Updated lm-boosted decoder
Browse files- added_tokens.json +1 -0
- alphabet.json +1 -0
- language_model/5gram.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +0 -0
- preprocessor_config.json +2 -0
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"<s>": 30, "</s>": 31}
|
alphabet.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"labels": ["i", "v", "s", "b", "w", "o", "y", "p", "d", "j", "t", "x", "k", "f", "m", "z", "q", "c", "n", "u", "e", "l", "h", "'", " ", "g", "a", "r", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
language_model/5gram.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:705062f79e4376379e5d00aefd40be36984e360d8be0bceb2ad2fb269efb2d8b
|
| 3 |
+
size 9929369
|
language_model/attrs.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
|
language_model/unigrams.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
preprocessor_config.json
CHANGED
|
@@ -1,8 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"do_normalize": true,
|
|
|
|
| 3 |
"feature_size": 1,
|
| 4 |
"padding_side": "right",
|
| 5 |
"padding_value": 0.0,
|
|
|
|
| 6 |
"return_attention_mask": true,
|
| 7 |
"sampling_rate": 16000
|
| 8 |
}
|
| 1 |
{
|
| 2 |
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
| 8 |
"return_attention_mask": true,
|
| 9 |
"sampling_rate": 16000
|
| 10 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
| 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": "|"}
|
| 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": "/root/.cache/huggingface/transformers/159be5ec81b9a474e801c4a3a8fcecf0c9644a382d3436a3896909f936bdace4.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "name_or_path": "csikasote/wav2vec2-large-xlsr-bemba", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}
|