Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ Try it with [ZFTurbo's Music-Source-Separation-Training](https://github.com/ZFTu
|
|
| 13 |
|
| 14 |
## Models
|
| 15 |
|
| 16 |
-
### 1. Fused Models
|
| 17 |
|
| 18 |
I used [a model fusion script](https://huggingface.co/Sucial/Dereverb-Echo_Mel_Band_Roformer/blob/main/scripts/model_fusion.py) to fuse three models with the same model structure. The three models and their corresponding fusion ratios are as follows:<br>
|
| 19 |
**0.5 * dereverb_echo_mbr_v2_sdr_dry_13.4843.ckpt + 0.25 * de_big_reverb_mbr_ep_362.ckpt + 0.25 * de_super_big_reverb_mbr_ep_346.ckpt**<br>
|
|
|
|
| 13 |
|
| 14 |
## Models
|
| 15 |
|
| 16 |
+
### 1. Fused Models(I personally recommend using this model)
|
| 17 |
|
| 18 |
I used [a model fusion script](https://huggingface.co/Sucial/Dereverb-Echo_Mel_Band_Roformer/blob/main/scripts/model_fusion.py) to fuse three models with the same model structure. The three models and their corresponding fusion ratios are as follows:<br>
|
| 19 |
**0.5 * dereverb_echo_mbr_v2_sdr_dry_13.4843.ckpt + 0.25 * de_big_reverb_mbr_ep_362.ckpt + 0.25 * de_super_big_reverb_mbr_ep_346.ckpt**<br>
|