up

config.json

@@ -1,6 +1,5 @@
 {
   "activation_dropout": 0.0,
-  "apply_spec_augment": true,
   "architectures": [
     "UniSpeechSatForPreTraining"
   ],
@@ -8,7 +7,6 @@
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 768,
-  "contrastive_logits_temperature": 0.1,
   "conv_bias": true,
   "conv_dim": [
     512,
@@ -37,9 +35,6 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "sum",
-  "ctc_zero_infinity": false,
-  "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": true,
   "eos_token_id": 2,
   "feat_extract_activation": "gelu",
@@ -48,7 +43,6 @@
   "feat_proj_dropout": 0.1,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout": 0.1,
   "hidden_size": 1024,
@@ -56,18 +50,10 @@
   "intermediate_size": 4096,
   "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_prob": 0.0,
   "mask_time_length": 10,
-  "mask_time_min_space": 1,
-  "mask_time_other": 0.0,
   "mask_time_prob": 0.075,
-  "mask_time_selection": "static",
   "model_type": "unispeech-sat",
   "num_attention_heads": 16,
   "num_clusters": 504,
@@ -80,9 +66,9 @@
   "num_negatives": 100,
   "pad_token_id": 0,
   "proj_codevector_dim": 768,
-  "replace_prob": 0.5,
   "torch_dtype": "float32",
   "transformers_version": "4.12.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 256
+  "vocab_size": 256,
+	"tokenizer_class": "Wav2Vec2CTCTokenizer"
 }

preprocessor_config.json

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