ddidderr
24b1030776
Request speaker diarization through OpenRouter's Azure provider options for all transcription uploads. Add --no-diarization to explicitly disable it for both plain text and SRT output; returned speaker labels let existing SRT cue generation split at speaker changes. Default to 10-minute chunks when diarization is enabled because Microsoft reports failures around 15 minutes and longer. Preserve the 30-minute default with the opt-out and honor explicit --chunk-minutes values in both modes. Document the options, duration limits, and output behavior. Test Plan: - python3 -B -m unittest -v: all 32 tests passed, including request options, default upload limits, opt-out combinations, and SRT speaker boundaries. - bash -n transcribe: passed. - ./transcribe --help: verified the new option and chunk defaults. - git diff --cached --check: passed. - Provider responses were mocked; no live API request was made.
80 lines
3.0 KiB
Python
80 lines
3.0 KiB
Python
#!/usr/bin/env python3
|
|
"""Test-only replacements for op/curl; no network or real credentials."""
|
|
|
|
import base64
|
|
import json
|
|
import os
|
|
from pathlib import Path
|
|
import subprocess
|
|
import sys
|
|
|
|
|
|
if Path(sys.argv[0]).name == "op":
|
|
print("test-api-key")
|
|
sys.exit(0)
|
|
|
|
args = sys.argv[1:]
|
|
request = json.loads(Path(args[args.index("--data-binary") + 1][1:]).read_text())
|
|
output = Path(args[args.index("-o") + 1])
|
|
index = int(output.stem.split("-")[1])
|
|
manifest = json.loads((output.parent / "chunks.json").read_text())
|
|
chunk = manifest[index]
|
|
assert request["model"] == "microsoft/mai-transcribe-2"
|
|
assert request["input_audio"]["format"] == "mp3"
|
|
if len(manifest) > 1:
|
|
assert request["response_format"] == "verbose_json"
|
|
assert request["timestamp_granularities"] == ["segment", "word"]
|
|
|
|
audio = output.parent / "uploaded.mp3"
|
|
audio.write_bytes(base64.b64decode(request["input_audio"]["data"], validate=True))
|
|
info = json.loads(subprocess.check_output([
|
|
"ffprobe", "-v", "error", "-show_entries",
|
|
"format=duration:stream=codec_name,sample_rate,channels", "-of", "json", str(audio),
|
|
], text=True))
|
|
assert info["streams"][0] == {"codec_name": "mp3", "sample_rate": "16000", "channels": 1}
|
|
assert abs(float(info["format"]["duration"]) - (chunk["end"] - chunk["start"])) < 0.1
|
|
with open(os.environ["TRANSCRIBE_TEST_LOG"], "a") as log:
|
|
log.write(json.dumps({
|
|
"index": index, "chunk": chunk, "staging": str(output.parent),
|
|
"upload_duration": float(info["format"]["duration"]),
|
|
"provider": request.get("provider"),
|
|
"response_format": request.get("response_format"),
|
|
"timestamp_granularities": request.get("timestamp_granularities"),
|
|
}) + "\n")
|
|
|
|
mode = os.environ.get("TRANSCRIBE_TEST_MODE", "ok")
|
|
if index == 1:
|
|
if mode == "http-error":
|
|
output.write_text('{"error":{"message":"simulated timeout"}}')
|
|
sys.exit(22)
|
|
if mode == "bad-json":
|
|
output.write_text("not json")
|
|
sys.exit(0)
|
|
if mode == "api-error":
|
|
output.write_text('{"error":{"message":"simulated API error"},"text":""}')
|
|
sys.exit(0)
|
|
if mode == "missing-words":
|
|
output.write_text('{"text":"speech without timestamps"}')
|
|
sys.exit(0)
|
|
|
|
if "response_format" not in request:
|
|
response = {"text": "Provider's original formatting.\nNext line."}
|
|
else:
|
|
words = [
|
|
{"word": text, "start": start - chunk["start"], "end": end - chunk["start"]}
|
|
for text, start, end in [
|
|
("Hello.", 1, 1.4), ("boundary", 56.7, 57.1),
|
|
("continues.", 57.4, 57.8), ("Last.", 65, 65.4),
|
|
] if start >= chunk["start"] and end <= chunk["end"]
|
|
]
|
|
if mode == "speakers":
|
|
words = [
|
|
{"word": "Hello", "start": 1, "end": 1.4},
|
|
{"word": "there", "start": 1.5, "end": 1.9},
|
|
]
|
|
if request["provider"]["options"]["azure"]["diarization"]["enabled"]:
|
|
for speaker, word in enumerate(words):
|
|
word["speaker"] = speaker
|
|
response = {"text": " ".join(w["word"] for w in words), "words": words}
|
|
output.write_text(json.dumps(response))
|