Training in progress, epoch 1

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "asapp/sew-d-tiny-100k-ft-ls100h",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SEWDForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    64,
+    128,
+    128,
+    128,
+    128,
+    256,
+    256,
+    256,
+    256,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    1,
+    3,
+    1,
+    3,
+    1,
+    3,
+    1,
+    2,
+    1,
+    2,
+    1
+  ],
+  "conv_stride": [
+    5,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_layer_norm_eps": 1e-05,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu_python",
+  "hidden_dropout": 0.0,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "owl",
+    "1": "not_owl"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "not_owl": 1,
+    "owl": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "layerdrop": 0.1,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.5,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.65,
+  "max_position_embeddings": 512,
+  "model_type": "sew-d",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 6,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 31,
+  "num_feat_extract_layers": 13,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "squeeze_factor": 2,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c771a00ff3c0fede8396444f06b32030f3f376fe4cc957eeaf5c4bc97d1f1f
+size 96884500

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

runs/Mar01_22-15-48_209-20-156-194/events.out.tfevents.1709331349.209-20-156-194.3359.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a93547fe470561cb46bef59aa110d350477bb5b211395b7e07c028ce06c7d0
+size 7248

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b3d570acb65e07165e165f82c50f938055356a9011af8fc50c5f29e564bf59
+size 4920