Upload melbandroformers2Fvoc_gabox.yaml
Browse files
misc/melbandroformers2Fvoc_gabox.yaml
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
audio:
|
| 2 |
+
chunk_size: 352800
|
| 3 |
+
dim_f: 1024
|
| 4 |
+
dim_t: 256
|
| 5 |
+
hop_length: 441
|
| 6 |
+
n_fft: 2048
|
| 7 |
+
num_channels: 2
|
| 8 |
+
sample_rate: 44100
|
| 9 |
+
min_mean_abs: 0.001
|
| 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 |
+
|
| 41 |
+
training:
|
| 42 |
+
instruments:
|
| 43 |
+
- Vocals
|
| 44 |
+
- Instrumental
|
| 45 |
+
target_instrument: Vocals
|
| 46 |
+
|
| 47 |
+
inference:
|
| 48 |
+
batch_size: 1
|
| 49 |
+
dim_t: 1101
|
| 50 |
+
num_overlap: 1
|
| 51 |
+
chunk_size: 352800
|