This error occurred as I was using ensemble mode with a wav file I am sorry I am not a developer and not really any use in providing more info

[latextor]

What I can say is that I was using a Mac Pro 5,1 40gb ram due xeon x5670 with sapphire rx580 nitro+

Last Error Received:

Process: Ensemble Mode

If this error persists, please contact the developers with the error details.

Raw Error Details:

ParameterError: "Audio buffer is not finite everywhere"
Traceback Error: "
File "UVR.py", line 4578, in process_start
File "separate.py", line 634, in seperate
File "separate.py", line 830, in spec_to_wav
File "lib_v5/spec_utils.py", line 352, in cmb_spectrogram_to_wave
File "librosa/util/decorators.py", line 104, in inner_f
File "librosa/core/audio.py", line 606, in resample
File "librosa/util/decorators.py", line 88, in inner_f
File "librosa/util/utils.py", line 294, in valid_audio
"

Error Time Stamp [2023-01-07 22:30:33]

Full Application Settings:

vr_model: Choose Model
aggression_setting: 10
window_size: 320
batch_size: 4
crop_size: 256
is_tta: True
is_output_image: False
is_post_process: False
is_high_end_process: True
post_process_threshold: 0.2
vr_voc_inst_secondary_model: No Model Selected
vr_other_secondary_model: No Model Selected
vr_bass_secondary_model: No Model Selected
vr_drums_secondary_model: No Model Selected
vr_is_secondary_model_activate: False
vr_voc_inst_secondary_model_scale: 0.9
vr_other_secondary_model_scale: 0.7
vr_bass_secondary_model_scale: 0.5
vr_drums_secondary_model_scale: 0.5
demucs_model: v4 | htdemucs_6s
segment: Default
overlap: 0.25
shifts: 2
chunks_demucs: Auto
margin_demucs: 44100
is_chunk_demucs: False
is_primary_stem_only_Demucs: True
is_secondary_stem_only_Demucs: False
is_split_mode: True
is_demucs_combine_stems: False
demucs_voc_inst_secondary_model: No Model Selected
demucs_other_secondary_model: No Model Selected
demucs_bass_secondary_model: No Model Selected
demucs_drums_secondary_model: No Model Selected
demucs_is_secondary_model_activate: False
demucs_voc_inst_secondary_model_scale: 0.9
demucs_other_secondary_model_scale: 0.7
demucs_bass_secondary_model_scale: 0.5
demucs_drums_secondary_model_scale: 0.5
demucs_pre_proc_model: No Model Selected
is_demucs_pre_proc_model_activate: False
is_demucs_pre_proc_model_inst_mix: False
mdx_net_model: Choose Model
chunks: Auto
margin: 44100
compensate: Auto
is_denoise: True
is_invert_spec: True
mdx_voc_inst_secondary_model: No Model Selected
mdx_other_secondary_model: No Model Selected
mdx_bass_secondary_model: No Model Selected
mdx_drums_secondary_model: No Model Selected
mdx_is_secondary_model_activate: False
mdx_voc_inst_secondary_model_scale: 0.9
mdx_other_secondary_model_scale: 0.7
mdx_bass_secondary_model_scale: 0.5
mdx_drums_secondary_model_scale: 0.5
is_save_all_outputs_ensemble: True
is_append_ensemble_name: True
chosen_audio_tool: Manual Ensemble
choose_algorithm: Min Spec
time_stretch_rate: 2.0
pitch_rate: 2.0
is_gpu_conversion: True
is_primary_stem_only: False
is_secondary_stem_only: False
is_testing_audio: True
is_add_model_name: True
is_accept_any_input: True
is_task_complete: False
is_normalization: False
is_create_model_folder: True
mp3_bit_set: 320k
save_format: WAV
wav_type_set: 32-bit Float
help_hints_var: True
model_sample_mode: False
model_sample_mode_duration: 30
demucs_stems: Piano

[Anjok07]

What was the duration of the wav file? There is a known (but rare) bug with one of the Librosa libraries in the arm64 version of the application and how it handles wavs that are short or really long.

[latextor]

Sorry Been Awhile since I checked in. by the way I love what you are doing here its awesome.So this happens what ever file I put through on all the updates since the version from around 30th Dec last Year. I always keep the older version and rename just incase so that version still works for me. Also I am running on a Mac Pro 2010 with twin Xeons and a RX580 Nitro+ . And also a Mac Pro 2013 with twin AMD fire Pro D500 and a 2.7 GHz 12-Core Intel Xeon E5. And also a Old iMac. All running Monterey 12.6. I have the manual install and the Mac OS X Dmg installs running.
On the Mac Pro twin Xeon Machine UVR only uses one processor now it did previously use both. For some reason it stopped. Also when using the VR models UVR uses the Metal Api on the RX 580 and D500's on both Mac Pros but using any other Model it uses the CPU. I assume that the is a variable that sets CPU, GPU, Multi Processing in the VR model code. I have followed the code in the Manual install version and can see how it is implemented but as my python knowledge is poor and I don't really know how Pytorch works I in the dark here.

I am spending hours working with your Product by the way. Fine tuning work flows and lots of results analysis. If you have any questions I would be happy to give some context etc. Particularly re the attributes of the source files re dynamics, compression, loudness etc. Also how he various models drop the odd sample here and there. How the different models affect musical key of the output. Also how if the source file is a stereo file de interleaved and then use the mono files as source the resulting files are stereo with both channels having different levels and sometime content.....

Again Love what you are doing you are miles ahead of the other options out there Ripx, Izotope Music rebalance in RX advance, Ai Splitter online, and many others I have tried.

Many Many Thanks

Mark