Upload lm-boosted decoder

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "\u2047", " ", "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", "\u00e0", "\u00e1", "\u00e2", "\u00e4", "\u00e8", "\u00e9", "\u00ea", "\u00eb", "\u00ef", "\u00f4", "\u00fa", "\u00fb", "\u00fc"], "is_bpe": false}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d8f63447ae7817c2f05fc4d0adceb679dd07363242934ab32828edef338b8d
+size 7441214

language_model/attrs.json

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

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "name_or_path": "wietsedv/wav2vec2-large-xlsr-53-frisian",
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/57517e892f3757c01994942cd4436806e336aaaceb0f6177eca8b65599fa71d9.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,46 @@
+{
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "a": 6,
+  "b": 7,
+  "c": 8,
+  "d": 9,
+  "e": 10,
+  "f": 11,
+  "g": 12,
+  "h": 13,
+  "i": 14,
+  "j": 15,
+  "k": 16,
+  "l": 17,
+  "m": 18,
+  "n": 19,
+  "o": 20,
+  "p": 21,
+  "q": 22,
+  "r": 23,
+  "s": 24,
+  "t": 25,
+  "u": 26,
+  "v": 27,
+  "w": 28,
+  "x": 29,
+  "y": 30,
+  "z": 31,
+  "|": 4,
+  "à": 32,
+  "á": 33,
+  "â": 34,
+  "ä": 35,
+  "è": 36,
+  "é": 37,
+  "ê": 38,
+  "ë": 39,
+  "ï": 40,
+  "ô": 41,
+  "ú": 42,
+  "û": 43,
+  "ü": 44
+}