add model

CKPT.yaml

@@ -0,0 +1,5 @@
+# yamllint disable
+end-of-epoch: true
+error: 0.0
+loss: 0.058331675827503204
+unixtime: 1634475037.448386

brain.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e24193f36931b7f57932532efbdcf64971f42732383ba6808825f77db258f6
+size 28

classifier.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57270fa9ce8a76382228543c9796a559568a1c4af7c130ac1964465090762c5
+size 1075387

counter.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e629fa6598d732768f7c726b4b621285f9c3b85303900aa912017db7617d8bdb
+size 2

dataloader-TRAIN.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2d127de37b942baad06145e54b0c619a1f22327b2ebbcfbec78f5564afe39d
+size 1

embedding_model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7b47edce468057b2606011073677c8353e86a2d603dc5c6782c240d788383dc
+size 16875574

hparams_inference.yaml

@@ -0,0 +1,55 @@
+pretrained_path: ChainYo/speaker-recognition-meetup
+
+# Model parameters
+n_mels: 23
+sample_rate: 16000
+n_classes: 2
+emb_dim: 512
+
+# Feature extraction
+compute_features: !new:speechbrain.lobes.features.Fbank
+    n_mels: !ref <n_mels>
+
+# Mean and std normalization of the input features
+mean_var_norm: !new:speechbrain.processing.features.InputNormalization
+    norm_type: sentence
+    std_norm: False
+
+# To design a custom model, either just edit the simple CustomModel
+# class that's listed here, or replace this `!new` call with a line
+# pointing to a different file you've defined.
+embedding_model: !new:custom_model.Xvector
+    in_channels: !ref <n_mels>
+    activation: !name:torch.nn.LeakyReLU
+    tdnn_blocks: 5
+    tdnn_channels: [512, 512, 512, 512, 1500]
+    tdnn_kernel_sizes: [5, 3, 3, 1, 1]
+    tdnn_dilations: [1, 2, 3, 1, 1]
+    lin_neurons: !ref <emb_dim>
+
+classifier: !new:custom_model.Classifier
+    input_shape: [null, null, !ref <emb_dim>]
+    activation: !name:torch.nn.LeakyReLU
+    lin_blocks: 1
+    lin_neurons: !ref <emb_dim>
+    out_neurons: !ref <n_classes>
+
+label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder
+
+# Objects in "modules" dict will have their parameters moved to the correct
+# device, as well as having train()/eval() called on them by the Brain class.
+modules:
+    compute_features: !ref <compute_features>
+    embedding_model: !ref <embedding_model>
+    classifier: !ref <classifier>
+    mean_var_norm: !ref <mean_var_norm>
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        embedding_model: !ref <embedding_model>
+        classifier: !ref <classifier>
+        label_encoder: !ref <label_encoder>
+    paths:
+        embedding_model: !ref <pretrained_path>/embedding_model.ckpt
+        classifier: !ref <pretrained_path>/classifier.ckpt
+        label_encoder: !ref <pretrained_path>/label_encoder.txt

label_encoder.txt

@@ -0,0 +1,4 @@
+'0' => 0
+'1' => 1
+================
+'starting_index' => 0

normalizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c312ee14b371c04e4c155338b4e9f799bede9154c79f4ffd075ae4dfb94e0d30
+size 1063

optimizer.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b207a802f5a78c505cfe6398654280f8ac8696b4064d4e94dc8b0bd15a9c57
+size 35813937