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/unigrams.txt filter=lfs diff=lfs merge=lfs -text

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "\u0a02", "\u0a05", "\u0a06", "\u0a07", "\u0a08", "\u0a09", "\u0a0a", "\u0a0f", "\u0a10", "\u0a13", "\u0a14", "\u0a15", "\u0a16", "\u0a17", "\u0a18", "\u0a1a", "\u0a1b", "\u0a1c", "\u0a1d", "\u0a1f", "\u0a20", "\u0a21", "\u0a22", "\u0a23", "\u0a24", "\u0a25", "\u0a26", "\u0a27", "\u0a28", "\u0a2a", "\u0a2b", "\u0a2c", "\u0a2d", "\u0a2e", "\u0a2f", "\u0a30", "\u0a32", "\u0a33", "\u0a35", "\u0a36", "\u0a38", "\u0a39", "\u0a3c", "\u0a3e", "\u0a3f", "\u0a40", "\u0a41", "\u0a42", "\u0a47", "\u0a48", "\u0a4b", "\u0a4c", "\u0a4d", "\u0a59", "\u0a5a", "\u0a5b", "\u0a5c", "\u0a5e", "\u0a70", "\u0a71", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295d80f5abfe07d3a83716f44bd4f5a85569f1fb9a90a2e845fcd39022922b5a
+size 2582534323

language_model/attrs.json

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

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985e5d576dca1f8550a1a1bd9840262dcaa93efcc10a760ba6a6f077d3428cc8
+size 19200861

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

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"}
+{"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": "anuragshas/wav2vec2-large-xls-r-300m-pa-in", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}