add new model

README.md

@@ -1,13 +1,3 @@
 ---
 license: gpl-3.0
 ---
-
-~~推荐8_256_6~~
-
-**推荐[deverb_bs_roformer](https://huggingface.co/anvuew/deverb_bs_roformer)**
-
-~~虽然8_512_12的SDR稍高~~，但因仅使用单A100训练了14h，导致提升有限的同时却使推理时间变为8_256_6的3倍以上
-
-~90h数据，76种混响
-
-也许是混响类型太多，训练效果不太理想，有兴趣可以使用特定类型的混响微调

dereverb_mel_band_roformer_anvuew.yaml

@@ -0,0 +1,76 @@
+audio:
+  chunk_size: 352800
+  dim_f: 1024
+  dim_t: 256
+  hop_length: 441
+  n_fft: 2048
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.000
+
+model:
+  dim: 384
+  depth: 6
+  stereo: true
+  num_stems: 1
+  time_transformer_depth: 1
+  freq_transformer_depth: 1
+  num_bands: 60
+  dim_head: 64
+  heads: 8
+  attn_dropout: 0
+  ff_dropout: 0
+  flash_attn: True
+  dim_freqs_in: 1025
+  sample_rate: 44100  # needed for mel filter bank from librosa
+  stft_n_fft: 2048
+  stft_hop_length: 441
+  stft_win_length: 2048
+  stft_normalized: False
+  mask_estimator_depth: 2
+  multi_stft_resolution_loss_weight: 1.0
+  multi_stft_resolutions_window_sizes: !!python/tuple
+  - 4096
+  - 2048
+  - 1024
+  - 512
+  - 256
+  multi_stft_hop_size: 147
+  multi_stft_normalized: False
+
+training:
+  batch_size: 3
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+  - noreverb
+  - reverb
+  lr: 5.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: noreverb
+  num_epochs: 1000
+  num_steps: 4000
+  q: 0.95
+  coarse_loss_clip: false
+  ema_momentum: 0.999
+  optimizer: adamw
+  other_fix: true # it's needed for checking on multisong dataset if other is actually instrumental
+  use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true
+
+augmentations:
+  enable: true # enable or disable all augmentations (to fast disable if needed)
+  loudness: true # randomly change loudness of each stem on the range (loudness_min; loudness_max)
+  loudness_min: 0.1
+  loudness_max: 1.0
+  mixup: false # mix several stems of same type with some probability (only works for dataset types: 1, 2, 3)
+  mixup_probs: !!python/tuple # 2 additional stems of the same type (1st with prob 0.2, 2nd with prob 0.02)
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+
+inference:
+  batch_size: 1
+  dim_t: 801
+  num_overlap: 2

dereverb_mel_band_roformer_anvuew_sdr_19.1729.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9262877b87e9ebb0fb808a456b0a411fa677f5df31c8383c1254af531c078970
+size 913107578

dereverb_mel_band_roformer_less_aggressive_anvuew_sdr_18.8050.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db8f1b41c00cead1112e967262a12802fd32e76c0c3a8eb207e772bae25d07b
+size 913107578