Upload lm-boosted decoder

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 51,
+  "<s>": 50
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "\\", "]", "`", "a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "v", "w", "x", "y", "z", "\u00bd", "\u00e1", "\u00e9", "\u00f3", "\u014b", "\u0161", "\u03b7", "\u0572", "\u1fce", "\u1fdd", "\u1fef", "\u2013", "\u2014", "\u201c", "\u201d", "\u201f", "\u2022", "\u2026", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d42a3caf79e582b7046b0b90c33d7a03f9244d100a57f922dbaebe3977dc123
+size 74736693

language_model/attrs.json

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

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 +1,22 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
+{
+  "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
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,14 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "Sunbird/sunbird-asr",
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--Sunbird--sunbird-asr/snapshots/086129f56ce59a6df9a00fedb3296a83e5cc79d7/special_tokens_map.json",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -1 +1,52 @@
-{"\\": 1, "]": 2, "`": 3, "a": 4, "b": 5, "c": 6, "d": 7, "e": 8, "f": 9, "g": 10, "h": 11, "i": 12, "j": 13, "k": 14, "l": 15, "m": 16, "n": 17, "o": 18, "p": 19, "q": 20, "r": 21, "s": 22, "t": 23, "u": 24, "v": 25, "w": 26, "x": 27, "y": 28, "z": 29, "½": 30, "á": 31, "é": 32, "ó": 33, "ŋ": 34, "š": 35, "η": 36, "ղ": 37, "῎": 38, "῝": 39, "`": 40, "–": 41, "—": 42, "“": 43, "”": 44, "‟": 45, "•": 46, "…": 47, "|": 0, "[UNK]": 48, "[PAD]": 49}
+{
+  "[PAD]": 49,
+  "[UNK]": 48,
+  "\\": 1,
+  "]": 2,
+  "`": 3,
+  "a": 4,
+  "b": 5,
+  "c": 6,
+  "d": 7,
+  "e": 8,
+  "f": 9,
+  "g": 10,
+  "h": 11,
+  "i": 12,
+  "j": 13,
+  "k": 14,
+  "l": 15,
+  "m": 16,
+  "n": 17,
+  "o": 18,
+  "p": 19,
+  "q": 20,
+  "r": 21,
+  "s": 22,
+  "t": 23,
+  "u": 24,
+  "v": 25,
+  "w": 26,
+  "x": 27,
+  "y": 28,
+  "z": 29,
+  "|": 0,
+  "½": 30,
+  "á": 31,
+  "é": 32,
+  "ó": 33,
+  "ŋ": 34,
+  "š": 35,
+  "η": 36,
+  "ղ": 37,
+  "῎": 38,
+  "῝": 39,
+  "`": 40,
+  "–": 41,
+  "—": 42,
+  "“": 43,
+  "”": 44,
+  "‟": 45,
+  "•": 46,
+  "…": 47
+}