Upload new lm-boosted decoder

.gitattributes

@@ -29,3 +29,4 @@ 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/unigrams.txt filter=lfs diff=lfs merge=lfs -text

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "!", "'", ",", "-", ".", ":", ";", "=", "?", "\u0964", "\u0981", "\u0982", "\u0983", "\u0985", "\u0986", "\u0987", "\u0988", "\u0989", "\u098a", "\u098b", "\u098f", "\u0990", "\u0993", "\u0994", "\u0995", "\u0996", "\u0997", "\u0998", "\u0999", "\u099a", "\u099b", "\u099c", "\u099d", "\u099e", "\u099f", "\u09a0", "\u09a1", "\u09a2", "\u09a3", "\u09a4", "\u09a5", "\u09a6", "\u09a7", "\u09a8", "\u09aa", "\u09ab", "\u09ac", "\u09ad", "\u09ae", "\u09af", "\u09b0", "\u09b2", "\u09b6", "\u09b7", "\u09b8", "\u09b9", "\u09be", "\u09bf", "\u09c0", "\u09c1", "\u09c2", "\u09c3", "\u09c7", "\u09c8", "\u09cb", "\u09cc", "\u09cd", "\u09ce", "\u09dc", "\u09dd", "\u09df", "\u09e6", "\u09e7", "\u09e8", "\u09e9", "\u09ea", "\u09eb", "\u09ec", "\u09ed", "\u09ee", "\u09ef", "\u200d", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/6gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854863b2d7ef86d1dab687cbd0894c4ab048358de11058e3e9c2f47b5fca6170
+size 8319130332

language_model/attrs.json

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

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80a16e5bcddb0b96faa8311173b9595b5dcb6c87e9d8bcc139fe0ef88cc89c8
+size 106370349

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

special_tokens_map.json

@@ -1,5 +1,19 @@
 {
   "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
     {
       "content": "<s>",
       "lstrip": false,

tokenizer_config.json

@@ -2,8 +2,9 @@
   "bos_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
-  "name_or_path": "./",
+  "name_or_path": "MBMMurad/wav2vec2_murad_with_some_new_data",
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
   "special_tokens_map_file": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",