meskvlla33 commited on
Commit
0d105fb
·
verified ·
1 Parent(s): 4f0df64

Upload 2 files

Browse files
config_rifforge_mesk.yaml ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ audio:
2
+ chunk_size: 734706
3
+ dim_f: 1024
4
+ dim_t: 1667
5
+ hop_length: 441
6
+ n_fft: 2048
7
+ num_channels: 2
8
+ sample_rate: 44100
9
+ min_mean_abs: 0.000
10
+
11
+ model:
12
+ dim: 384
13
+ depth: 6
14
+ stereo: true
15
+ num_stems: 1
16
+ time_transformer_depth: 1
17
+ freq_transformer_depth: 1
18
+ num_bands: 60
19
+ dim_head: 64
20
+ heads: 8
21
+ attn_dropout: 0
22
+ ff_dropout: 0
23
+ flash_attn: True
24
+ dim_freqs_in: 1025
25
+ sample_rate: 44100 # needed for mel filter bank from librosa
26
+ stft_n_fft: 2048
27
+ stft_hop_length: 441
28
+ stft_win_length: 2048
29
+ stft_normalized: False
30
+ mask_estimator_depth: 2
31
+ multi_stft_resolution_loss_weight: 1.0
32
+ multi_stft_resolutions_window_sizes: !!python/tuple
33
+ - 4096
34
+ - 2048
35
+ - 1024
36
+ - 512
37
+ - 256
38
+ multi_stft_hop_size: 147
39
+ multi_stft_normalized: False
40
+ use_torch_checkpoint: true
41
+
42
+ training:
43
+ instruments:
44
+ - other
45
+ - vocals
46
+ target_instrument: other
47
+ other_fix: true # it's needed for checking on multisong dataset if other is actually instrumental
48
+ use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true
49
+
50
+ inference:
51
+ batch_size: 1
52
+ dim_t: 1667
53
+ num_overlap: 2
rifforge_mesk_beta_v1_sdr_14.0127.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee1111a1beb812250a700e3d65936d5b9db3934fb41b3fa1db1bc1b09aafdbf
3
+ size 913108043