Revert "Upload lm-boosted decoder"
Browse filesThis reverts commit b1572f2dea0fa3ddd4a8186df53621fa703ddaeb.
- alphabet.json +0 -1
- language_model/5gram.bin +0 -0
- language_model/attrs.json +0 -1
- language_model/unigrams.txt +0 -0
- preprocessor_config.json +0 -1
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
alphabet.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"labels": [" ", "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", "\u00e2", "\u00ee", "\u0103", "\u0219", "\u021b", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
|
|
|
|
|
language_model/5gram.bin
DELETED
|
File without changes
|
language_model/attrs.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
|
|
|
|
|
|
language_model/unigrams.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
CHANGED
|
@@ -4,7 +4,6 @@
|
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0,
|
| 7 |
-
"processor_class": "Wav2Vec2ProcessorWithLM",
|
| 8 |
"return_attention_mask": true,
|
| 9 |
"sampling_rate": 16000
|
| 10 |
}
|
|
|
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0,
|
|
|
|
| 7 |
"return_attention_mask": true,
|
| 8 |
"sampling_rate": 16000
|
| 9 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1 +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}
|
|
|
|
| 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}]}
|
tokenizer_config.json
CHANGED
|
@@ -1 +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": "gigant/wav2vec2-ro-300m_01", "tokenizer_class": "Wav2Vec2CTCTokenizer"
|
|
|
|
| 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": "./gigant/wav2vec2-ro-300m_01", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|