Upload Spanish Wav2Vec2 XLS-R 300M decoder with lm

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", "\u00e1", "\u00e9", "\u00ed", "\u00f1", "\u00f3", "\u00fa", "\u00fc", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/4gram_correct.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8242a372633f08cac675f3d0ce638509392cea3bb8cec5eafdad3569f2b573
+size 3594701740

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,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

special_tokens_map.json

@@ -21,6 +21,20 @@
       "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

@@ -2,8 +2,9 @@
   "bos_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
-  "name_or_path": "./wav2vec2-common_voice-es-xls-r-300m",
+  "name_or_path": "/vol/tensusers4/aparikh/Generic_Wav2vec2_models/Spanish_wav2vec2/wav2vec2-common_voice-es-xls-r-300m",
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
   "special_tokens_map_file": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",