Cool_Tools/ultimatevocalremovergui
1
0
Fork 0
mirror of https://github.com/Anjok07/ultimatevocalremovergui.git synced 2025-02-17 19:19:15 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Anjok07 2021-06-01 03:36:31 -05:00 committed by GitHub
parent ff9538e4cc
commit b0e6013c23
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
README.md
View File

@ -87,27 +87,31 @@ python inference.py -g 0 -m modelparams/2band_32000.json -P models/MGM-v5-2Band-
```
The following examples show how to run the ensemble model scripts -
```
python 4Band_ens_inference.py -g 0 -i "INPUT"
```
```
python 12_model_ens_inference.py -g 0 -i "INPUT"
python ensemble_inference.py -g 0 -i "INPUT"
```
Or if you wish to save all individual outputs generated in addition to the final ensembled outputs, please run the following -
```
python 4Band_ens_inference.py -g 0 -s -i "INPUT"
```
```
python 12_model_ens_inference.py -g 0 -s -i "INPUT"
python ensemble_inference.py -g 0 -s -i "INPUT"
```
- **Please Note:** Do not specify the model parameters or a model for the ensemble inference scripts! Those details are already fixed within the script. All final outputs generated through the ensemble scripts can be found in the "ensembled" folder.
You can also specify the models you wish to ensemble. For the ensemble_inference script specifically, do not input the ".pth" extension within the command, only the name. Here is an example -
```
python ensemble_inference.py -g 0 -P "MODELNAME1" "MODELNAME2" "MODELNAME3" -i "INPUT"
```
- **Please Note the Following:**
- Do not specify the model parameters or architectures for the ensemble inference script. Those details are already fixed.
- When ensembling models with low and high bandwidth conversions, '--bypass' is highly recommended.
- The ensembled outputs generated through the ensemble scripts can be found in the "ensembled" folder.
### Ensembler
The ensembler has the ability to take 2 or more instrumental or vocal outputs generated by different models and combine the best results from all of them! Here is how to use it manually -
The stand alone ensembler has the ability to take 2 or more instrumental or vocal outputs generated by different models and combine the best results from all of them! Here is how to use it manually -
- For instrumental outputs, run the following command: