Repository navigation
Not generating txt file. #266
Description
Hey. At first you have an awsome thing going on here. Keep up the good work.
I got the Problem that Ultrasinger isnt generating a txt File for me.
I have a JPEG, MP3, MP4 and cashe with some wav files.
I Tried with Youtube links and with MP3´s. Same Problem.
Here´s the complete Log:
(.venv) C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src>py Ultrasinger.py -i https://youtu.be/KZQcD8ZDySE?si=HTLX38fGksDiOhGQ
C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main.venv\lib\site-packages\librosa\util\files.py:10: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
from pkg_resources import resource_filename
[UltraSinger] ********************************
[UltraSinger] UltraSinger Version: 0.0.13-dev8
[UltraSinger] ********************************
[UltraSinger] Checking GPU support.
[UltraSinger] Found GPU: NVIDIA GeForce RTX 4080 SUPER VRAM: 15.99 GB.
[UltraSinger] pytorch - using cuda gpu.
[UltraSinger] tensorflow - using cuda gpu.
[UltraSinger] ----------------------
[UltraSinger] FFmpeg - using C:\Users\Anwender\Desktop\Ultrastar\ffmpeg-2025-10-09-git-469aad3897-essentials_build\bin\ffmpeg.EXE
[UltraSinger] FFprobe - using C:\Users\Anwender\Desktop\Ultrastar\ffmpeg-2025-10-09-git-469aad3897-essentials_build\bin\ffprobe.EXE
[UltraSinger] ----------------------
[UltraSinger] Full Automatic Mode
[youtube] Extracting URL: https://youtu.be/KZQcD8ZDySE?si=HTLX38fGksDiOhGQ
[youtube] KZQcD8ZDySE: Downloading webpage
[youtube] KZQcD8ZDySE: Downloading tv client config
[youtube] KZQcD8ZDySE: Downloading tv player API JSON
[youtube] KZQcD8ZDySE: Downloading ios player API JSON
[youtube] KZQcD8ZDySE: Downloading player 3dfa10c2-main
WARNING: [youtube] KZQcD8ZDySE: Signature extraction failed: Some formats may be missing
WARNING: [youtube] KZQcD8ZDySE: Some web client https formats have been skipped as they are missing a url. YouTube is forcing SABR streaming for this client. See yt-dlp/yt-dlp#12482 for more details
[youtube] KZQcD8ZDySE: Downloading m3u8 information
[UltraSinger] Found data on Musicbrainz: Artist=From Fall to Spring Title=TAKE THE PAIN AWAY
[UltraSinger] Found year: 2025
[UltraSinger] Found cover image
[UltraSinger] Creating output folder. -> C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\output\From Fall to Spring - TAKE THE PAIN AWAY
[UltraSinger] Downloading Audio
[youtube] Extracting URL: https://youtu.be/KZQcD8ZDySE?si=HTLX38fGksDiOhGQ
[youtube] KZQcD8ZDySE: Downloading webpage
[youtube] KZQcD8ZDySE: Downloading tv client config
[youtube] KZQcD8ZDySE: Downloading tv player API JSON
[youtube] KZQcD8ZDySE: Downloading ios player API JSON
[youtube] KZQcD8ZDySE: Downloading player 3dfa10c2-main
WARNING: [youtube] KZQcD8ZDySE: Signature extraction failed: Some formats may be missing
WARNING: [youtube] KZQcD8ZDySE: Some web client https formats have been skipped as they are missing a url. YouTube is forcing SABR streaming for this client. See yt-dlp/yt-dlp#12482 for more details
[youtube] KZQcD8ZDySE: Downloading m3u8 information
[info] KZQcD8ZDySE: Downloading 1 format(s): 234
[hlsnative] Downloading m3u8 manifest
[hlsnative] Total fragments: 32
[download] Destination: C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\output\From Fall to Spring - TAKE THE PAIN AWAY\From Fall to Spring - TAKE THE PAIN AWAY
[download] 100% of 2.70MiB in 00:00:00 at 4.22MiB/s
[ExtractAudio] Destination: C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\output\From Fall to Spring - TAKE THE PAIN AWAY\From Fall to Spring - TAKE THE PAIN AWAY.mp3
Deleting original file C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\output\From Fall to Spring - TAKE THE PAIN AWAY\From Fall to Spring - TAKE THE PAIN AWAY (pass -k to keep)
[UltraSinger] Downloading Video
[youtube] Extracting URL: https://youtu.be/KZQcD8ZDySE?si=HTLX38fGksDiOhGQ
[youtube] KZQcD8ZDySE: Downloading webpage
[youtube] KZQcD8ZDySE: Downloading tv client config
[youtube] KZQcD8ZDySE: Downloading player 3dfa10c2-player_es5_vflset_en_US_base
[youtube] KZQcD8ZDySE: Downloading tv player API JSON
[youtube] KZQcD8ZDySE: Downloading ios player API JSON
WARNING: [youtube] KZQcD8ZDySE: Signature extraction failed: Some formats may be missing
WARNING: [youtube] KZQcD8ZDySE: Some web client https formats have been skipped as they are missing a url. YouTube is forcing SABR streaming for this client. See yt-dlp/yt-dlp#12482 for more details
[youtube] KZQcD8ZDySE: Downloading m3u8 information
[info] KZQcD8ZDySE: Downloading 1 format(s): 625
[hlsnative] Downloading m3u8 manifest
[hlsnative] Total fragments: 32
[download] Destination: C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\output\From Fall to Spring - TAKE THE PAIN AWAY\From Fall to Spring - TAKE THE PAIN AWAY.mp4
[download] 100% of 102.41MiB in 00:00:05 at 17.19MiB/s
[UltraSinger] BPM is 126.05
[UltraSinger] Creating output folder. -> C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\output\From Fall to Spring - TAKE THE PAIN AWAY\cache
[UltraSinger] Separating vocals from audio with demucs with model htdemucs and cuda as worker.
Selected model is a bag of 1 models. You will see that many progress bars per track.
Separated tracks will be stored in C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\output\From Fall to Spring - TAKE THE PAIN AWAY\cache\separated\htdemucs
Separating track C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\output\From Fall to Spring - TAKE THE PAIN AWAY\From Fall to Spring - TAKE THE PAIN AWAY.mp3
0%| | 0.0/175.5 [00:00<?, ?seconds/s]C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main.venv\lib\site-packages\torch\nn\modules\activation.py:1221: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.)
return torch._native_multi_head_attention(
100%|████████████████████████████████████████████████████████████████████████| 175.5/175.5 [00:02<00:00, 86.20seconds/s]
[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
No language specified, language will be first be detected for each audio file (increases inference time).
Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.5.1.post0. To apply the upgrade to your files permanently, run python -m pytorch_lightning.utilities.upgrade_checkpoint C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\.venv\lib\site-packages\whisperx\assets\pytorch_model.bin
Model was trained with pyannote.audio 0.0.1, yours is 3.3.2. Bad things might happen unless you revert pyannote.audio to 0.x.
Model was trained with torch 1.10.0+cu102, yours is 2.3.1+cu118. Bad things might happen unless you revert torch to 1.x.
[UltraSinger] Transcribing C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\output\From Fall to Spring - TAKE THE PAIN AWAY\cache\From Fall to Spring - TAKE THE PAIN AWAY_mute.wav
C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main.venv\lib\site-packages\pyannote\audio\utils\reproducibility.py:74: ReproducibilityWarning: TensorFloat-32 (TF32) has been disabled as it might lead to reproducibility issues and lower accuracy.
It can be re-enabled by calling
import torch
torch.backends.cuda.matmul.allow_tf32 = True
torch.backends.cudnn.allow_tf32 = True
See pyannote/pyannote-audio#1370 for more details.
warnings.warn(
Traceback (most recent call last):
File "C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\Ultrasinger.py", line 752, in
main(sys.argv[1:])
File "C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\Ultrasinger.py", line 592, in main
run()
File "C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\Ultrasinger.py", line 168, in run
TranscribeAudio(process_data)
File "C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\Ultrasinger.py", line 375, in TranscribeAudio
transcription_result = transcribe_audio(process_data.process_data_paths.cache_folder_path,
File "C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\Ultrasinger.py", line 498, in transcribe_audio
transcription_result = transcribe_with_whisper(
File "C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\modules\Speech_Recognition\Whisper.py", line 217, in transcribe_with_whisper
raise exception
File "C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src\modules\Speech_Recognition\Whisper.py", line 158, in transcribe_with_whisper
result = loaded_whisper_model.transcribe(
File "C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main.venv\lib\site-packages\whisperx\asr.py", line 219, in transcribe
language = language or self.detect_language(audio)
File "", line 13, in detect_language
File "C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main.venv\lib\site-packages\whisperx\asr.py", line 96, in encode
return self.model.encode(features, to_cpu=to_cpu)
RuntimeError: Library cublas64_12.dll is not found or cannot be loaded
(.venv) C:\Users\Anwender\Desktop\Ultrastar\UltraSinger-main\src>
Activity
rakuri255 commentedon Nov 13, 2025
@Alpha0ne9 I think you need an other GPU install script because of the cuda version.
Someone else mentioned it with an rtx5000, that the old cuda versions are not supported anymore.
Look into the GPU install script and try an newer version of pytorch + cuda
shuenli commentedon Dec 17, 2025
Hello all
I have the same problem here.
I managed to create few songs some weeks before and today, error message as above.
I tried updating pytorch + cuda to v2.8.0 and v12.9 but same error.
Everything worked fine before.
End of log :
[youtube] 0aqlS9SOkjs: Downloading m3u8 information
Traceback (most recent call last):
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 1348, in do_open
h.request(req.get_method(), req.selector, req.data, headers,
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 1283, in request
self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 1329, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 1278, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 1038, in _send_output
self.send(msg)
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 976, in send
self.connect()
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 1455, in connect
self.sock = self._context.wrap_socket(self.sock,
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 513, in wrap_socket
return self.sslsocket_class._create(
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 1071, in _create
self.do_handshake()
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 1342, in do_handshake
self._sslobj.do_handshake()
ConnectionResetError: [WinError 10054] Une connexion existante a dû être fermée par l’hôte distant
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main.venv\lib\site-packages\musicbrainzngs\musicbrainz.py", line 497, in _safe_read
f = opener.open(req)
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 519, in open
response = self._open(req, data)
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 536, in _open
result = self._call_chain(self.handle_open, protocol, protocol +
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 496, in _call_chain
result = func(*args)
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 1391, in https_open
return self.do_open(http.client.HTTPSConnection, req,
File "C:\Users\Shuenli\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 1351, in do_open
raise URLError(err)
urllib.error.URLError: <urlopen error [WinError 10054] Une connexion existante a dû être fermée par l’hôte distant>
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main\src\UltraSinger.py", line 752, in
main(sys.argv[1:])
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main\src\UltraSinger.py", line 592, in main
run()
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main\src\UltraSinger.py", line 154, in run
process_data = InitProcessData()
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main\src\UltraSinger.py", line 360, in InitProcessData
) = download_from_youtube(settings.input_file_path, settings.output_folder_path, settings.cookiefile)
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main\src\modules\Audio\youtube.py", line 104, in download_from_youtube
song_info = search_musicbrainz(title, artist)
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main\src\modules\musicbrainz_client.py", line 49, in search_musicbrainz
recording = __multi_line_search(artist, title)
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main\src\modules\musicbrainz_client.py", line 118, in __multi_line_search
result2 = musicbrainzngs.search_recordings(recording=title2, limit=10, artist=artist2, artistname=artist2)
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main.venv\lib\site-packages\musicbrainzngs\musicbrainz.py", line 971, in search_recordings
return _do_mb_search('recording', query, fields, limit, offset, strict)
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main.venv\lib\site-packages\musicbrainzngs\musicbrainz.py", line 782, in _do_mb_search
return _do_mb_query(entity, '', [], params)
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main.venv\lib\site-packages\musicbrainzngs\musicbrainz.py", line 728, in _do_mb_query
return _mb_request(path, 'GET', auth_required, args=args)
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main.venv\lib\site-packages\musicbrainzngs\musicbrainz.py", line 417, in call
return self.fun(*args, **kwargs)
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main.venv\lib\site-packages\musicbrainzngs\musicbrainz.py", line 690, in _mb_request
resp = _safe_read(opener, req, body)
File "D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main.venv\lib\site-packages\musicbrainzngs\musicbrainz.py", line 525, in _safe_read
raise NetworkError(cause=exc)
musicbrainzngs.musicbrainz.NetworkError: caused by: <urlopen error [WinError 10054] Une connexion existante a dû être fermée par l’hôte distant>
(.venv) D:\Jeux_Jeux musicaux\UltraStar\UltraSinger-main\src>
SacredSkull commentedon Dec 18, 2025
For the rtx 5000 series there's a post on the ultrastar discord (and ultrasinger channel) for this server with a requirements.txt / instructions, but the requirements file has a lot of fluff.
You need to use WSL too, but it completely works
rakuri255 commentedon Feb 14, 2026
I currently fixing the installer and moving to uv.
The current solution has a broken dependencie chain and cant be installed anymore.
rakuri255 commentedon Feb 14, 2026
The cublas64_12.dll issue from @Alpha0ne9 should be solver. Jumped to python 3.12 + pytorch 2.8.0+cu128
The musicbrainz.NetworkError from @shuenli is an other issue that seems already fixed
rakuri255 commentedon Feb 15, 2026
@shuenli it is already fixed and in main. Thanks to @magicus
See here: b098d16