Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "disgust",
+    "2": "enthusiasm",
+    "3": "fear",
+    "4": "happiness",
+    "5": "neutral",
+    "6": "sadness"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anger": 0,
+    "disgust": 1,
+    "enthusiasm": 2,
+    "fear": 3,
+    "happiness": 4,
+    "neutral": 5,
+    "sadness": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 1024,
+  "model_type": "audio-spectrogram-transformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_mel_bins": 128,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "time_stride": 10,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0"
+}

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "ASTFeatureExtractor",
+  "feature_size": 1,
+  "max_length": 1024,
+  "mean": -4.2677393,
+  "num_mel_bins": 128,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "std": 4.5689974
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfddb4ffa62be40560af6233e3d8448dc97532f1688e1bfe5c5d6de460a0209
+size 344850809

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89815cd70770adc0b0683c491706a9b121ae52b5c91b25ad0196e54461cab4d6
+size 3579