Training in progress, epoch 1

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-speech-commands-v2",
   "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": "onboard",
@@ -70,61 +22,16 @@
     "return": "2",
     "unknown": "3"
   },
-  "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": 128,
+  "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": "4.38.1",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32,
-  "xvector_output_dim": 512
+  "transformers_version": "4.38.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0b163bd8a3ab5a7e8d0794e086e78de1f37e93f9e67c085e2535e99da29d74d
-size 378304424
+oid sha256:a80324a692b6c11a88514e69c1fddae8d697625f17ef304584bc0672882c6639
+size 341515296

preprocessor_config.json

@@ -1,9 +1,13 @@
 {
   "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "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
+  "sampling_rate": 16000,
+  "std": 5.5654526
 }

runs/Apr15_10-30-24_voice-ai-transformer/events.out.tfevents.1713177065.voice-ai-transformer.69074.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ea44906e4839065ef5e02ccf61e76d608a051dc735ac48b95a35655a0e905a
+size 4719

runs/Apr15_12-01-24_voice-ai-transformer/events.out.tfevents.1713182525.voice-ai-transformer.136042.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593de290c5d6f45bd40e3bd092d25a9a680b89f3d8909c125c80c9b411f19366
+size 4717

runs/Apr15_12-31-27_voice-ai-transformer/events.out.tfevents.1713184293.voice-ai-transformer.215553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1383ea3878524082dbc4dd11c30daf660a0df0baac5512f1a33fe9339e8700f7
+size 4717

runs/Apr15_13-54-56_voice-ai-transformer/events.out.tfevents.1713189302.voice-ai-transformer.282817.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fad1af2690fc313d92c0abb5f842c22f04bf86d77f91699bb37afb106ed0259
+size 10265

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88e161f66768b25ae4ebd206e69408d0d3a1268ddec6caf408a8862da9e5094
+oid sha256:5ccb13220a3671b782b6e2dcb8a97ae212fe9433f34ab9c53c56f5ae5312c574
 size 4920