ddidderr
38894c2549
Chunked text output previously joined every word into one line and discarded speaker labels. Add a shared plain-text formatter that wraps lines, breaks paragraphs at speaker changes and pauses, and splits long turns while preserving word order. Display provider speaker IDs with chunk scope where needed, without implying that IDs identify the same person across requests. Request structured output for short diarized recordings too, and warn when speaker labels are missing or incomplete. Keep SRT formatting separate and preserve existing line breaks for short requests without diarization. Test Plan: - python3 -B -m unittest -q: all 43 tests passed. - bash -n transcribe and git diff --cached --check: passed. - Reflowed the existing transcript locally and verified all 15,888 words were preserved; source audio and generated transcripts are not committed. - A live excerpt check was blocked before upload by unavailable 1Password access; actual provider diarization remains unverified.
75 lines
3.4 KiB
Python
75 lines
3.4 KiB
Python
import copy
|
|
import unittest
|
|
|
|
from chunks import merge
|
|
from transcript import render_text
|
|
|
|
|
|
def word(text, start, speaker=None):
|
|
return {"word": text, "start": start, "end": start + 0.4, "speaker": speaker}
|
|
|
|
|
|
class TranscriptTests(unittest.TestCase):
|
|
def test_turns_preserve_zero_speaker_id_and_do_not_invent_unknown_ids(self):
|
|
response = {"words": [
|
|
word("Hello", 1, 0), word("there.", 1.5, 0),
|
|
word("Hi!", 2, 1), word("Unlabelled", 2.5), word("Again.", 3, 0),
|
|
]}
|
|
original = copy.deepcopy(response)
|
|
self.assertEqual(render_text(response), (
|
|
"[Speaker 0]\nHello there.\n\n[Speaker 1]\nHi!\n\n"
|
|
"[Speaker unknown]\nUnlabelled\n\n[Speaker 0]\nAgain.\n"
|
|
))
|
|
self.assertEqual(response, original)
|
|
|
|
def test_speaker_ids_are_scoped_to_chunks_even_when_numbers_match(self):
|
|
response = merge(
|
|
[{"start": 0, "end": 63, "seam": 0}, {"start": 57, "end": 100, "seam": 60}],
|
|
[{"words": [word("First.", 1, 0)]}, {"words": [word("Second.", 10, 0)]}],
|
|
)
|
|
self.assertEqual(render_text(response), (
|
|
"[Chunk 1, Speaker 0]\nFirst.\n\n[Chunk 2, Speaker 0]\nSecond.\n"
|
|
))
|
|
|
|
def test_long_unpunctuated_turn_is_wrapped_and_split_without_losing_words(self):
|
|
tokens = [f"word{i}" for i in range(400)]
|
|
result = render_text({"words": [word(token, i * 0.5) for i, token in enumerate(tokens)]})
|
|
self.assertTrue(all(len(line) <= 80 for line in result.splitlines()))
|
|
self.assertGreater(len(result.split("\n\n")), 1)
|
|
self.assertEqual(result.split(), tokens)
|
|
self.assertNotIn("Speaker", result)
|
|
|
|
def test_long_paragraph_prefers_sentence_boundary(self):
|
|
first = ["word"] * 85 + ["end."]
|
|
tokens = first + ["Next", "sentence."]
|
|
result = render_text({"words": [word(token, i * 0.5) for i, token in enumerate(tokens)]})
|
|
blocks = result.split("\n\n")
|
|
self.assertEqual([block.split() for block in blocks], [first, ["Next", "sentence."]])
|
|
|
|
def test_pause_breaks_paragraph_and_repeats_the_speaker_marker(self):
|
|
self.assertEqual(render_text({"words": [word("Before", 1, 0), word("After", 4, 0)]}),
|
|
"[Speaker 0]\nBefore\n\n[Speaker 0]\nAfter\n")
|
|
|
|
def test_text_only_preserves_existing_breaks_and_reflows_long_lines(self):
|
|
text = "Original line.\nNext line.\n\n" + "A sentence with several words. " * 50
|
|
result = render_text({"text": text})
|
|
self.assertTrue(result.startswith("Original line.\nNext line.\n\n"))
|
|
self.assertTrue(all(len(line) <= 80 for line in result.splitlines()))
|
|
self.assertGreater(result.count("\n\n"), 1)
|
|
self.assertEqual(result.split(), text.split())
|
|
|
|
def test_empty_and_long_unbroken_word(self):
|
|
self.assertEqual(render_text({"text": ""}), "")
|
|
self.assertEqual(render_text({"text": "", "words": []}), "")
|
|
self.assertEqual(render_text({"text": "x" * 100}), "x" * 100 + "\n")
|
|
|
|
def test_bad_timing_is_not_silently_replaced_with_untimed_text(self):
|
|
for response in ({"text": "Speech", "words": []}, {"text": "Speech", "words": None},
|
|
{"words": [word("Speech", -1)]}, {"text": None}, {"error": "failed"}):
|
|
with self.subTest(response=response), self.assertRaises(ValueError):
|
|
render_text(response)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|