initialize repo with zho models

.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
+mean_var_norm_emb.ckpt filter=lfs diff=lfs merge=lfs -text
+classifier.ckpt filter=lfs diff=lfs merge=lfs -text
+embedding_model.ckpt filter=lfs diff=lfs merge=lfs -text

classifier.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8809181205e9143259fdc2bbe4781d7e1c62833a7460903c5f20bbc0a91b90
+size 3115

embedding_model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7439a26b4b1ce99e9f5ee9c0c3363ff113fb3354cb6732c0a52cfe8a6afacb
+size 83310835

hyperparams.yaml

@@ -0,0 +1,59 @@
+# ############################################################################
+# Model: ECAPA big for Speaker verification
+# ############################################################################
+
+# Feature parameters
+n_mels: 80
+
+# Pretrain folder (HuggingFace)
+pretrained_path: Jotanner/speechbrain-embedding-zho
+
+# Output parameters
+out_n_neurons: 3
+
+# Model params
+compute_features: !new:speechbrain.lobes.features.Fbank
+    n_mels: !ref <n_mels>
+
+mean_var_norm: !new:speechbrain.processing.features.InputNormalization
+    norm_type: sentence
+    std_norm: False
+
+embedding_model: !new:speechbrain.lobes.models.ECAPA_TDNN.ECAPA_TDNN
+    input_size: !ref <n_mels>
+    channels: [1024, 1024, 1024, 1024, 3072]
+    kernel_sizes: [5, 3, 3, 3, 1]
+    dilations: [1, 2, 3, 4, 1]
+    attention_channels: 128
+    lin_neurons: 192
+
+classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
+    input_size: 192
+    out_neurons: !ref <out_n_neurons>
+
+mean_var_norm_emb: !new:speechbrain.processing.features.InputNormalization
+    norm_type: global
+    std_norm: False
+
+modules:
+    compute_features: !ref <compute_features>
+    mean_var_norm: !ref <mean_var_norm>
+    embedding_model: !ref <embedding_model>
+    mean_var_norm_emb: !ref <mean_var_norm_emb>
+    classifier: !ref <classifier>
+        
+#label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder
+
+        
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        embedding_model: !ref <embedding_model>
+        mean_var_norm_emb: !ref <mean_var_norm_emb>
+        classifier: !ref <classifier>
+        #label_encoder: !ref <label_encoder>
+    paths:
+        embedding_model: !ref <pretrained_path>/embedding_model.ckpt
+        mean_var_norm_emb: !ref <pretrained_path>/mean_var_norm_emb.ckpt
+        classifier: !ref <pretrained_path>/classifier.ckpt
+        #label_encoder: !ref <pretrained_path>/label_encoder.txt
+

mean_var_norm_emb.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad6ae225d4c7d7aaba42b4066292947feef1a2de0c8637949701e7613e837d7
+size 1383