Skip to content

disable_separation and Safety Check #295

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
RobUmf wants to merge 20 commits into
base: main
Choose a base branch
from
Open

disable_separation and Safety Check #295

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
20 commits
Select commit Hold shift + click to select a range
3dd55e7
Add sweet_mixer.sh to tools folder
RobUmf Jan 20, 2026
3ad834d
Text to go with sweet_mixer
RobUmf Jan 20, 2026
2e36408
Mixer in PY and MD
RobUmf Jan 20, 2026
60c9b54
Update sweet_mixer.py
RobUmf Jan 21, 2026
3b3893d
Add --disable_separation flag to bypass Demucs
RobUmf Jan 23, 2026
3fe421a
portableMP3.py and for mobile optimization
RobUmf Jan 24, 2026
92306a7
Update portableMP3.md with flags
RobUmf Jan 24, 2026
554d543
Unnecessary comment.
RobUmf Jan 31, 2026
c2a81f9
Clean up comments in UltraSinger.py
RobUmf Jan 31, 2026
5bbd60a
Clean up bypass mode handling in UltraSinger
RobUmf Jan 31, 2026
623f1cd
Add safety checks for audio file conversions
RobUmf Jan 31, 2026
2386ce4
Merge pull request #1 from RobUmf/disable_seperation
RobUmf Feb 1, 2026
7c70f93
Add cache_override_path to Settings.py
RobUmf Feb 1, 2026
08ca61a
Merge pull request #2 from RobUmf/patch-1
RobUmf Feb 1, 2026
1291a79
Delete tools/sweet_mixer.sh
RobUmf Feb 1, 2026
1efc8d1
Delete tools/sweet_mixer.txt
RobUmf Feb 1, 2026
3fe132e
Delete tools directory
RobUmf Feb 1, 2026
c0cf7ef
cache_override_path twice
RobUmf Feb 1, 2026
0ecb206
Remove A.I Commits
RobUmf Feb 9, 2026
3f072ff
cache_override_path from empty string to None
RobUmf Feb 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/Settings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,4 +70,4 @@ class Settings:
skip_cache_denoise_vocal_audio = False
skip_cache_transcription = False
skip_cache_pitch_detection = False
calculate_score = True
calculate_score = True
49 changes: 31 additions & 18 deletions src/UltraSinger.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -399,14 +399,23 @@ def CreateUltraStarTxt(process_data: ProcessData):
if settings.create_karaoke and version.parse(settings.format_version.value) < version.parse(
FormatVersion.V1_1_0.value):
karaoke_output_path = os.path.join(settings.output_folder_path, process_data.basename + " [Karaoke].mp3")
convert_wav_to_mp3(process_data.process_data_paths.instrumental_audio_file_path, karaoke_output_path)

if process_data.process_data_paths.instrumental_audio_file_path:
convert_wav_to_mp3(process_data.process_data_paths.instrumental_audio_file_path, karaoke_output_path)
Comment on lines 399 to +404
Copy link

@coderabbitai coderabbitai bot Feb 9, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

Silent skip of karaoke conversion when instrumental is unavailable — user gets no feedback.

When --disable_separation is used, instrumental_audio_file_path is never set, so the karaoke MP3 is silently not created. The v1.1.0+ branch (line 413) prints a bypass message, but this older-format branch does not. Users expecting a karaoke file will be confused.

Proposed fix: add a similar bypass message 
     if process_data.process_data_paths.instrumental_audio_file_path:
         convert_wav_to_mp3(process_data.process_data_paths.instrumental_audio_file_path, karaoke_output_path)
+    else:
+        print(f"{ULTRASINGER_HEAD} Skipping karaoke conversion (Bypass mode).")
🤖 Prompt for AI Agents 
In `@src/UltraSinger.py` around lines 399 - 404, The karaoke conversion silently
skips when settings.create_karaoke is true but
process_data.process_data_paths.instrumental_audio_file_path is missing; add an
else branch after the existing if to emit the same bypass message used in the
v1.1.0+ branch (i.e., log/print that karaoke creation was skipped because no
instrumental audio was produced) so users see feedback for the
karaoke_output_path decision; reference the same variables used here
(settings.create_karaoke, FormatVersion.V1_1_0, karaoke_output_path,
process_data.process_data_paths.instrumental_audio_file_path,
convert_wav_to_mp3) and keep the message consistent with the newer-format
branch.

Copy link
Owner

@rakuri255 rakuri255 Feb 15, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@RobUmf can you check this?
Maybe just use the given prompt for your ai

Copy link

@coderabbitai coderabbitai bot Feb 15, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Seems like the humans are having a chat. I'll hop back into my burrow for now. If you need me again, just tag @coderabbitai in a new comment, and I'll come hopping out!


if version.parse(settings.format_version.value) >= version.parse(FormatVersion.V1_1_0.value):
instrumental_output_path = os.path.join(settings.output_folder_path,
process_data.basename + " [Instrumental].mp3")
convert_wav_to_mp3(process_data.process_data_paths.instrumental_audio_file_path, instrumental_output_path)

if process_data.process_data_paths.instrumental_audio_file_path:
convert_wav_to_mp3(process_data.process_data_paths.instrumental_audio_file_path, instrumental_output_path)
else:
print(f"{ULTRASINGER_HEAD} Skipping instrumental conversion (Bypass mode).")

vocals_output_path = os.path.join(settings.output_folder_path, process_data.basename + " [Vocals].mp3")
convert_wav_to_mp3(process_data.process_data_paths.vocals_audio_file_path, vocals_output_path)
# Safety Check for Vocals
if process_data.process_data_paths.vocals_audio_file_path:
convert_wav_to_mp3(process_data.process_data_paths.vocals_audio_file_path, vocals_output_path)

# Create Ultrastar txt
if not settings.ignore_audio:
Expand Down Expand Up @@ -444,29 +453,30 @@ def CreateProcessAudio(process_data) -> str:
)
os_helper.create_folder(process_data.process_data_paths.cache_folder_path)

# Separate vocal from audio
audio_separation_folder_path = separate_vocal_from_audio(
process_data.process_data_paths.cache_folder_path,
process_data.process_data_paths.audio_output_file_path,
settings.use_separated_vocal,
settings.create_karaoke,
settings.pytorch_device,
settings.demucs_model,
settings.skip_cache_vocal_separation
)
process_data.process_data_paths.vocals_audio_file_path = os.path.join(audio_separation_folder_path, "vocals.wav")
process_data.process_data_paths.instrumental_audio_file_path = os.path.join(audio_separation_folder_path,
"no_vocals.wav")

if settings.use_separated_vocal:

audio_separation_folder_path = separate_vocal_from_audio(
process_data.process_data_paths.cache_folder_path,
process_data.process_data_paths.audio_output_file_path,
settings.use_separated_vocal,
settings.create_karaoke,
settings.pytorch_device,
settings.demucs_model,
settings.skip_cache_vocal_separation
)
process_data.process_data_paths.vocals_audio_file_path = os.path.join(audio_separation_folder_path, "vocals.wav")
process_data.process_data_paths.instrumental_audio_file_path = os.path.join(audio_separation_folder_path, "no_vocals.wav")

input_path = process_data.process_data_paths.vocals_audio_file_path

else:
input_path = process_data.process_data_paths.audio_output_file_path

# Denoise vocal audio
denoised_output_path = os.path.join(
process_data.process_data_paths.cache_folder_path, process_data.basename + "_denoised.wav"
)

denoise_vocal_audio(input_path, denoised_output_path, settings.skip_cache_denoise_vocal_audio)

# Convert to mono audio
Expand Down Expand Up @@ -691,6 +701,8 @@ def init_settings(argv: list[str]) -> Settings:
settings.keep_cache = True
elif opt in ("--musescore_path"):
settings.musescore_path = arg
elif opt in ("--cache_override_path"):
settings.cache_override_path = arg
#Addition of demucs model choice. Work seems to be needed to make sure syntax is same for models. Added error handling for unknown models
elif opt in ("--demucs"):
try:
Expand Down Expand Up @@ -741,6 +753,7 @@ def arg_options():
"format_version=",
"keep_cache",
"musescore_path=",
"cache_override_path=",
"keep_numbers",
"interactive",
"cookiefile=",
Expand Down