[Discussion] Custom Model does not separate at all.

Hi all,

I've posted here a few times, this spleeter thing isn't a walk in the park! BUT, I have managed to almost get there in the end. I just need help training a model, all my models don't seem to work.

A little backstory about my use case - I'm trying to adapt spleeter to separate dialogue from films. In the Fan Edit community, this is basically the hardest part of editing release material. Some films and shows have a 'clean' centre channel, with only dialogue, and this makes life super easy, most do not. If I can figure this out, it will basically revolutionise fan edits and make edits previously impossible due to music bleed, possible.

I have compiled a collection of shows and movies I could get my hands on with 100% clean centre channels for audio dialogue. No music bleed. This was extremely time consuming! With the idea I could train a model that output "vocals" and "other".

I ended up with 160 odd episodes and 3 films. Roughly 90 hours or so of raw data.

Steps so far:

1. Using ffmpeg, I took the 5.1 Audio from the films/episodes. This gave me 6 channels: `[FL][FR][FC][LFE][BL][BR]` where the centre channel was entirely dialogue and no music. I verified this for every data point.
2. Using ffmpeg I created a mono track that downmixed the entire 5.1 audio to 1x mono. Giving me dialogue, music and effects.
3. I organised the config files as instructed. With a .csv file with "mix_path" containing the mono full downmixed film audio, "vocal_path" containing the centre channel audio and "other_path" containing a channel with the music mix, and edited the config.json with the new paths and my data directories.
4. I ran `spleeter train -p ~/Configs/filmModel.json -d ~/filmDataSet`. This gave me:
```
INFO:spleeter:Start model training
INFO:spleeter:Model training done
```
And this output the model into the directory "filmModel" (as the config file told it to). This took a suspiciously small amount of time for 90 hours of audio...

5. I then used `spleeter separate -i "~\Testfilm.mp4" -o Test -p "~\Configs\filmModel.json"`
6. It did its thing and ouput:
```
INFO:spleeter:File ~/vocals.wav written succesfully
INFO:spleeter:File ~/other.wav written succesfully
```
This also took a very short amount of time, but this was less suspicious as the test file I was using is only 1m50s.

7. I went to audacity and dragged my two files in and they are practically identical.
8. Tested with `spleeter:2stems` on the same `~\Testfilm.mp4` and it does output music and vocals (but it's not that good).

Am I training correctly? I can't seem to figure out why my model doesn't work! Anyone have any advice, tips or things to try?

One thing that did come to mind was that the length of these files might be too much for spleeter. I ran into issues trying to use `spleeter separate` on lengthy files, spleeter threw tons of errors. I currently use a 1m50s sample file of a film not in my training data, this does not throw any errors and works fine with `spleeter:2stem`. No errors are thrown for training my custom model, but could this be a possible issue?

Start by reviewing the custom config.json and the dataset paths named in the report, then reproduce the `spleeter train` and `spleeter separate` commands with the supplied mono, vocal, and other tracks. Compare the generated outputs with the source tracks and training logs; the issue is resolved only when the custom model produces distinct, correctly separated stems.

Written by the indexing model from the issue text.