):
|
|
def setUp(self):
|
|
self.directory = tempfile.TemporaryDirectory()
|
|
self.addCleanup(self.directory.cleanup)
|
|
self.path = Path(self.directory.name)
|
|
self.bin = self.path / "bin"
|
|
self.bin.mkdir()
|
|
for name in ("op", "curl"):
|
|
fake = self.bin / name
|
|
shutil.copyfile(ROOT / "tests" / "fake_provider.py", fake)
|
|
fake.chmod(0o755)
|
|
self.log = self.path / "requests.jsonl"
|
|
self.env = dict(os.environ, PATH=f"{self.bin}{os.pathsep}{os.environ['PATH']}",
|
|
TRANSCRIBE_TEST_LOG=str(self.log), TRANSCRIBE_TEST_MODE="ok")
|
|
self.audio = self.path / "input with spaces.wav"
|
|
|
|
def run_cli(self, *args, mode="ok", duration=70):
|
|
make_audio(self.audio, duration)
|
|
return subprocess.run([str(ROOT / "transcribe"), *args, str(self.audio)],
|
|
env=dict(self.env, TRANSCRIBE_TEST_MODE=mode),
|
|
capture_output=True, text=True, timeout=30)
|
|
|
|
def requests(self):
|
|
return [json.loads(line) for line in self.log.read_text().splitlines()]
|
|
|
|
def assert_cleaned(self):
|
|
self.assertTrue(all(not Path(r["staging"]).exists() for r in self.requests()))
|
|
|
|
def test_long_text_uploads_bounded_mp3_and_stitches_once(self):
|
|
result = self.run_cli("--chunk-minutes", "1")
|
|
self.assertEqual(result.returncode, 0, result.stderr)
|
|
self.assertEqual(result.stdout, "Hello. boundary continues. Last.\n")
|
|
self.assertIn("chunk 2/2", result.stderr)
|
|
requests = self.requests()
|
|
self.assertEqual(len(requests), 2)
|
|
self.assertAlmostEqual(requests[0]["chunk"]["end"] - requests[1]["chunk"]["start"], 6)
|
|
self.assert_cleaned()
|
|
|
|
def test_long_srt_uses_original_timeline_and_continuous_numbers(self):
|
|
result = self.run_cli("--srt", "--chunk-minutes", "1")
|
|
self.assertEqual(result.returncode, 0, result.stderr)
|
|
self.assertEqual(result.stdout, (
|
|
"1\n00:00:01,000 --> 00:00:01,400\nHello.\n\n"
|
|
"2\n00:00:56,700 --> 00:00:57,800\nboundary continues.\n\n"
|
|
"3\n00:01:05,000 --> 00:01:05,400\nLast.\n\n"
|
|
))
|
|
self.assert_cleaned()
|
|
|
|
def test_short_text_retains_provider_formatting(self):
|
|
result = self.run_cli(duration=5)
|
|
self.assertEqual(result.returncode, 0, result.stderr)
|
|
self.assertEqual(result.stdout, "Provider's original formatting.\nNext line.\n")
|
|
self.assertEqual(len(self.requests()), 1)
|
|
self.assert_cleaned()
|
|
|
|
def test_short_srt_still_requests_word_timestamps(self):
|
|
result = self.run_cli("--srt", duration=5)
|
|
self.assertEqual(result.returncode, 0, result.stderr)
|
|
self.assertEqual(result.stdout, "1\n00:00:01,000 --> 00:00:01,400\nHello.\n\n")
|
|
|
|
def test_failed_later_chunk_has_no_partial_stdout_and_cleans_up(self):
|
|
for mode in ("http-error", "bad-json", "api-error", "missing-words"):
|
|
with self.subTest(mode=mode):
|
|
result = self.run_cli("--chunk-minutes", "1", mode=mode)
|
|
self.assertNotEqual(result.returncode, 0)
|
|
self.assertEqual(result.stdout, "")
|
|
self.assertTrue(result.stderr)
|
|
self.assert_cleaned()
|
|
|
|
def test_invalid_limits_fail_before_provider_access(self):
|
|
for value in ("0", "31", "abc", "1.5", "-1"):
|
|
with self.subTest(value=value):
|
|
result = self.run_cli("--chunk-minutes", value, duration=1)
|
|
self.assertNotEqual(result.returncode, 0)
|
|
self.assertIn("integer between 1 and 30", result.stderr)
|
|
self.assertFalse(self.log.exists())
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|