Upload Wav2Vec2ForCTC

config.json

@@ -1,6 +1,6 @@
 {
-  "_name_or_path": "/scratch/project_462000187/home/getmanya/python_env_exp/wav2vec2_base/wav2vec2_base_cont_lp_512gpus_lr0006_15336steps_hf",
-  "activation_dropout": 0.0,
+  "_name_or_path": "/scratch/project_462000187/home/getmanya/python_env_exp/interspeech_2024_best_models/wav2vec2_base_cont_pt/FT/wav2vec2_base_cont_lp_512gpus_lr0006_15336steps_ft_full_hf",
+  "activation_dropout": 0.1,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -9,7 +9,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 256,
@@ -42,7 +42,7 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "mean",
+  "ctc_loss_reduction": "sum",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": false,
@@ -51,14 +51,14 @@
   "feat_extract_norm": "group",
   "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
+  "final_dropout": 0.1,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
+  "hidden_dropout": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.1,
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
@@ -102,6 +102,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.36.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 35,
+  "vocab_size": 34,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c0b1db2b907bf16011b95bb1634bb405e912516375a127a8259d681a8d4ef8
-size 377620300
+oid sha256:7f7d8843a4261be8c9296f811650ba87e4c5fbb1f94edcfa79de4005d519127b
+size 377617224