add model

README.md

@@ -0,0 +1,30 @@
+---
+license: cc-by-4.0
+metrics:
+  - accuracy
+  - f1
+  - uar
+pipeline_tag: audio-classification
+tags:
+  - audio
+  - audio-classification
+  - speech-emotion-recognition
+  - autrainer
+library_name: autrainer
+model-index:
+  - name: dcase-2020-t1a-cnn14-32k-t
+    results:
+      - task:
+          type: audio-classification
+          name: Speech Emotion Recognition
+        metrics:
+          - type: accuracy
+            name: Accuracy
+            value: 0.6166793457588436
+          - type: f1
+            name: F1
+            value: 0.5716599171523286
+          - type: uar
+            name: Unweighted Average Recall
+            value: 0.6499883154795764
+---

_best/dev.yaml

@@ -0,0 +1,9 @@
+accuracy:
+  all: 0.5984346298218992
+uar:
+  all: 0.630735177103743
+f1:
+  all: 0.5791954276271887
+dev_loss:
+  all: 0.9837130961151764
+iteration: 4

_test/test_holistic.yaml

@@ -0,0 +1,8 @@
+accuracy:
+  all: 0.6166793457588436
+uar:
+  all: 0.6499883154795764
+f1:
+  all: 0.5716599171523286
+loss:
+  all: 0.914642338334034

file_handler.yaml

@@ -0,0 +1,2 @@
+$autrainer.datasets.utils.file_handlers.AudioFileHandler==0.4.0:
+  target_sample_rate: null

inference_transform.yaml

@@ -0,0 +1,12 @@
+$autrainer.transforms.smart_compose.SmartCompose==0.4.0:
+  transforms:
+  - $autrainer.transforms.specific_transforms.Expand==0.4.0:
+      size: 48000
+      method: pad
+      axis: -1
+      order: -85
+  - $autrainer.transforms.specific_transforms.FeatureExtractor==0.4.0:
+      fe_type: W2V2
+      fe_transfer: audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim
+      sampling_rate: 16000
+      order: -80

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae40f66ab797c5840326e268c5145af234e22cf37582cc364cde4a06f04ca5f9
+size 659338874

model.yaml

@@ -0,0 +1,7 @@
+$autrainer.models.w2v2.W2V2FFNN==0.4.0:
+  output_dim: 4
+  model_name: audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim
+  freeze_extractor: true
+  hidden_size: 512
+  num_layers: 2
+  dropout: 0.5

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f41960597a39d7adf831a04678b998bf4c60f170c4b53cd9f418fab918273eab
+size 3448

preprocess_file_handler.yaml

@@ -0,0 +1,2 @@
+$autrainer.datasets.utils.file_handlers.AudioFileHandler==0.4.0:
+  target_sample_rate: null

preprocess_pipeline.yaml

@@ -0,0 +1,2 @@
+$autrainer.transforms.smart_compose.SmartCompose==0.4.0:
+  transforms: []

target_transform.yaml

@@ -0,0 +1,6 @@
+$autrainer.datasets.utils.target_transforms.label_encoder.LabelEncoder==0.4.0:
+  labels:
+  - A
+  - H
+  - N
+  - S