Training in progress, epoch 0

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "MIT/ast-finetuned-speech-commands-v2",
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "disp",
+    "1": "fdisp",
+    "2": "hfdisp",
+    "3": "laryngitis",
+    "4": "psydisp",
+    "5": "rekparese"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "disp": "0",
+    "fdisp": "1",
+    "hfdisp": "2",
+    "laryngitis": "3",
+    "psydisp": "4",
+    "rekparese": "5"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 128,
+  "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": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10682bd541d69803fadd34a12847af84a670bae441c9b618f5236cb78d304637
+size 341521448

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "ASTFeatureExtractor",
+  "feature_size": 1,
+  "max_length": 128,
+  "mean": -6.845978,
+  "num_mel_bins": 128,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "std": 5.5654526
+}

runs/Sep04_10-56-44_LAPTOP-GK9KSOG2/events.out.tfevents.1725440208.LAPTOP-GK9KSOG2.20576.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3643cf1168fcac77fb7d8c70ddf98b266dbedf3d5b85e8b98dea6de4b8026ea
+size 10851

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87cac8f2ae0e675484c5725da4edb0dab2537dfce59c478ece200d6d33c4d101
+size 5304