Windows 10 Home (current with updates)
Dell Inspiron 5759
16 gig RAM
Intel HD Graphics 520 (Dell)
4096MB ATI AMD Radeon R5 M335 (Dell)
CrossFire Disabled
Python 3.7.3 (v3.7.3:ef4ec6ed12, Mar 25 2019, 22:22:05) [MSC v.1916 64 bit (AMD64)] on win32
Installed using
pip install spleeter
Even just trying to get the help info I get...
D:>spleeter -h
Traceback (most recent call last):
File "c:\python\lib\site-packages\pkg_resources__init__.py", line 583, in _build_master
ws.require(__requires__)
File "c:\python\lib\site-packages\pkg_resources__init__.py", line 900, in require
needed = self.resolve(parse_requirements(requirements))
File "c:\python\lib\site-packages\pkg_resources__init__.py", line 791, in resolve
raise VersionConflict(dist, req).with_context(dependent_req)
pkg_resources.ContextualVersionConflict: (setuptools 40.8.0 (c:\python\lib\site-packages), Requirement.parse('setuptools>=41.0.0'), {'tensorboard'})
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Python\Scripts\spleeter-script.py", line 6, in
from pkg_resources import load_entry_point
File "c:\python\lib\site-packages\pkg_resources__init__.py", line 3191, in
@_call_aside
File "c:\python\lib\site-packages\pkg_resources__init__.py", line 3175, in _call_aside
f(args, *kwargs)
File "c:\python\lib\site-packages\pkg_resources__init__.py", line 3204, in _initialize_master_working_set
working_set = WorkingSet._build_master()
File "c:\python\lib\site-packages\pkg_resources__init__.py", line 585, in _build_master
return cls._build_from_requirements(__requires__)
File "c:\python\lib\site-packages\pkg_resources__init__.py", line 598, in _build_from_requirements
dists = ws.resolve(reqs, Environment())
File "c:\python\lib\site-packages\pkg_resources__init__.py", line 791, in resolve
raise VersionConflict(dist, req).with_context(dependent_req)
pkg_resources.ContextualVersionConflict: (setuptools 40.8.0 (c:\python\lib\site-packages), Requirement.parse('setuptools>=41.0.0'), {'tensorboard'})
Reverend-Jim
All 7 comments
While I am not associated with the project, it seems like (from the error) that you need to install setuptools 41.0.0 or greater? Obviously ideally pip would correctly install this dependency, but does installing that package manually unblock you?
awesomer
on 6 Nov 2019
python -m pip install --upgrade pip setuptools
did the upgrade from 40.x to 41.x and it works now. Thanks.
Reverend-Jim
on 6 Nov 2019
We added the good setuptools dependency to the package requirements and the next release will fix that up.
Faylixe
on 6 Nov 2019
How long should a run take? I started a run against a song (2:48 duration) this afternoon and it is still running at 9:25 pm. Here is what it shows so far:
D:>spleeter separate -i test.mp3
INFO:tensorflow:Downloading model archive https://github.com/deezer/spleeter/releases/download/v1.4.0/2stems.tar.gz
INFO:tensorflow:Using config: {'_model_dir': 'pretrained_models\2stems', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': gpu_options {
per_process_gpu_memory_fraction: 0.7
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_service': None, '_cluster_spec':
INFO:tensorflow:Calling model_fn.
WARNING:tensorflow:From c:\python\lib\site-packages\spleeter\model\functions\unet.py:29: The name tf.keras.initializers.he_uniform is deprecated. Please use tf.compat.v1.keras.initializers.he_uniform instead.
INFO:tensorflow:Apply unet for vocals_spectrogram
INFO:tensorflow:Apply unet for accompaniment_spectrogram
INFO:tensorflow:Done calling model_fn.
WARNING:tensorflow:From c:\python\lib\site-packages\tensorflow\python\ops\array_ops.py:1354: add_dispatch_support.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
INFO:tensorflow:Graph was finalized.
WARNING:tensorflow:From c:\python\lib\site-packages\tensorflow\python\training\saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from pretrained_models\2stems\model
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
WARNING:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.string
WARNING:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int32
WARNING:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.string
INFO:tensorflow:Loading audio b'test.mp3' from 0.0 to 600.0
Spleeter.exe is still shown as running but is using 0% cpu. It did get as far as creating the following directory and files:
D:\>dir pretrained_models /s
Volume in drive D is D-Data
Volume Serial Number is 366A-6FA3
Directory of D:\pretrained_models
2019-11-06 13:04 <DIR> .
2019-11-06 13:04 <DIR> ..
2019-11-06 13:04 <DIR> 2stems
0 File(s) 0 bytes
Directory of D:\pretrained_models\2stems
2019-11-06 13:04 <DIR> .
2019-11-06 13:04 <DIR> ..
2019-10-24 03:35 176 ._checkpoint
2019-11-06 13:04 2 .probe
2019-10-24 03:35 67 checkpoint
2019-10-24 03:35 78,614,080 model.data-00000-of-00001
2019-10-24 03:35 5,244 model.index
2019-10-24 03:35 805,575 model.meta
6 File(s) 79,425,144 bytes
Total Files Listed:
6 File(s) 79,425,144 bytes
5 Dir(s) 776,089,026,560 bytes free
How long should a run take? I started a run against a song (2:48 duration) this afternoon and it is still running at 9:25 pm. Here is what it shows so far:
D:>spleeter separate -i test.mp3
INFO:tensorflow:Downloading model archive https://github.com/deezer/spleeter/releases/download/v1.4.0/2stems.tar.gz
INFO:tensorflow:Using config: {'_model_dir': 'pretrained_models\2stems', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': gpu_options {
per_process_gpu_memory_fraction: 0.7
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_service': None, '_cluster_spec':, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
INFO:tensorflow:Calling model_fn.
WARNING:tensorflow:From c:\python\lib\site-packages\spleeter\model\functions\unet.py:29: The name tf.keras.initializers.he_uniform is deprecated. Please use tf.compat.v1.keras.initializers.he_uniform instead.INFO:tensorflow:Apply unet for vocals_spectrogram
INFO:tensorflow:Apply unet for accompaniment_spectrogram
INFO:tensorflow:Done calling model_fn.
WARNING:tensorflow:From c:\python\lib\site-packages\tensorflow\python\ops\array_ops.py:1354: add_dispatch_support..wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
INFO:tensorflow:Graph was finalized.
WARNING:tensorflow:From c:\python\lib\site-packages\tensorflow\python\training\saver.py:1276: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from pretrained_models\2stems\model
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
WARNING:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.string
WARNING:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int32
WARNING:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.string
INFO:tensorflow:Loading audio b'test.mp3' from 0.0 to 600.0Spleeter.exe is still shown as running but is using 0% cpu. It did get as far as creating the following directory and files:
D:\>dir pretrained_models /s Volume in drive D is D-Data Volume Serial Number is 366A-6FA3 Directory of D:\pretrained_models 2019-11-06 13:04 <DIR> . 2019-11-06 13:04 <DIR> .. 2019-11-06 13:04 <DIR> 2stems 0 File(s) 0 bytes Directory of D:\pretrained_models\2stems 2019-11-06 13:04 <DIR> . 2019-11-06 13:04 <DIR> .. 2019-10-24 03:35 176 ._checkpoint 2019-11-06 13:04 2 .probe 2019-10-24 03:35 67 checkpoint 2019-10-24 03:35 78,614,080 model.data-00000-of-00001 2019-10-24 03:35 5,244 model.index 2019-10-24 03:35 805,575 model.meta 6 File(s) 79,425,144 bytes Total Files Listed: 6 File(s) 79,425,144 bytes 5 Dir(s) 776,089,026,560 bytes free
Same issue.
btw, I am not using the original sample, but a mp3-form audio from my music collection.
ffmpeg and ffplay can read the file successfully, but spleeter keeps stuck on reading the file,
and spleeter works on the given sample(audio_example.mp3) well.
Saltflow
on 7 Nov 2019
Duplicate with #30 and #29 please retry with the new version released. It fixes FFmpeg reading.
Faylixe
on 7 Nov 2019
OK. This is now officially awesome.
Reverend-Jim
on 7 Nov 2019
Related issues
ateammeech
路
3Comments
Rahul-Sindhu
路
4Comments
max6292
路
5Comments
NXG2005
路
4Comments
JohnSmith2007
路
4Comments