Training in progress, epoch 0

config.json

@@ -1,60 +1,12 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
-  "activation_dropout": 0.0,
-  "adapter_attn_dim": null,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
-  "apply_spec_augment": true,
+  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
   "architectures": [
-    "Wav2Vec2ForSequenceClassification"
+    "ASTForAudioClassification"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 1,
-  "classifier_proj_size": 256,
-  "codevector_dim": 256,
-  "contrastive_logits_temperature": 0.1,
-  "conv_bias": false,
-  "conv_dim": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
-  "conv_kernel": [
-    10,
-    3,
-    3,
-    3,
-    3,
-    2,
-    2
-  ],
-  "conv_stride": [
-    5,
-    2,
-    2,
-    2,
-    2,
-    2,
-    2
-  ],
-  "ctc_loss_reduction": "sum",
-  "ctc_zero_infinity": false,
-  "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": false,
-  "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
     "0": 0,
@@ -134,61 +86,16 @@
     "34": "34",
     "35": "35"
   },
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "mask_channel_length": 10,
-  "mask_channel_min_space": 1,
-  "mask_channel_other": 0.0,
-  "mask_channel_prob": 0.0,
-  "mask_channel_selection": "static",
-  "mask_feature_length": 10,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.0,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_min_space": 1,
-  "mask_time_other": 0.0,
-  "mask_time_prob": 0.05,
-  "mask_time_selection": "static",
-  "model_type": "wav2vec2",
-  "no_mask_channel_overlap": false,
-  "no_mask_time_overlap": false,
-  "num_adapter_layers": 3,
+  "layer_norm_eps": 1e-12,
+  "max_length": 1024,
+  "model_type": "audio-spectrogram-transformer",
   "num_attention_heads": 12,
-  "num_codevector_groups": 2,
-  "num_codevectors_per_group": 320,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
   "num_hidden_layers": 12,
-  "num_negatives": 100,
-  "output_hidden_size": 768,
-  "pad_token_id": 0,
-  "proj_codevector_dim": 256,
-  "tdnn_dilation": [
-    1,
-    2,
-    3,
-    1,
-    1
-  ],
-  "tdnn_dim": [
-    512,
-    512,
-    512,
-    512,
-    1500
-  ],
-  "tdnn_kernel": [
-    5,
-    3,
-    3,
-    1,
-    1
-  ],
+  "num_mel_bins": 128,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "time_stride": 10,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32,
-  "xvector_output_dim": 512
+  "transformers_version": "4.34.1"
 }

preprocessor_config.json

@@ -1,9 +1,13 @@
 {
   "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "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
+  "sampling_rate": 16000,
+  "std": 4.5689974
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801ba807e375a2dcdd3fb6d83eb415934348cab7e4caa2882a5ffbd33eb67b98
-size 378385894
+oid sha256:0623afa930a78a8b5f43461ca3c24f592a657c5ce70de8a45cea43ca37951f47
+size 344940470

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b127206d10b39a4a825e242407ff6e401bd3a2c070bf7925f9d004a49268969
+oid sha256:b40453a5690a0279fb85b53d7e4191affb91f0b65940218236832de7ee0cdcde
 size 4536