feat: Upload LM-boosted decoder

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["u", "f", "y", "\u00f8", "\u00e9", "\u00e6", "w", " ", "j", "h", "x", "g", "s", "\u00e5", "n", "v", "r", "c", "a", "b", "z", "l", "o", "p", "m", "d", "t", "k", "e", "i", "\u00f3", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98811780e72fe5d0b04d58042cc0393ef8cfd64356a02f69b988a5f2d45cbda
+size 1253607640

language_model/attrs.json

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

preprocessor_config.json

@@ -4,7 +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

@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "saattrupdan/wav2vec2-xls-r-300m-cv8-da", "processor_class": "Wav2Vec2ProcessorWithLM", "tokenizer_class": "Wav2Vec2CTCTokenizer"}