search

rakuri255 / UltraSinger

AI based tool to convert vocals lyrics and pitch from music to autogenerate Ultrastar Deluxe, Midi and notes. It automatic tapping, adding text, pitch vocals and creates karaoke files.
MIT License
230 stars 19 forks source link

create ulstrastar txt fails #111

Open dhessmann opened 6 months ago

dhessmann commented 6 months ago

Hi,

I stumbled across this promising project this morning and wanted to try it out straight away. The installation went smoothly. However, when creating a song I get an index out of range.

` py UltraSinger.py -i https://youtu.be/-8UxX5STKL4?si=CYOWfP37e7pGkA4D -o E:\UltraSinger\output The torchaudio backend is switched to 'soundfile'. Note that 'sox_io' is not supported on Windows. The torchaudio backend is switched to 'soundfile'. Note that 'sox_io' is not supported on Windows.

[UltraSinger] [UltraSinger] UltraSinger Version: 0.0.5 [UltraSinger] [UltraSinger] Checking GPU support for tensorflow and pytorch. [UltraSinger] tensorflow - using cuda gpu. [UltraSinger] pytorch - using cuda gpu. [UltraSinger] full automatic mode .... [UltraSinger] Creating midi notes from pitched data [UltraSinger] Creating Ultrastar notes from midi data [UltraSinger] BPM is 96.98 [UltraSinger] Creating E:\UltraSinger\output\Alphabeat - Fascination (Official Music Video) (2)\Alphabeat - Fascination (Official Music Video).txt from transcription. Traceback (most recent call last): File "E:\UltraSinger\src\UltraSinger.py", line 925, in main(sys.argv[1:]) File "E:\UltraSinger\src\UltraSinger.py", line 832, in main run() File "E:\UltraSinger\src\UltraSinger.py", line 403, in run real_bpm, ultrastar_file_output = create_ultrastar_txt_from_automation( File "E:\UltraSinger\src\UltraSinger.py", line 596, in create_ultrastar_txt_from_automation ultrastar_writer.create_ultrastar_txt_from_automation( File "E:\UltraSinger\src\modules\Ultrastar\ultrastar_writer.py", line 56, in create_ultrastar_txt_from_automation gap = transcribed_data[0].start IndexError: list index out of range `

Maybe someone can help me and tell me what I'm doing wrong.

Best regards Dominik

rakuri255 commented 6 months ago

Hi @dhessmann. I just testet the song and it works for me.

It says that the issue is here:

gap = transcribed_data[0].start
IndexError: list index out of range

There shouldnt be an error here. UltraSinger says that the data is missing although he had already used it before. Please post the full Log. And try a new installation. Download the sources again and rebuild venv.

dhessmann commented 6 months ago

Hi @rakuri255,

after your comment i deleted everything, made a fresh installation an e'voila. Everything works as expected. Don't know what I did wrong at the frist try. Thank you for help.

dwedman93 commented 6 months ago

I have the same issue with the large model. The tiny model works fine.

rakuri255 commented 6 months ago

@dwedman93 can you post your log?

dwedman93 commented 6 months ago

Sure: Reinstallation did not work for me either. I suspect, not enough vram. (6gb, gtx 1660 super)

D:\Other Games\Ultrastar\Python\UltraSinger> python src/UltraSinger.py -i https://www.youtube.com/watch?v=kRrP-bZvD2s --language de The torchaudio backend is switched to 'soundfile'. Note that 'sox_io' is not supported on Windows. The torchaudio backend is switched to 'soundfile'. Note that 'sox_io' is not supported on Windows.

[UltraSinger] [UltraSinger] UltraSinger Version: 0.0.7 [UltraSinger] [UltraSinger] Checking GPU support for tensorflow and pytorch. [UltraSinger] tensorflow - using cuda gpu. [UltraSinger] pytorch - using cuda gpu. [UltraSinger] full automatic mode [youtube] Extracting URL: https://www.youtube.com/watch?v=kRrP-bZvD2s [youtube] kRrP-bZvD2s: Downloading webpage

[youtube] kRrP-bZvD2s: Downloading ios player API JSON [youtube] kRrP-bZvD2s: Downloading android player API JSON [youtube] kRrP-bZvD2s: Downloading m3u8 information [UltraSinger] Searching song in musicbrainz [UltraSinger] Found Titel and Artist Deine Schuld by Die Ärzte [UltraSinger] Found release year: 2004-07-12 [UltraSinger] Found genres: rock,punk,punk rock, [UltraSinger] Creating output folder. -> D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld [UltraSinger] Downloading Audio [youtube] Extracting URL: https://www.youtube.com/watch?v=kRrP-bZvD2s [youtube] kRrP-bZvD2s: Downloading webpage [youtube] kRrP-bZvD2s: Downloading ios player API JSON [youtube] kRrP-bZvD2s: Downloading android player API JSON [youtube] kRrP-bZvD2s: Downloading m3u8 information [info] kRrP-bZvD2s: Downloading 1 format(s): 251 [download] Destination: D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld [download] 100% of 3.63MiB in 00:00:00 at 9.82MiB/s [ExtractAudio] Destination: D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld.mp3 Deleting original file D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld (pass -k to keep) [UltraSinger] Downloading Video [youtube] Extracting URL: https://www.youtube.com/watch?v=kRrP-bZvD2s [youtube] kRrP-bZvD2s: Downloading webpage [youtube] kRrP-bZvD2s: Downloading ios player API JSON [youtube] kRrP-bZvD2s: Downloading android player API JSON [youtube] kRrP-bZvD2s: Downloading m3u8 information [info] kRrP-bZvD2s: Downloading 1 format(s): 605+140 [hlsnative] Downloading m3u8 manifest [hlsnative] Total fragments: 45 [download] Destination: D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld.f605.mp4 [download] 100% of 6.13MiB in 00:00:04 at 1.43MiB/s [download] Destination: D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld.f140.m4a [download] 100% of 3.63MiB in 00:00:00 at 9.23MiB/s [Merger] Merging formats into "D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld.mp4" Deleting original file D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld.f140.m4a (pass -k to keep) Deleting original file D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld.f605.mp4 (pass -k to keep) [UltraSinger] Downloading thumbnail [youtube] Extracting URL: https://www.youtube.com/watch?v=kRrP-bZvD2s [youtube] kRrP-bZvD2s: Downloading webpage [youtube] kRrP-bZvD2s: Downloading ios player API JSON [youtube] kRrP-bZvD2s: Downloading android player API JSON [youtube] kRrP-bZvD2s: Downloading m3u8 information [UltraSinger] Creating output folder. -> D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\cache [UltraSinger] Separating vocals from audio with demucs and cuda as worker. Important: the default model was recently changed to htdemucs the latest Hybrid Transformer Demucs model. In some cases, this model can actually perform worse than previous models. To get back the old default model use -n mdx_extra_q. Selected model is a bag of 1 models. You will see that many progress bars per track. Separated tracks will be stored in D:\Other Games\Ultrastar\Python\UltraSinger\separated\htdemucs Separating track D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld.mp3 100%|██████████████████████████████████████████████████████████████████████| 239.85/239.85 [00:19<00:00, 12.62seconds/s] [UltraSinger] Converting wav to mp3 [UltraSinger] Reduce noise from vocal audio with ffmpeg. [UltraSinger] Converting audio for AI [UltraSinger] Mute audio parts with no singing [UltraSinger] Loading whisper with model large-v2 and cuda as worker Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.1.3. To apply the upgrade to your files permanently, run python -m pytorch_lightning.utilities.upgrade_checkpoint C:\Users\username\.cache\torch\whisperx-vad-segmentation.bin Model was trained with pyannote.audio 0.0.1, yours is 3.1.0. Bad things might happen unless you revert pyannote.audio to 0.x. Model was trained with torch 1.10.0+cu102, yours is 2.0.1+cu117. Bad things might happen unless you revert torch to 1.x. [UltraSinger] Transcribing D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\cache\Die Ärzte - Deine Schuld_mute.wav Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... [UltraSinger] Hyphenate using language code: de_DE 0it [00:00, ?it/s] [UltraSinger] Removing silent parts from transcription data [UltraSinger] Pitching with crepe and model full and cuda as worker 2023-12-30 16:27:35.547540: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2 To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2023-12-30 16:27:37.250106: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1532] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 2558 MB memory: -> device: 0, name: NVIDIA GeForce GTX 1660 SUPER, pci bus id: 0000:26:00.0, compute capability: 7.5 2023-12-30 16:27:47.577121: I tensorflow/stream_executor/cuda/cuda_dnn.cc:384] Loaded cuDNN version 8500 2023-12-30 16:27:47.785914: E tensorflow/core/platform/windows/subprocess.cc:287] Call to CreateProcess failed. Error code: 2, command: '"ptxas.exe" "--version"' 2023-12-30 16:27:47.786943: E tensorflow/core/platform/windows/subprocess.cc:287] Call to CreateProcess failed. Error code: 2, command: '"ptxas.exe" "--version"' 2023-12-30 16:27:47.787067: W tensorflow/stream_executor/gpu/asm_compiler.cc:80] Couldn't get ptxas version string: INTERNAL: Couldn't invoke ptxas.exe --version 2023-12-30 16:27:47.804187: E tensorflow/core/platform/windows/subprocess.cc:287] Call to CreateProcess failed. Error code: 2, command: '"ptxas.exe" "C:\Users\username\AppData\Local\Temp\/tempfile-DESKTOP" "-o" "C:\Users\username\AppData\Local\Temp\/tempfile-DESKTOP" "-arch=sm_75" "--warn-on-spills"' 2023-12-30 16:27:47.804711: W tensorflow/stream_executor/gpu/redzone_allocator.cc:314] INTERNAL: Failed to launch ptxas Relying on driver to perform ptx compilation. Modify $PATH to customize ptxas location. This message will be only logged once. 2023-12-30 16:27:48.135513: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.56GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 16:27:48.135788: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.56GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 16:27:48.158402: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.56GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 16:27:48.158596: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.56GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 734/735 [============================>.] - ETA: 0s2023-12-30 16:28:03.578672: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.51GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 16:28:03.578851: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.51GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 16:28:03.601021: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.51GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 16:28:03.601162: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.51GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 735/735 [==============================] - 17s 21ms/step [UltraSinger] Creating midi notes from pitched data [UltraSinger] Creating Ultrastar notes from midi data [UltraSinger] BPM is 108.17 [UltraSinger] Creating D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld\Die Ärzte - Deine Schuld.txt from transcription. Traceback (most recent call last): File "D:\Other Games\Ultrastar\Python\UltraSinger\src\UltraSinger.py", line 984, in main(sys.argv[1:]) File "D:\Other Games\Ultrastar\Python\UltraSinger\src\UltraSinger.py", line 883, in main run() File "D:\Other Games\Ultrastar\Python\UltraSinger\src\UltraSinger.py", line 435, in run real_bpm, ultrastar_file_output = create_ultrastar_txt_from_automation( File "D:\Other Games\Ultrastar\Python\UltraSinger\src\UltraSinger.py", line 651, in create_ultrastar_txt_from_automation ultrastar_writer.create_ultrastar_txt_from_automation( File "D:\Other Games\Ultrastar\Python\UltraSinger\src\modules\Ultrastar\ultrastar_writer.py", line 75, in create_ultrastar_txt_from_automation gap = transcribed_data[0].start IndexError: list index out of range

rakuri255 commented 6 months ago

ok it seems it's a race condition. Seems that the pitcher break the transcribed_data when low on VRAM.

@dwedman93 you are right. You have to low VRAM. You could fix that by forcing crepe to CPU --force_crepe_cpu True. Can you try it please if this help you?

dwedman93 commented 6 months ago

Everything worked fine with --force_cpu True

But I can also do the other one for debugging purposes.

The Song turned out great in Ultrastar. Good Job!

dwedman93 commented 6 months ago

Does not work unfortunetaly.

PS D:\Other Games\Ultrastar\Python\UltraSinger> python src/UltraSinger.py -i https://www.youtube.com/watch?v=kRrP-bZvD2s --language de --force_crepe_cpu True The torchaudio backend is switched to 'soundfile'. Note that 'sox_io' is not supported on Windows. The torchaudio backend is switched to 'soundfile'. Note that 'sox_io' is not supported on Windows.

[UltraSinger] [UltraSinger] UltraSinger Version: 0.0.7 [UltraSinger] [UltraSinger] Checking GPU support for tensorflow and pytorch. [UltraSinger] tensorflow - using cuda gpu. [UltraSinger] pytorch - using cuda gpu. [UltraSinger] full automatic mode [youtube] Extracting URL: https://www.youtube.com/watch?v=kRrP-bZvD2s [youtube] kRrP-bZvD2s: Downloading webpage [youtube] kRrP-bZvD2s: Downloading ios player API JSON [youtube] kRrP-bZvD2s: Downloading android player API JSON [youtube] kRrP-bZvD2s: Downloading m3u8 information [UltraSinger] Searching song in musicbrainz [UltraSinger] Found Titel and Artist Deine Schuld by Die Ärzte [UltraSinger] Found release year: 2004-07-12 [UltraSinger] Found genres: rock,punk,punk rock, [UltraSinger] Creating output folder. -> D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2) [UltraSinger] Downloading Audio [youtube] Extracting URL: https://www.youtube.com/watch?v=kRrP-bZvD2s [youtube] kRrP-bZvD2s: Downloading webpage [youtube] kRrP-bZvD2s: Downloading ios player API JSON [youtube] kRrP-bZvD2s: Downloading android player API JSON [youtube] kRrP-bZvD2s: Downloading m3u8 information [info] kRrP-bZvD2s: Downloading 1 format(s): 251 [download] Destination: D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld [download] 100% of 3.63MiB in 00:00:00 at 9.52MiB/s [ExtractAudio] Destination: D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld.mp3 Deleting original file D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld (pass -k to keep) [UltraSinger] Downloading Video [youtube] Extracting URL: https://www.youtube.com/watch?v=kRrP-bZvD2s [youtube] kRrP-bZvD2s: Downloading webpage [youtube] kRrP-bZvD2s: Downloading ios player API JSON [youtube] kRrP-bZvD2s: Downloading android player API JSON [youtube] kRrP-bZvD2s: Downloading m3u8 information [info] kRrP-bZvD2s: Downloading 1 format(s): 605+140 [hlsnative] Downloading m3u8 manifest [hlsnative] Total fragments: 45 [download] Destination: D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld.f605.mp4 [download] 100% of 6.13MiB in 00:00:03 at 1.63MiB/s [download] Destination: D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld.f140.m4a [download] 100% of 3.63MiB in 00:00:00 at 9.79MiB/s [Merger] Merging formats into "D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld.mp4" Deleting original file D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld.f140.m4a (pass -k to keep) Deleting original file D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld.f605.mp4 (pass -k to keep) [UltraSinger] Downloading thumbnail [youtube] Extracting URL: https://www.youtube.com/watch?v=kRrP-bZvD2s [youtube] kRrP-bZvD2s: Downloading webpage [youtube] kRrP-bZvD2s: Downloading ios player API JSON [youtube] kRrP-bZvD2s: Downloading android player API JSON [youtube] kRrP-bZvD2s: Downloading m3u8 information [UltraSinger] Creating output folder. -> D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\cache [UltraSinger] Separating vocals from audio with demucs and cuda as worker. Important: the default model was recently changed to htdemucs the latest Hybrid Transformer Demucs model. In some cases, this model can actually perform worse than previous models. To get back the old default model use -n mdx_extra_q. Selected model is a bag of 1 models. You will see that many progress bars per track. Separated tracks will be stored in D:\Other Games\Ultrastar\Python\UltraSinger\separated\htdemucs Separating track D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld.mp3 100%|██████████████████████████████████████████████████████████████████████| 239.85/239.85 [00:12<00:00, 19.67seconds/s] [UltraSinger] Converting wav to mp3 [UltraSinger] Reduce noise from vocal audio with ffmpeg. [UltraSinger] Converting audio for AI [UltraSinger] Mute audio parts with no singing [UltraSinger] Loading whisper with model large-v2 and cuda as worker Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.1.3. To apply the upgrade to your files permanently, run python -m pytorch_lightning.utilities.upgrade_checkpoint C:\Users\username\.cache\torch\whisperx-vad-segmentation.bin Model was trained with pyannote.audio 0.0.1, yours is 3.1.0. Bad things might happen unless you revert pyannote.audio to 0.x. Model was trained with torch 1.10.0+cu102, yours is 2.0.1+cu117. Bad things might happen unless you revert torch to 1.x. [UltraSinger] Transcribing D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\cache\Die Ärzte - Deine Schuld_mute.wav Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... Failed to align segment ("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"): no characters in this segment found in model dictionary, resorting to original... [UltraSinger] Hyphenate using language code: de_DE 0it [00:00, ?it/s] [UltraSinger] Removing silent parts from transcription data [UltraSinger] Pitching with crepe and model full and cpu as worker 2023-12-30 17:36:27.238137: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2 To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2023-12-30 17:36:27.826226: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1532] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 2558 MB memory: -> device: 0, name: NVIDIA GeForce GTX 1660 SUPER, pci bus id: 0000:26:00.0, compute capability: 7.5 2023-12-30 17:36:36.642596: I tensorflow/stream_executor/cuda/cuda_dnn.cc:384] Loaded cuDNN version 8500 2023-12-30 17:36:36.762784: E tensorflow/core/platform/windows/subprocess.cc:287] Call to CreateProcess failed. Error code: 2, command: '"ptxas.exe" "--version"' 2023-12-30 17:36:36.763890: E tensorflow/core/platform/windows/subprocess.cc:287] Call to CreateProcess failed. Error code: 2, command: '"ptxas.exe" "--version"' 2023-12-30 17:36:36.764022: W tensorflow/stream_executor/gpu/asm_compiler.cc:80] Couldn't get ptxas version string: INTERNAL: Couldn't invoke ptxas.exe --version 2023-12-30 17:36:36.767460: E tensorflow/core/platform/windows/subprocess.cc:287] Call to CreateProcess failed. Error code: 2, command: '"ptxas.exe" "C:\Users\username\AppData\Local\Temp\/tempfile-DESKTOP--2998-2900-60dbcc09c95e1" "-o" "C:\Users\username\AppData\Local\Temp\/tempfile-DESKTOP--2998-2900-60dbcc09ca0a7" "-arch=sm_75" "--warn-on-spills"' 2023-12-30 17:36:36.767800: W tensorflow/stream_executor/gpu/redzone_allocator.cc:314] INTERNAL: Failed to launch ptxas Relying on driver to perform ptx compilation. Modify $PATH to customize ptxas location. This message will be only logged once. 2023-12-30 17:36:37.089981: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.56GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 17:36:37.090143: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.56GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 17:36:37.111752: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.56GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 17:36:37.111901: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.56GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 734/735 [============================>.] - ETA: 0s2023-12-30 17:36:52.574384: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.51GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 17:36:52.574582: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.51GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 17:36:52.596424: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.51GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 2023-12-30 17:36:52.596562: W tensorflow/core/common_runtime/bfc_allocator.cc:290] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.51GiB with freed_by_count=0. The caller indicates that this is not a failure, but this may mean that there could be performance gains if more memory were available. 735/735 [==============================] - 16s 21ms/step [UltraSinger] Creating midi notes from pitched data [UltraSinger] Creating Ultrastar notes from midi data [UltraSinger] BPM is 108.17 [UltraSinger] Creating D:\Other Games\Ultrastar\Python\UltraSinger\output\Die Ärzte - Deine Schuld (2)\Die Ärzte - Deine Schuld.txt from transcription. Traceback (most recent call last): File "D:\Other Games\Ultrastar\Python\UltraSinger\src\UltraSinger.py", line 984, in main(sys.argv[1:]) File "D:\Other Games\Ultrastar\Python\UltraSinger\src\UltraSinger.py", line 883, in main run() File "D:\Other Games\Ultrastar\Python\UltraSinger\src\UltraSinger.py", line 435, in run real_bpm, ultrastar_file_output = create_ultrastar_txt_from_automation( File "D:\Other Games\Ultrastar\Python\UltraSinger\src\UltraSinger.py", line 651, in create_ultrastar_txt_from_automation ultrastar_writer.create_ultrastar_txt_from_automation( File "D:\Other Games\Ultrastar\Python\UltraSinger\src\modules\Ultrastar\ultrastar_writer.py", line 75, in create_ultrastar_txt_from_automation gap = transcribed_data[0].start IndexError: list index out of range

rakuri255 commented 6 months ago

Interessting.