mirror of
https://github.com/nomadkaraoke/karaoke-gen.git
synced 2026-11-20 13:07:57 +09:00
fix(tenant): transcribe the mixed audio, not the supplied instrumental (#825)
@coderabbitai ignore ## Problem (found by the first real tenant E2E) After #824 made tenant jobs attribute correctly, the first real Vocal Star job **failed at transcription**: `Lyrics transcription failed: 400 ... audioshake.ai/tasks`. Firestore showed `input_media_gcs_path` pointing at `existing_instrumental.mp3` — transcription was running on the **instrumental**, not the vocals. **Root cause:** in the `existing_instrumental` flow (every tenant submission), the mixed audio and the instrumental are uploaded into the **same** `uploads/{job_id}/audio/` directory: - mixed → `audio/<filename>` - instrumental → `audio/existing_instrumental.*` On `uploads-complete`, resolving the `'audio'` slot listed the whole `audio/` dir and took `files[0]` — which sorts to `existing_instrumental.mp3` (`e` < most letters). So the instrumental became the transcription input. This was a **latent bug never hit in prod** because no existing-instrumental job had ever run end-to-end (0 tenant jobs ever, per #824). ## Fix Extract `_select_mixed_audio_files()` to exclude the existing-instrumental file when selecting the `'audio'` (mixed, with-vocals) input. Regression tests added (incl. real filenames). ## Testing - New regression tests + `test_file_upload.py`/`test_upload_api.py` green (156). - Re-running the real Vocal Star E2E to completion after this deploys. Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
fea6ebec1a
commit
829ff02bdb
3 files changed
+54
-2
No files matched your search
@@ -57,6 +57,19 @@ def _is_youtube_url(url: str) -> bool:
|
||||
router = APIRouter(tags=["jobs"])
|
||||
|
||||
|
||||
def _select_mixed_audio_files(files):
|
||||
"""Filter a listing of ``uploads/{job_id}/audio/`` down to the mixed (with-vocals) audio.
|
||||
|
||||
When a job supplies its own instrumental (existing_instrumental flow, e.g. tenant
|
||||
submissions), that file is uploaded into the SAME ``audio/`` directory as the mixed
|
||||
audio (``existing_instrumental.*``). The ``audio/`` prefix therefore matches both, and
|
||||
because ``existing_instrumental`` sorts before most filenames, ``files[0]`` would pick
|
||||
the instrumental — so transcription would run on the backing track instead of the
|
||||
vocals. Excluding it here ensures the mixed audio is selected as the transcription input.
|
||||
"""
|
||||
return [f for f in files if not Path(f).name.startswith('existing_instrumental')]
|
||||
|
||||
|
||||
def _apply_tenant_overrides(
|
||||
dist: EffectiveDistributionSettings,
|
||||
tenant_config,
|
||||
@@ -1388,12 +1401,14 @@ async def mark_uploads_complete(
|
||||
|
||||
# List files with this prefix to find the actual uploaded file
|
||||
files = storage_service.list_files(prefix)
|
||||
if file_type == 'audio':
|
||||
files = _select_mixed_audio_files(files)
|
||||
if not files:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"File for '{file_type}' was not uploaded to GCS. Expected prefix: {prefix}"
|
||||
)
|
||||
|
||||
|
||||
# Use the first (and should be only) file found
|
||||
gcs_path = files[0]
|
||||
|
||||
|
||||
@@ -56,6 +56,43 @@ def _make_job_mock(**kwargs):
|
||||
return job
|
||||
|
||||
|
||||
class TestSelectMixedAudioFiles:
|
||||
"""Regression tests for _select_mixed_audio_files() in file_upload.py.
|
||||
|
||||
The existing-instrumental file shares the uploads/{job}/audio/ directory with the
|
||||
mixed audio, so the 'audio/' prefix matches both. Before the fix, files[0] resolved to
|
||||
'existing_instrumental.mp3' (it sorts first) and transcription ran on the instrumental.
|
||||
"""
|
||||
|
||||
def _fn(self):
|
||||
from backend.api.routes.file_upload import _select_mixed_audio_files
|
||||
return _select_mixed_audio_files
|
||||
|
||||
def test_excludes_existing_instrumental(self):
|
||||
fn = self._fn()
|
||||
# Listing is sorted alphabetically by GCS, so the instrumental comes first.
|
||||
files = [
|
||||
"uploads/job123/audio/existing_instrumental.mp3",
|
||||
"uploads/job123/audio/mixed.mp3",
|
||||
]
|
||||
result = fn(files)
|
||||
assert result == ["uploads/job123/audio/mixed.mp3"]
|
||||
assert result[0] == "uploads/job123/audio/mixed.mp3"
|
||||
|
||||
def test_plain_audio_only_unchanged(self):
|
||||
fn = self._fn()
|
||||
files = ["uploads/job123/audio/My Song.flac"]
|
||||
assert fn(files) == files
|
||||
|
||||
def test_real_filenames_with_instrumental(self):
|
||||
fn = self._fn()
|
||||
files = [
|
||||
"uploads/job123/audio/existing_instrumental.mp3",
|
||||
"uploads/job123/audio/Eddy Grant - I Don't Wanna Dance Guide.mp3",
|
||||
]
|
||||
assert fn(files) == ["uploads/job123/audio/Eddy Grant - I Don't Wanna Dance Guide.mp3"]
|
||||
|
||||
|
||||
class TestApplyTenantOverrides:
|
||||
"""Tests for _apply_tenant_overrides() in file_upload.py."""
|
||||
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
[tool.poetry]
|
||||
name = "karaoke-gen"
|
||||
version = "0.183.0"
|
||||
version = "0.183.1"
|
||||
description = "Generate karaoke videos with synchronized lyrics. Handles the entire process from downloading audio and lyrics to creating the final video with title screens."
|
||||
authors = ["Andrew Beveridge <andrew@beveridge.uk>"]
|
||||
license = "MIT"
|
||||
|
||||
Reference in new issue
Block a user