anzorq
commited on
Commit
•
bb1e90f
1
Parent(s):
9a714cd
Upload lm-boosted decoder
Browse files- .gitattributes +1 -0
- alphabet.json +1 -0
- language_model/5gram.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +3 -0
- preprocessor_config.json +1 -1
- tokenizer_config.json +1 -1
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
language_model/unigrams.txt filter=lfs diff=lfs merge=lfs -text
|
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"labels": [" ", "\u0430", "\u044d", "\u0431", "\u0432", "\u0433", "\u0263", "\u0434", "j", "\u04e1", "\u0435", "\u0436", "\u0290", "\u0437", "\u0438", "\u0439", "\u043a", "\u049b", "q", "\u043b", "\u026c", "\u052f", "\u043c", "\u043d", "\u043e", "\u043f", "\u0525", "\u0440", "\u0441", "\u0442", "\u04ad", "\u0443", "\u0444", "\u10f6", "\u0445", "h", "\u04b3", "\u0446", "\u04b5", "\u0447", "\u0448", "\u0449", "\u0255", "\u044b", "\u04cf", "\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:be7f6914c91af0d0138cc8b5361ef3e2f8b5d7c8a1d757a30606bc2f19c1d30e
|
3 |
+
size 910297768
|
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
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:949357737f27ba3a362a68a3672dce80acc874386649e9b1aa344c5324573011
|
3 |
+
size 23697394
|
preprocessor_config.json
CHANGED
@@ -4,7 +4,7 @@
|
|
4 |
"num_mel_bins": 80,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
-
"processor_class": "
|
8 |
"return_attention_mask": true,
|
9 |
"sampling_rate": 16000,
|
10 |
"stride": 2
|
|
|
4 |
"num_mel_bins": 80,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
"return_attention_mask": true,
|
9 |
"sampling_rate": 16000,
|
10 |
"stride": 2
|
tokenizer_config.json
CHANGED
@@ -39,7 +39,7 @@
|
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
42 |
-
"processor_class": "
|
43 |
"replace_word_delimiter_char": " ",
|
44 |
"target_lang": null,
|
45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
42 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
43 |
"replace_word_delimiter_char": " ",
|
44 |
"target_lang": null,
|
45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|