alakxender
commited on
Commit
•
73cf6ae
1
Parent(s):
b386381
Upload lm-boosted decoder
Browse files- .gitattributes +1 -0
- alphabet.json +1 -0
- runs/Jun21_16-12-04_sv-gpu02/events.out.tfevents.1718968399.sv-gpu02.1615741.0 → language_model/5gram.bin +2 -2
- language_model/attrs.json +1 -0
- runs/Jun21_15-43-50_sv-gpu02/events.out.tfevents.1718966709.sv-gpu02.1606527.0 → language_model/unigrams.txt +2 -2
- preprocessor_config.json +1 -1
- special_tokens_map.json +28 -4
- 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": [" ", "\u060c", "\u061f", "\u0627", "\u0644", "\u0647", "\u0651", "\u0780", "\u0781", "\u0782", "\u0783", "\u0784", "\u0785", "\u0786", "\u0787", "\u0788", "\u0789", "\u078a", "\u078b", "\u078c", "\u078d", "\u078e", "\u078f", "\u0790", "\u0791", "\u0792", "\u0793", "\u0794", "\u0795", "\u0796", "\u0797", "\u0798", "\u0799", "\u079a", "\u079b", "\u079d", "\u079e", "\u079f", "\u07a0", "\u07a1", "\u07a2", "\u07a3", "\u07a4", "\u07a5", "\u07a6", "\u07a7", "\u07a8", "\u07a9", "\u07aa", "\u07ab", "\u07ac", "\u07ad", "\u07ae", "\u07af", "\u07b0", "\u2013", "\u2019", "\ufdf2", "\ufdfa", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
runs/Jun21_16-12-04_sv-gpu02/events.out.tfevents.1718968399.sv-gpu02.1615741.0 → language_model/5gram.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:013fca28020b14a717a8ee4937e1a476e7e62f371dc51223eb716bb662d99817
|
3 |
+
size 4568484585
|
language_model/attrs.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
|
runs/Jun21_15-43-50_sv-gpu02/events.out.tfevents.1718966709.sv-gpu02.1606527.0 → language_model/unigrams.txt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa9981e528a096b6aea1d577a89375bbb7fcba71ea88a83e0972d8e1c16a439f
|
3 |
+
size 63846755
|
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
|
special_tokens_map.json
CHANGED
@@ -1,6 +1,30 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "[UNK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
}
|
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",
|