Upload Wav2Vec2ForCTC

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "meandyou200175/sp2t",
-  "activation_dropout": 0.0,
+  "_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
+  "activation_dropout": 0.1,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -12,9 +12,9 @@
   "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "codevector_dim": 768,
+  "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
-  "conv_bias": true,
+  "conv_bias": false,
   "conv_dim": [
     512,
     512,
@@ -45,49 +45,41 @@
   "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
+  "do_stable_layer_norm": false,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
   "feat_extract_dropout": 0.0,
-  "feat_extract_norm": "layer",
-  "feat_proj_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "gradient_checkpointing": false,
+  "final_dropout": 0.1,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
-  "hidden_size": 1024,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.1,
-  "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",
   "num_adapter_layers": 3,
-  "num_attention_heads": 16,
+  "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": 24,
+  "num_hidden_layers": 12,
   "num_negatives": 100,
-  "output_hidden_size": 1024,
-  "pad_token_id": 90,
-  "proj_codevector_dim": 768,
+  "output_hidden_size": 768,
+  "pad_token_id": 109,
+  "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
     2,
@@ -110,8 +102,8 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.33.1",
+  "transformers_version": "4.36.0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 93,
+  "vocab_size": 110,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b0090a8efcb55b0c992f2b943fb57d45c25a894cd1ed141126ae68e2f051f98
+size 377851008