Training in progress, step 200

config.json

@@ -1,19 +1,13 @@
 {
-  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "_name_or_path": "omarxadel/hubert-large-arabic-egyptian",
   "activation_dropout": 0.0,
-  "adapter_attn_dim": null,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2ForCTC"
+    "HubertForCTC"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 768,
-  "contrastive_logits_temperature": 0.1,
   "conv_bias": true,
   "conv_dim": [
     512,
@@ -44,23 +38,22 @@
   ],
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": true,
-  "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
   "feat_extract_norm": "layer",
   "feat_proj_dropout": 0.0,
-  "feat_quantizer_dropout": 0.0,
+  "feat_proj_layer_norm": true,
   "final_dropout": 0.0,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
+  "hidden_dropout": 0.0,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
+  "layerdrop": 0.0,
   "mask_channel_length": 10,
   "mask_channel_min_space": 1,
   "mask_channel_other": 0.0,
@@ -75,43 +68,16 @@
   "mask_time_other": 0.0,
   "mask_time_prob": 0.05,
   "mask_time_selection": "static",
-  "model_type": "wav2vec2",
-  "num_adapter_layers": 3,
+  "model_type": "hubert",
   "num_attention_heads": 16,
-  "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": 24,
-  "num_negatives": 100,
-  "output_hidden_size": 1024,
   "pad_token_id": 109,
-  "proj_codevector_dim": 768,
-  "tdnn_dilation": [
-    1,
-    2,
-    3,
-    1,
-    1
-  ],
-  "tdnn_dim": [
-    512,
-    512,
-    512,
-    512,
-    1500
-  ],
-  "tdnn_kernel": [
-    5,
-    3,
-    3,
-    1,
-    1
-  ],
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.37.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 112,
-  "xvector_output_dim": 512
+  "vocab_size": 112
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634294931b6f9cc604f229d6f66dedecd91ab599fe3d4256d17ede9931b75f21
-size 1267695008
+oid sha256:d4d833c3bab5cde51d816cf96c8ac2fc05a265a28e440de827a7847c3ff1d5df
+size 1267694072

preprocessor_config.json

@@ -4,7 +4,6 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
-  "processor_class": "Wav2Vec2Processor",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

runs/Dec27_18-12-36_e130e727b7e8/events.out.tfevents.1703700960.e130e727b7e8.2076.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93374a52d9b2f8d69e57f40230f0af40d2ec4b09b1ad94e8132c92fb32918503
+size 17932

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5e7370a071874382de2373aa1ebb883205aacbbdc28cf03dcba2204f4bd37d7
+oid sha256:23f6dfe6ae20e95915e4d3e13d589b74ca187f3cb20395c322743e471387f738
 size 4664