Training in progress, epoch 1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u64e6\u8db3",
+    "1": "\u8db3\u4f4e",
+    "2": "\u8db3\u6253",
+    "3": "\u8db3\u6fc0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u64e6\u8db3": "0",
+    "\u8db3\u4f4e": "1",
+    "\u8db3\u6253": "2",
+    "\u8db3\u6fc0": "3"
+  },
+  "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": "4.46.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d011f8e8373814d194f6eacc9078abbe301f6815b5ddc14164aa791bd90d825d
+size 344796192

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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d53f75c182ee5906b74aefe1bd509b5f42ba01f2e786bd1c186d6db1e7a3539
+size 5432