commit files to HF hub

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "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", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b15c479141d06a5fab8b50378663dd55aecb5f38a028c9a6777ee52307793c
+size 3921919482

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.0, "unk_score_offset": -10.0, "score_boundary": true}

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "ignore_mismatched_sizes": true,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -1,5 +1,33 @@
 {
   "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,
+      "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

@@ -2,11 +2,13 @@
   "bos_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
-  "name_or_path": "./",
+  "name_or_path": "/content/drive/MyDrive/CAAD/dataset/large_tokenizer-lv60/",
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
   "special_tokens_map_file": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_file": null,
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"
 }