Upload lm-boosted decoder

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+language_model/parl_3gram_correct.arpa filter=lfs diff=lfs merge=lfs -text

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "\u2047", "E", "N", "A", "I", "T", "O", "D", "R", " ", "L", "S", "H", "G", "M", "K", "V", "J", "W", "Z", "U", "B", "C", "P", "F", "Y", "\u00c9", "'", "X", "\u00cb", "Q", "-", "\u00ca", "\u00c0", "\u00c4", "\u00c8", "\u00cf", "\u00c2", "\u00db", "\u00d6", "\u00d4", "\u00dc", "\u00ce", "\u00c7", "\u00c6", "\u00d9", "\u0152"], "is_bpe": false}

language_model/attrs.json

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

language_model/parl_3gram_correct.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1700a7aec278895ca94b364bb93eec67532c066e00c5554a28f38b4c167c7b
+size 825928828

preprocessor_config.json

@@ -1,8 +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
 }

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": true, "word_delimiter_token": "|", "special_tokens_map_file": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-dutch/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-dutch"}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": true, "word_delimiter_token": "|", "special_tokens_map_file": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-dutch/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "Iskaj/w2v-xlsr-dutch-lm-added", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}