Upload lm-boosted decoder

.gitattributes

@@ -32,3 +32,4 @@ 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
+language_model/voctext.arpa filter=lfs diff=lfs merge=lfs -text

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "\u2047", " ", "-", "\u0621", "\u0622", "\u0623", "\u0624", "\u0625", "\u0626", "\u0627", "\u0628", "\u0629", "\u062a", "\u062b", "\u062c", "\u062d", "\u062e", "\u062f", "\u0630", "\u0631", "\u0632", "\u0633", "\u0634", "\u0635", "\u0636", "\u0637", "\u0638", "\u0639", "\u063a", "\u0640", "\u0641", "\u0642", "\u0643", "\u0644", "\u0645", "\u0646", "\u0647", "\u0648", "\u0649", "\u064a", "\u064b", "\u064c", "\u064d", "\u064e", "\u064f", "\u0650", "\u0651", "\u0652"], "is_bpe": false}

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/voctext.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8422712cac378f8e79e90baa707b71d88daabfea40beed51c719a67ad27a1d45
+size 16146401

preprocessor_config.json

@@ -4,7 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
-  "processor_class": "Wav2Vec2Processor",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

tokenizer_config.json

@@ -3,9 +3,9 @@
   "do_lower_case": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "my_model9/",
+  "name_or_path": "anzhir2011/wav2vec2_ar_anz2",
   "pad_token": "<pad>",
-  "processor_class": "Wav2Vec2Processor",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
   "special_tokens_map_file": "/root/.cache/huggingface/hub/models--jonatasgrosman--wav2vec2-large-xlsr-53-arabic/snapshots/af46c2d8531b8dcbb5e23b952f739b372c2e5d2d/special_tokens_map.json",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",