Training in progress, epoch 0

config.json

@@ -1,13 +1,12 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
+  "_name_or_path": "microsoft/WavLM-base",
   "activation_dropout": 0.0,
-  "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
   "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2ForSequenceClassification"
+    "WavLMForSequenceClassification"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 1,
@@ -91,7 +90,7 @@
     "pay_bill": "13"
   },
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.05,
   "mask_channel_length": 10,
   "mask_channel_min_space": 1,
   "mask_channel_other": 0.0,
@@ -106,15 +105,18 @@
   "mask_time_other": 0.0,
   "mask_time_prob": 0.05,
   "mask_time_selection": "static",
-  "model_type": "wav2vec2",
+  "max_bucket_distance": 800,
+  "model_type": "wavlm",
   "no_mask_channel_overlap": false,
   "no_mask_time_overlap": false,
   "num_adapter_layers": 3,
   "num_attention_heads": 12,
+  "num_buckets": 320,
   "num_codevector_groups": 2,
   "num_codevectors_per_group": 320,
   "num_conv_pos_embedding_groups": 16,
   "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
   "num_feat_extract_layers": 7,
   "num_hidden_layers": 12,
   "num_negatives": 100,
@@ -142,6 +144,7 @@
     1,
     1
   ],
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.36.0",
   "use_weighted_layer_sum": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488524485195e519ed29855ff06c718c68e257cb25ed71f6132a64f9122c0b8c
-size 378314704
+oid sha256:bc4d3c1db8a26504d88d1d60222d863ab8d753936be6f74b1cca6b59a7af9c7d
+size 378359600

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,
-  "return_attention_mask": false,
+  "return_attention_mask": true,
   "sampling_rate": 16000
 }

runs/Dec12_16-41-09_449c93594040/events.out.tfevents.1702399269.449c93594040.4848.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aec9124e69b63db11d5fac508944d7c9639b820596a915dedd36c326c996b80
-size 9313
+oid sha256:3ca9c7b93e7e702c6d81703e10983a4af5d1b7f96bd1ec30e0c26f117b420bea
+size 10132

runs/Dec12_16-47-28_449c93594040/events.out.tfevents.1702399649.449c93594040.4848.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830eb9b93a6cda1a078ba25136638071d0076d44898db5bb2f9cfd905081755b
+size 7209

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d86a768c671f475a5e9e93e9d5f7407b3026a6d6f51bebf31ff5176d93b471c5
+oid sha256:10f8a61b1461bc2266a58aa7bf2e0157f8354f8746bba95777ccae298fc32313
 size 4728