Training in progress, epoch 0

config.json

@@ -1,19 +1,13 @@
 {
-  "_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": "ntu-spml/distilhubert",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": false,
   "architectures": [
-    "Wav2Vec2ForSequenceClassification"
+    "HubertForSequenceClassification"
   ],
   "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,
@@ -44,15 +38,13 @@
   ],
   "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,
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": false,
   "final_dropout": 0.0,
-  "freeze_feat_extract_train": true,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
   "hidden_size": 768,
@@ -72,59 +64,21 @@
   },
   "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,
+  "model_type": "hubert",
   "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,
+  "num_hidden_layers": 2,
   "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
-  ],
   "torch_dtype": "float32",
   "transformers_version": "4.38.1",
   "use_weighted_layer_sum": false,
-  "vocab_size": 32,
-  "xvector_output_dim": 512
+  "vocab_size": 32
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0753d57ccb0b05968cb542ba0ae42e5ea9d24654eba31bb8b25cdbb7ce6a3d97
-size 378304424
+oid sha256:6bfd76eedc5bef22517b00becdf99502e8d32144fc602cd2aeb8a381ec2276d6
+size 94765560

preprocessor_config.json

@@ -1,9 +1,9 @@
 {
-  "do_normalize": true,
+  "do_normalize": false,
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",
-  "padding_value": 0.0,
+  "padding_value": 0,
   "return_attention_mask": false,
   "sampling_rate": 16000
 }

runs/Feb28_13-55-54_voice-ai-transformer/events.out.tfevents.1709128560.voice-ai-transformer.1130470.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b21732b2ffe66c7c120e03d1180068df4338213ae8c37268e056ec7cc55126c
+size 5832

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9f0964ec7f6094821e01e093e19c2e5a5142381f0a0daff5f83c71b159b5bb
+oid sha256:45101e17493052635fcbcd94e78683472998affb5318bdfdfa4f90ebbff352aa
 size 4920