Upload lm-boosted decoder

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "\u0b01", "\u0b02", "\u0b03", "\u0b05", "\u0b06", "\u0b07", "\u0b08", "\u0b09", "\u0b0a", "\u0b0f", "\u0b13", "\u0b15", "\u0b16", "\u0b17", "\u0b18", "\u0b19", "\u0b1a", "\u0b1b", "\u0b1c", "\u0b1d", "\u0b1e", "\u0b1f", "\u0b20", "\u0b21", "\u0b22", "\u0b23", "\u0b24", "\u0b25", "\u0b26", "\u0b27", "\u0b28", "\u0b2a", "\u0b2b", "\u0b2c", "\u0b2d", "\u0b2e", "\u0b2f", "\u0b30", "\u0b32", "\u0b33", "\u0b35", "\u0b36", "\u0b37", "\u0b38", "\u0b39", "\u0b3c", "\u0b3e", "\u0b3f", "\u0b40", "\u0b41", "\u0b42", "\u0b43", "\u0b47", "\u0b48", "\u0b4b", "\u0b4c", "\u0b4d", "\u0b5f", "\u0b71", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bb887ffa98f6faa0579359c1cb2545b2a0dcc298ce6e20d7f27d66ab01ecda7
+size 614947653

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

@@ -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": "|", "replace_word_delimiter_char": " ", "special_tokens_map_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": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "anuragshas/wav2vec2-xls-r-300m-or-cv9-with-lm", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}