Uploading the model files for PL-BERT for Persian

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+step_305000_loss=1.4_val_loss=0.35_token_loss=1.2.t7 filter=lfs diff=lfs merge=lfs -text

config_fa.yml

@@ -0,0 +1,30 @@
+log_dir: "Checkpoint_fa"
+mixed_precision: "fp16"
+data_folder: "wikipedia_fa.processed"
+batch_size: 48
+save_interval: 5000
+log_interval: 10
+num_process: 1 # number of GPUs
+num_steps: 2000000
+
+dataset_params:
+    tokenizer: "HooshvareLab/bert-base-parsbert-uncased"
+    token_separator: " " # token used for phoneme separator (space)
+    token_mask: "M" # token used for phoneme mask (M)
+    word_separator: 3039 # token used for word separator (<formula>)
+    token_maps: "token_fa_maps.pkl" # token map path
+    
+    max_mel_length: 512 # max phoneme length
+    
+    word_mask_prob: 0.15 # probability to mask the entire word
+    phoneme_mask_prob: 0.1 # probability to mask each phoneme
+    replace_prob: 0.2 # probablity to replace phonemes
+    
+model_params:
+    vocab_size: 178
+    hidden_size: 768
+    num_attention_heads: 12
+    intermediate_size: 2048
+    max_position_embeddings: 512
+    num_hidden_layers: 12
+    dropout: 0.1

step_305000_loss=1.4_val_loss=0.35_token_loss=1.2.t7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b1af0d1985e967acce8691ae4a04bb1e44f881fc6fc9c30321aacdbf1a32bd
+size 764258718

token_fa_maps.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6751f277ecad951f541adbed21d6d92a38e5307c5a2b935714a59abb214b89c
+size 2228273

wikipedia_fa.processed.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b898fe466fba4c6d4b8511d0aae8aed42d894038a683dae24bed350646afe874
+size 171694383