Open
Conversation
Adding the bash mixer script to handle 1.4x volume boosting and prevent overmodulation.
Instructions with options
"Updated default volume from 1.4x to 1.2x. During testing, 1.4x caused slight overmodulation in tracks transitioning between high-resonance strings and percussive piano. 1.2x provides the necessary 'Sweet Spot' boost while maintaining clean head-room."
Being compliant with according to CodeFactor
--disable_separation flag, allowing users to provide pre-separated vocal stems (e.g., from a high-quality manual extraction or specialized external tools). When active, UltraSinger skips the Demucs separation phase entirely, significantly reducing processing time and preventing redundant extraction.
A high-performance Python utility designed to compress and migrate large music archives for mobile devices, flip phones, and portable storage.
Notice I didn't add the flag options
Unnecessary comment. OUT
Should I delete or reduce other commits.
Removed bypass mode print statements and variable assignments for vocals and instrumental paths.
How about?
# Denoise vocal audio
if settings.use_separated_vocal:
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)
# Update input_path to the denoised version for the next step (Pitch Tracking)
input_path = denoised_output_path
else:
# In Bypass Mode, we skip denoising the full song to prevent distortion/overmodulation
print(f"{ULTRASINGER_HEAD} {gold_highlighted('Bypass Mode:')} {cyan_highlighted('Skipping vocal denoising.')}")
Added safety checks for instrumental and vocals audio file paths before conversion. With --disable_separation on going to mp3 Error purposely created.
Add safety checks for audio file conversions
Was having problem preventing hugging face downloading the bin files
Add cache_override_path to Settings.py
been converted to py
Changed to MD
Moving to different branch
Deleted bottom one
rakuri255
requested changes
Feb 8, 2026
📝 WalkthroughWalkthroughAdds a new CLI option Changes
Sequence Diagram(s)sequenceDiagram
participant CLI
participant UltraSinger
participant FS as FileSystem
participant Converter
CLI->>UltraSinger: start (args, --cache_override_path)
UltraSinger->>UltraSinger: init_settings (set cache_override_path)
UltraSinger->>FS: check input audio path exists
alt use_separated_vocal
UltraSinger->>Converter: separate vocals/instrumental
Converter->>FS: write separated files
UltraSinger->>FS: check separated vocal/instrumental exist
end
UltraSinger->>Converter: convert vocal (if exists)
UltraSinger->>Converter: convert instrumental (if exists)
Converter->>FS: write converted outputs
UltraSinger->>CLI: finish (results / warnings)
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
🚥 Pre-merge checks | ✅ 1 | ❌ 2❌ Failed checks (1 warning, 1 inconclusive)
✅ Passed checks (1 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
🧪 Generate unit tests (beta)
No actionable comments were generated in the recent review. 🎉 Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In `@src/Settings.py`:
- Line 62: Change the default for cache_override_path from an empty string to
None in Settings.py so the existing check in UltraSinger.py (if
settings.cache_override_path is None) works as intended; update the declaration
of cache_override_path to use None (referencing the variable name
cache_override_path in Settings.py) so UltraSinger.py will fall back to
os.path.join(settings.output_folder_path, "cache") when no override is provided.
In `@src/UltraSinger.py`:
- Around line 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.
🧹 Nitpick comments (1)
src/UltraSinger.py (1)
416-418: Silent skip of vocals conversion — inconsistent with instrumental handling.The instrumental branch (line 412–413) logs a message when skipping, but the vocals branch silently skips. Add a similar log for consistency and debuggability.
Proposed fix
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) + else: + print(f"{ULTRASINGER_HEAD} Skipping vocals conversion (Bypass mode).")
Comment on lines
399
to
+404
| 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) |
There was a problem hiding this comment.
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.
Owner
There was a problem hiding this comment.
@RobUmf can you check this?
Maybe just use the given prompt for your ai
There was a problem hiding this comment.
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!
Original idea is better.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Added safety checks for instrumental and vocals audio file paths with --disable_separation before conversion to mp3
Summary by CodeRabbit
New Features
Bug Fixes