celery-slow logs:

[2022-02-13 10:33:47,946: INFO/MainProcess] Task api.tasks.create_dynamic_mix[fcc56ab5-30ea-44f3-a5b4-c969b9c7bdbc] received
INFO:tensorflow:Apply unet for vocals_spectrogram
[2022-02-13 10:33:52,470: INFO/ForkPoolWorker-1] Apply unet for vocals_spectrogram
2022-02-13 10:33:52.539600: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2022-02-13 10:33:52.539653: W tensorflow/stream_executor/cuda/cuda_driver.cc:326] failed call to cuInit: UNKNOWN ERROR (303)
2022-02-13 10:33:52.539719: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (69eb1e621b67): /proc/driver/nvidia/version does not exist
WARNING:tensorflow:From /usr/local/lib/python3.7/site-packages/tensorflow/python/keras/layers/normalization.py:534:_colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
[2022-02-13 10:33:52,585: WARNING/ForkPoolWorker-1] From /usr/local/lib/python3.7/site-packages/tensorflow/python/keras/layers/normalization.py:534: _colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
INFO:tensorflow:Apply unet for drums_spectrogram
[2022-02-13 10:33:53,628: INFO/ForkPoolWorker-1] Apply unet for drums_spectrogram
INFO:tensorflow:Apply unet for bass_spectrogram
[2022-02-13 10:33:54,692: INFO/ForkPoolWorker-1] Apply unet for bass_spectrogram
INFO:tensorflow:Apply unet for other_spectrogram
[2022-02-13 10:33:55,773: INFO/ForkPoolWorker-1] Apply unet for other_spectrogram
[2022-02-13 10:33:58,728: WARNING/ForkPoolWorker-1] INFO:spleeter:Downloading model archive https://github.com/deezer/spleeter/releases/download/v1.4.0/4stems.tar.gz
[2022-02-13 10:33:58,727: INFO/ForkPoolWorker-1] Downloading model archive https://github.com/deezer/spleeter/releases/download/v1.4.0/4stems.tar.gz
[2022-02-13 10:34:03,811: WARNING/ForkPoolWorker-1] timed out
[2022-02-13 10:34:03,864: INFO/ForkPoolWorker-1] Task api.tasks.create_dynamic_mix[fcc56ab5-30ea-44f3-a5b4-c969b9c7bdbc] succeeded in 15.91590800700942s: None

Seems to be a bug in youtube-dl, which doesn't seem to be very active anymore. Consider using yt-dlp instead.

Should update deletion logic to clean up the empty directories as well.

api:

[django.request][WARNING]: Forbidden: /api/source-track/

It's likely due to the User header passed by the browser to nginx, and nginx passing it to api.

I used docker to build the image, but port 8000 was occupied and failed to start.

Creating spleeter-web_frontend_1    ... done
Creating spleeter-web_redis_1    ... done
Creating spleeter-web_celery-slow_1 ...
Creating spleeter-web_celery-fast_1 ...
Creating spleeter-web_api_1         ... error
Creating spleeter-web_celery-slow_1 ... done
Creating spleeter-web_celery-fast_1 ... done
0.0:8000 failed: port is already allocated

ERROR: for api  Cannot start service api: driver failed programming external connectivity on endpoint spleeter-web_api_1 (78dfbd67a1d4afbe00a8f9e8145d01ada08d9c41fe3622ef1584334f64a7384c): Bind for 0.0.0.0:8000 failed: port is already allocated
ERROR: Encountered errors while bringing up the project.

I enter the container, modify the port and try to start the container. The web page prompts "err_connection_reset", and the error "no module named 'API. Apps" is displayed in the container log

Applying migrations
Traceback (most recent call last):
  File "manage.py", line 21, in <module>
    main()
  File "manage.py", line 17, in main
    execute_from_command_line(sys.argv)
  File "/usr/local/lib/python3.7/site-packages/django/core/management/__init__.py", line 419, in execute_from_command_line
    utility.execute()
  File "/usr/local/lib/python3.7/site-packages/django/core/management/__init__.py", line 395, in execute
    django.setup()
  File "/usr/local/lib/python3.7/site-packages/django/__init__.py", line 24, in setup
    apps.populate(settings.INSTALLED_APPS)
  File "/usr/local/lib/python3.7/site-packages/django/apps/registry.py", line 91, in populate
    app_config = AppConfig.create(entry)
  File "/usr/local/lib/python3.7/site-packages/django/apps/config.py", line 212, in create
    mod = import_module(mod_path)
  File "/usr/local/lib/python3.7/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1006, in _gcd_import
  File "<frozen importlib._bootstrap>", line 983, in _find_and_load
  File "<frozen importlib._bootstrap>", line 965, in _find_and_load_unlocked
ModuleNotFoundError: No module named 'api.apps'
Traceback (most recent call last):
  File "manage.py", line 21, in <module>
    main()
  File "manage.py", line 17, in main
    execute_from_command_line(sys.argv)
  File "/usr/local/lib/python3.7/site-packages/django/core/management/__init__.py", line 419, in execute_from_command_line
    utility.execute()
  File "/usr/local/lib/python3.7/site-packages/django/core/management/__init__.py", line 395, in execute
    django.setup()
  File "/usr/local/lib/python3.7/site-packages/django/__init__.py", line 24, in setup
    apps.populate(settings.INSTALLED_APPS)
  File "/usr/local/lib/python3.7/site-packages/django/apps/registry.py", line 91, in populate
    app_config = AppConfig.create(entry)
  File "/usr/local/lib/python3.7/site-packages/django/apps/config.py", line 212, in create
    mod = import_module(mod_path)
  File "/usr/local/lib/python3.7/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1006, in _gcd_import
  File "<frozen importlib._bootstrap>", line 983, in _find_and_load
  File "<frozen importlib._bootstrap>", line 965, in _find_and_load_unlocked
ModuleNotFoundError: No module named 'api.apps'
Starting server
Watching for file changes with StatReloader
Exception in thread django-main-thread:
Traceback (most recent call last):
  File "/usr/local/lib/python3.7/threading.py", line 926, in _bootstrap_inner
    self.run()
  File "/usr/local/lib/python3.7/threading.py", line 870, in run
    self._target(*self._args, **self._kwargs)
  File "/usr/local/lib/python3.7/site-packages/django/utils/autoreload.py", line 64, in wrapper
    fn(*args, **kwargs)
  File "/usr/local/lib/python3.7/site-packages/django/core/management/commands/runserver.py", line 110, in inner_run
    autoreload.raise_last_exception()
  File "/usr/local/lib/python3.7/site-packages/django/utils/autoreload.py", line 87, in raise_last_exception
    raise _exception[1]
  File "/usr/local/lib/python3.7/site-packages/django/core/management/__init__.py", line 375, in execute
    autoreload.check_errors(django.setup)()
  File "/usr/local/lib/python3.7/site-packages/django/utils/autoreload.py", line 64, in wrapper
    fn(*args, **kwargs)
  File "/usr/local/lib/python3.7/site-packages/django/__init__.py", line 24, in setup
    apps.populate(settings.INSTALLED_APPS)
  File "/usr/local/lib/python3.7/site-packages/django/apps/registry.py", line 91, in populate
    app_config = AppConfig.create(entry)
  File "/usr/local/lib/python3.7/site-packages/django/apps/config.py", line 212, in create
    mod = import_module(mod_path)
  File "/usr/local/lib/python3.7/importlib/__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1006, in _gcd_import
  File "<frozen importlib._bootstrap>", line 983, in _find_and_load
  File "<frozen importlib._bootstrap>", line 965, in _find_and_load_unlocked
ModuleNotFoundError: No module named 'api.apps'

Example: https://sigsep.github.io/open-unmix/results.html#demo-tracks

https://docs.docker.com/develop/develop-images/multistage-build/#use-multi-stage-builds

• As part of build, the api image should include the result of the current frontend image.
• might be a good idea to split api and celeries
• celeries should have a base image, and add to it with 2 separate images

  FROM docker.io/JefferyCA/spleeter-web-celery-api
  ENTRYPOINT ["celery-fast-entrypoint.sh"]
  

  ^ would be JefferyCA/spleeter-web-celery-fast

What I did (on a VM dedicated to it):

git clone https://github.com/JeffreyCA/spleeter-web.git && cd spleeter-web && docker-compose -f docker-compose.yml -f docker-compose.dev.yml up > whatisthis.log

whatisthis.log

Also, please, this is unmaintainable. This setup wants to assume, that it has unlimited control of the VM/docker. From a self-hosting perspective, it looks like a day or two to get running, and even more burden down the road.

EDIT: I'm not dead, but don't also have any info on when I'll return to test, add.

Currently the delete button is disabled for YouTube source tracks whose tasks are queued or in progress.

Ideally, the delete action should revoke the corresponding task if it's in a queued state, and it should terminate the task if it's still in progress.

Huey supports the former, but does not have the ability to terminate a running task. Might be worthwhile to look at Celery as an alternative...

Hi,

Just wondering why the following errors pop up when I run spleeter-web$ sudo docker-compose -f docker-compose.yml -f docker-compose.build.yml -f docker-compose.prod.yml up --build -d from step 4:

I am using Azure as my storage provider and have created the .env file as specified in step 3.

Thanks,
Derek

• frontend:

  Starting frontend
  > [email protected] build /webapp/frontend
  > webpack --config webpack.prod.config.js
  Hash: 0234d98b2e6b059e2ee8
  Version: webpack 4.46.0
  Time: 53586ms
  Built at: 02/12/2022 3:02:48 PM
                Asset      Size  Chunks                    Chunk Names
          favicon.ico  32.2 KiB          [emitted]
          favicon.svg   117 KiB          [emitted]
              main.js   188 KiB       0  [emitted]         main
           runtime.js  1.46 KiB       1  [emitted]         runtime
           vendors.js  1.33 MiB       2  [emitted]  [big]  vendors
  vendors.js.LICENSE.txt  4.27 KiB          [emitted]
  Entrypoint main [big] = runtime.js vendors.js main.js
  [+YzT] ./node_modules/react-bootstrap/esm/Nav.js + 3 modules 5.11 KiB {2} [built]
   |    4 modules
  [2YZa] ./src/index.tsx + 53 modules 271 KiB {0} [built]
   | ./src/index.tsx 843 bytes [built]
   | ./src/models/Separator.ts 987 bytes [built]
   | ./src/Constants.tsx 568 bytes [built]
   | ./src/Utils.tsx 1.96 KiB [built]
   | ./src/models/YouTubeLinkFetchStatus.ts 464 bytes [built]
   | ./src/models/PartId.ts 59 bytes [built]
   | ./src/models/MusicParts.ts 214 bytes [built]
   | ./src/svg/cancel.svg 483 bytes [built]
   | ./src/svg/remove.svg 599 bytes [built]
   | ./src/svg/restart.svg 463 bytes [built]
   |     + 44 hidden modules
  [6ctO] ./node_modules/react-bootstrap/esm/Navbar.js + 4 modules 11.2 KiB {2} [built]
   |    5 modules
  [7Tkq] ./node_modules/@jeffreyca/react-jinke-music-player/es/index.js + 36 modules 245 KiB {2} [built]
   |    37 modules
  [91je] ./node_modules/react-bootstrap/node_modules/@restart/hooks/esm/useWillUnmount.js + 1 modules 700 bytes {2} [built]
   |    2 modules
  [DjlD] ./node_modules/awesome-debounce-promise/dist/index.es.js + 2 modules 5.74 KiB {2} [built]
   |    3 modules
  [JUMO] ./node_modules/react-bootstrap/esm/ProgressBar.js + 1 modules 5.17 KiB {2} [built]
   |    2 modules
  [LhCv] ./node_modules/history/esm/history.js + 2 modules 30.6 KiB {2} [built]
   |    3 modules
  [QojX] ./node_modules/react-bootstrap/esm/Form.js + 13 modules 23.3 KiB {2} [built]
   |    14 modules
  [XlTo] ./node_modules/tone/build/esm/index.js + 917 modules 1.19 MiB {2} [built]
   |    918 modules
  [dDCJ] ./node_modules/react-bootstrap/esm/OverlayTrigger.js + 61 modules 103 KiB {2} [built]
   |    62 modules
  [dI71] ./node_modules/@babel/runtime/helpers/esm/inheritsLoose.js + 1 modules 481 bytes {2} [built]
   |    2 modules
  [sjrs] ./node_modules/react-bootstrap/esm/ListGroup.js + 1 modules 3.72 KiB {2} [built]
   |    2 modules
  [yLpj] (webpack)/buildin/global.js 472 bytes {2} [built]
  [zM5D] ./node_modules/react-bootstrap/esm/Modal.js + 18 modules 39.5 KiB {2} [built]
   |    19 modules
   + 1750 hidden modules
  exited with code 0
  

  • Shouldn't frontend be generated before (in a Dockerfile) and included as part of an Image(s)?
• redis: 1:M 12 Feb 2022 15:01:34.804 * Ready to accept connections
• (before, both celery):

  [2022-02-12 15:03:12,728: INFO/MainProcess] Connected to redis://redis:6379/0
  [2022-02-12 15:03:12,750: INFO/MainProcess] mingle: searching for neighbors
  [2022-02-12 15:03:13,798: INFO/MainProcess] mingle: all alone
  

• celery-slow: [2022-02-12 15:03:12,984: INFO/MainProcess] celery@215ae8e2168e ready.
• celery-fast: [2022-02-12 15:03:13,832: INFO/MainProcess] celery@e0e0e3e79c76 ready.
• nginx: (returning 502)

  /docker-entrypoint.sh: /docker-entrypoint.d/ is not empty, will attempt to perform configuration
  /docker-entrypoint.sh: Looking for shell scripts in /docker-entrypoint.d/
  /docker-entrypoint.sh: Launching /docker-entrypoint.d/10-listen-on-ipv6-by-default.sh
  10-listen-on-ipv6-by-default.sh: info: /etc/nginx/conf.d/default.conf is not a file or does not exist
  /docker-entrypoint.sh: Launching /docker-entrypoint.d/20-envsubst-on-templates.sh
  /docker-entrypoint.sh: Launching /docker-entrypoint.d/30-tune-worker-processes.sh
  /docker-entrypoint.sh: Configuration complete; ready for start up
  2022/02/12 15:03:20 [notice] 1#1: using the "epoll" event method
  ...
  2022/02/12 15:03:25 [notice] 1#1: start worker process 60
  2022/02/12 15:03:33 [error] 23#23: *1 connect() failed (111: Connection refused) while connecting to upstream, client: 172.31.0.2, server: , request: "GET / HTTP/1.1", upstream: "http://192.168.48.6:8000/", host: "redacted_domain"
  172.31.0.2 - - [12/Feb/2022:15:03:33 +0000] "GET / HTTP/1.1" 502 158 "-" "Mozilla/5.0 (Windows NT 10.0; rv:91.0) Gecko/20100101 Firefox/91.0" "172.31.0.1"
  2022/02/12 15:15:14 [error] 23#23: *6 connect() failed (113: Host is unreachable) while connecting to upstream, client: 172.31.0.2, server: , request: "GET / HTTP/1.1", upstream: "http://192.168.48.6:8000/", host: "redacted_domain"
  172.31.0.2 - - [12/Feb/2022:15:15:14 +0000] "GET / HTTP/1.1" 502 158 "-" "Mozilla/5.0 (Windows NT 10.0; rv:91.0) Gecko/20100101 Firefox/91.0" "172.31.0.1"
  

• api: Waiting for asset creation (even after restarting the api container)`

docker-compose.yml:

networks:
  redacted_domain:
    internal: true
services:
  redacted_domain-redis:
    image: redis:6.0-buster
    user: "65534:65534"
    expose:
      - "6379"
    volumes:
      - /db/redacted_domain:/data
    networks:
      - redacted_domain
    restart: "no"

  redacted_domain-nginx:
    build: https://github.com/JeffreyCA/spleeter-web.git#:nginx
    image: spleeter-web-nginx:antihardcode
#    image: jeffreyca/spleeter-web-nginx:latest
    volumes:
      - /data/redacted_domain/staticfiles:/webapp/staticfiles:rw
    depends_on:
      - redacted_domain-api
    environment:
      - API_HOST=redacted_domain-api
    networks:
      - redacted_domain
      - proxy # on port 80, expose to https://redacted_domain
    restart: "no"

  redacted_domain-api:
    image: jeffreyca/spleeter-web-backend:latest
    volumes:
      - /data/redacted_domain/staticfiles:/webapp/staticfiles:rw
      - /data/redacted_domain/frontassets:/webapp/assets:rw
      - /data/redacted_domain/sqlite:/webapp/sqlite:rw
    env_file:
      - redacted_domain.env
    depends_on:
      - redacted_domain-redis
      - redacted_domain-frontend
    expose:
      - 8000
    networks:
      - redacted_domain
    restart: "no"

  redacted_domain-celery-fast:
    image: jeffreyca/spleeter-web-backend:latest
    entrypoint: ./celery-fast-entrypoint.sh
    volumes:
      - /data/redacted_domain/celery:/webapp/celery:rw
      - /data/redacted_domain/pretrained_models:/webapp/pretrained_models:rw
      - /data/redacted_domain/sqlite:/webapp/sqlite:rw
    env_file:
      - redacted_domain.env
    depends_on:
      - redacted_domain-redis
    dns:
      - "9.9.9.9"
    networks:
      - redacted_domain
    restart: "no"

  redacted_domain-celery-slow:
    image: jeffreyca/spleeter-web-backend:latest
    entrypoint: ./celery-slow-entrypoint.sh
    volumes:
      - /data/redacted_domain/celery:/webapp/celery:rw
      - /data/redacted_domain/pretrained_models:/webapp/pretrained_models:rw
      - /data/redacted_domain/sqlite:/webapp/sqlite:rw
    env_file:
      - redacted_domain.env
    depends_on:
      - redacted_domain-redis
    networks:
      - redacted_domain
    restart: "no"

  redacted_domain-frontend:
    image: jeffreyca/spleeter-web-frontend:latest
    volumes:
      - /data/redacted_domain/frontassets:/webapp/assets:rw
    networks:
      - redacted_domain
    restart: "no"

env:

DJANGO_SETTINGS_MODULE=django_react.settings_docker
CELERY_BROKER_URL=redis://redacted_domain-redis:6379/0
CELERY_RESULT_BACKEND=redis://redacted_domain-redis:6379/0
APP_HOST=redacted_domain
DEFAULT_FILE_STORAGE=api.storage.FileSystemStorage
YOUTUBE_API_KEY=redacted
CPU_SEPARATION=1
CELERY_FAST_QUEUE_CONCURRENCY=3
CELERY_SLOW_QUEUE_CONCURRENCY=1

So, like attempt 5 on getting this running. It's stuck on waiting?

The YouTube search feature still seems to work, but the download from YouTube seems to fail. I think some underlying conversion service this was relying on must have gone down. If I upload an mp3, the audio is split into parts, with only the conversion from YouTube failing.

Any chance you might be able to add Unraid Support in the future?

I was interested in testing this in Unraid with GPU Support. I'm already using a GPU for encoding with Emby in Unraid and thought I might be able to add this in there.

https://github.com/github/dmca/blob/master/2020/10/2020-10-23-RIAA.md

This makes it hard to tell what the actual track is.

This will be fixed in the next release of Spleeter.

Discussed in #84

Hello All,

I installed Anaconda 3.8. I can open the Anaconda Prompt and import files etc.. But I can't open Anaconda navigator.
I am facingproble as below.

Main Error
check_hostname requires server_hostname

Please suggest a solution.

Currently it always says "Spleeter Web" in the title

https://github.com/JeffreyCA/spleeterweb-xumx

(todo: docs in UI?)

Currently, only mp3, flac, and wav are supported.

1. Start a job
2. Stop containers
3. Start containers

Expected: slow-celery resumes / restarts jobs OR show job failed
Actual: slow-celery sits idle, UI shows 'processing'

Probably due to: Tonejs/Tone.js#706

Hello @JeffreyCA ,
Hope you are doing well.

I am trying to build your spleeter-web on my local Mac machine and also on my Ubuntu server. But I always get the tensorflow error and Error from chokidar. You can see the error log below.

P/S: I did follow your instruction too. I am starting your spleeter-web with docker.

tensorflow errors log (both happened on local mac machine and Ubuntu server):
| 2021-11-23 18:03:22.755058: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
api_1 | 2021-11-23 18:03:22.755269: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.

Error from chokidar log (This happended on Ubuntu server):

frontend_1 | Error from chokidar (/webapp/frontend/node_modules/@react-icons/all-files/ri): Error: ENOSPC: System limit for number of file watchers reached, watch '/webapp/frontend/node_modules/@react-icons/all-files/ri/RiFileList2Fill.esm.js'
frontend_1 | Error from chokidar (/webapp/frontend/node_modules/@react-icons/all-files/ri): Error: ENOSPC: System limit for number of file watchers reached, watch '/webapp/frontend/node_modules/@react-icons/all-files/ri/RiFileList2Fill.js'
frontend_1 | Error from chokidar (/webapp/frontend/node_modules/@react-icons/all-files/ri): Error: ENOSPC: System limit for number of file watchers reached, watch '/webapp/frontend/node_modules/@react-icons/all-files/ri/RiFileList2Line.d.ts'
frontend_1 | Error from chokidar (/webapp/frontend/node_modules/@react-icons/all-files/ri): Error: ENOSPC: System limit for

I am looking forward to your response!

Regards,
Peter

api isn't available, spleeterapi is used instead.

In the ubuntu19/20, centos 7, Mac os 10.14/10.15 I found a problem form the pip
like this:
Running command git clone -q https://github.com/JeffreyCA/youtube-dl.git /webapp/src/youtube-dl
Running command git checkout -q 3afecd1a8c3c4371369984137389d580210c3d15
fatal: reference is not a tree: 3afecd1a8c3c4371369984137389d580210c3d15
ERROR: Command errored out with exit status 128: git checkout -q 3afecd1a8c3c4371369984137389d580210c3d15 Check the logs for full command output.
WARNING: You are using pip version 20.1.1; however, version 20.3.1 is available.
You should consider upgrading via the '/usr/local/bin/python -m pip install --upgrade pip' command.
ERROR: Service 'huey' failed to build : The command '/bin/sh -c pip install --upgrade pip -r requirements.txt' returned a non-zero code: 1

The tips told the error is the pip3/pip vision was out of style, But I checked my machine and my pip is 20.3.1.
So what's the root about the pip? I'm tired, and thanks for you project.

I write the code in anaconda it does not read

Summary of other models

Celery keeps crashing on my MacBook:

celery-slow_1  | [2021-08-25 23:24:53,573: ERROR/MainProcess] Process 'ForkPoolWorker-3' pid:27 exited with 'signal 9 (SIGKILL)'
celery-slow_1  | [2021-08-25 23:24:53,588: ERROR/MainProcess] Task handler raised error: WorkerLostError('Worker exited prematurely: signal 9 (SIGKILL) Job: 3.')
celery-slow_1  | Traceback (most recent call last):
celery-slow_1  |   File "/usr/local/lib/python3.7/site-packages/billiard/pool.py", line 1267, in mark_as_worker_lost
celery-slow_1  |     human_status(exitcode), job._job),
celery-slow_1  | billiard.exceptions.WorkerLostError: Worker exited prematurely: signal 9 (SIGKILL) Job: 3.

Does anyone know what causes this?

Anyway, thanks for this great work!

Hi, I have followed all the procedures in Readme.md for running the app both with docker and without docker. Everything seems fine, no errors but http://0.0.0.0:8000 in my browser gives "This site can’t be reached".

Also, can it be deployed on VPS? How?

Thanks

It should be content_disposition instead.

Hi! I'm inspired by your project but I cannot find any information (step by step algorythm) how to train my own model by .wav tracks collection with spleeter. I know something like .csv and .json files are needed. Can you help me please? I ll collect .wav tracks and you will train model in spleeter. 4stems model is good but doesn't work well

Something similar to a mixing board where you can dynamically adjust the output levels of each component.

To reproduce:

• Upload mp3
• Generate static mix for D3Net
• Immediately fails with error

hey!
how to get access to cors from other domains?
For instance: I want to use api.site.com like backend,
and site.com like frontend, I'll send requests via jquery for downloading youtube videos, creating mixes (separating), and for getting urls to files.

But when I run js code from site.com
There is one problem:
Access to XMLHttpRequest at 'https://api.site.com/api/source-track/youtube/' from origin 'https://site.com' has been blocked by CORS policy: Response to preflight request doesn't pass access control check: No 'Access-Control-Allow-Origin' header is present on the requested resource.

I tried to install django cors headers
BUT it doesn't work, pls help me

Hello!
AFter uploading mp3 script waits.
Showing message: In queue
I am waiting more that one hour, but nothing happened

It's api's response:
{
"id": "6222892a-bcae-49cb-bed0-5a193361421e",
"source_track": "2ffae5d6-62e4-4af1-8d63-834ab3ad9301",
"separator": "spleeter",
"extra_info": [
"256 kbps",
"4 stems (16 kHz)"
],
"artist": "Taq tara",
"title": "Kisla",
"vocals_url": "",
"other_url": "",
"bass_url": "",
"drums_url": "",
"status": "Queued",
"error": "",
"date_created": "2021-12-13T10:40:47.057898Z"
}