first commit

.gitattributes

@@ -32,3 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+embedding_model.ckpt filter=lfs diff=lfs merge=lfs -text
+normalizer.ckpt filter=lfs diff=lfs merge=lfs -text
+projector.ckpt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,3 @@
+{
+  "speechbrain_interface": "SpeakerRecognition"
+}

embedding_model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6f7dcf4eb97e68fb0989e3fbc9c667c60eaa0c598753e86e7b07bac0729755
+size 301999678

hyperparams.yaml

@@ -0,0 +1,64 @@
+# ############################################################################
+# Model: ECAPA big for Speaker verification
+# ############################################################################
+
+# Feature parameters
+n_mels: 80
+
+# Pretrain folder (HuggingFace)
+pretrained_path: gorinars/sb-cssl-offline-wp
+
+# Output parameters
+out_n_neurons: 308
+
+# Model params
+compute_features: !new:speechbrain.lobes.features.Fbank
+  n_mels: 80
+  left_frames: 0
+  right_frames: 0
+  deltas: false
+  sample_rate: 16000
+  n_fft: 400
+  win_length: 25
+  hop_length: 10
+  f_min: 0
+
+
+mean_var_norm: !new:speechbrain.processing.features.InputNormalization
+    norm_type: sentence
+    std_norm: False
+
+classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
+    input_size: 2048
+    out_neurons: !ref <out_n_neurons>
+
+embedding_model: !new:speechbrain.nnet.containers.LengthsCapableSequential
+    input_shape: [null, 1, null]
+    embedding: !new:crytorch.models.components.pann.Cnn14
+        mel_bins: 80
+        emb_dim: 2048
+        norm_type: bn
+    projector: !new:crytorch.models.components.pann.SimSiamProjector
+        input_size: 2048
+        hidden_size: 2048
+        output_size: 2048
+        norm_type: bn
+
+modules:
+    compute_features: !ref <compute_features>
+    mean_var_norm: !ref <mean_var_norm>
+    embedding_model: !ref <embedding_model>
+    classifier: !ref <classifier>
+        
+label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder
+
+        
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        embedding: !ref <embedding_model.embedding>
+        projector: !ref <embedding_model.projector>
+    paths:
+        embedding: !ref <pretrained_path>/embedding_model.ckpt
+        projector: !ref <pretrained_path>/projector.ckpt
+
+

normalizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01dd629a2a24b29ad133b15930494e168114b788c4d7579ac2862e3d406e00fb
+size 1063

projector.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6918979197eb1af1eed53eb64405e08730f91fc1742707dc1bf821dbef7ec2fa
+size 33640379