Upload folder using huggingface_hub

config.yaml

@@ -0,0 +1,10 @@
+model:
+  _target_: pyannote.audio.models.embedding.wespeaker.WeSpeakerSimAMResNet100
+  sample_rate: 16000
+  num_channels: 1
+  num_mel_bins: 80
+  frame_length: 25
+  frame_shift: 10
+  dither: 0.0
+  window_type: hamming
+  use_energy: false

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58b657757e4b33ea2a62a3b53b01c74fa855ed0c78c42b9e5bcd95a58f1bdc01
+size 196045730

speaker-embedding.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c745571610ae105494a122e0597e5806e3f2e5de5a77e9ba91c915572e41861a
+size 201115747

wespeaker/config.yaml

@@ -0,0 +1,83 @@
+data_type: shard
+dataloader_args:
+  batch_size: 128
+  drop_last: true
+  num_workers: 16
+  pin_memory: false
+  prefetch_factor: 8
+dataset_args:
+  aug_prob: 0.6
+  fbank_args:
+    dither: 1.0
+    frame_length: 25
+    frame_shift: 10
+    num_mel_bins: 80
+  filter: true
+  filter_args:
+    max_num_frames: 800
+    min_num_frames: 100
+  num_frms: 200
+  resample_rate: 16000
+  sample_num_per_epoch: 0
+  shuffle: true
+  shuffle_args:
+    shuffle_size: 2500
+  spec_aug: false
+  spec_aug_args:
+    max_f: 8
+    max_t: 10
+    num_f_mask: 1
+    num_t_mask: 1
+    prob: 0.6
+  speed_perturb: true
+enable_amp: false
+exp_dir: exp/samresnet100/
+gpus:
+- 0
+- 1
+log_batch_interval: 100
+loss: CrossEntropyLoss
+loss_args: {}
+margin_scheduler: MarginScheduler
+margin_update:
+  epoch_iter: 4265
+  final_margin: 0.2
+  fix_start_epoch: 40
+  increase_start_epoch: 20
+  increase_type: exp
+  initial_margin: 0.0
+  update_margin: true
+model: SimAM_ResNet100_ASP
+model_args:
+  embed_dim: 256
+model_init: null
+noise_data: data/musan/lmdb
+num_avg: 1
+num_epochs: 150
+optimizer: SGD
+optimizer_args:
+  lr: 0.1
+  momentum: 0.9
+  nesterov: true
+  weight_decay: 0.0001
+projection_args:
+  do_lm: false
+  easy_margin: false
+  embed_dim: 256
+  num_class: 17982
+  project_type: arc_margin
+  scale: 32.0
+reverb_data: data/rirs/lmdb
+save_epoch_interval: 5
+scheduler: ExponentialDecrease
+scheduler_args:
+  epoch_iter: 4265
+  final_lr: 5.0e-05
+  initial_lr: 0.1
+  num_epochs: 150
+  scale_ratio: 4.0
+  warm_from_zero: true
+  warm_up_epoch: 6
+seed: 42
+train_data: data/vox2_dev/shard.list
+train_label: data/vox2_dev/utt2spk