Aditya3107
commited on
Commit
•
a819821
1
Parent(s):
fe87c67
Upload Spanish Wav2Vec2 XLS-R 300M decoder with lm
Browse files- alphabet.json +1 -0
- language_model/4gram_correct.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +0 -0
- preprocessor_config.json +1 -0
- special_tokens_map.json +14 -0
- tokenizer_config.json +2 -1
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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", "\u00e1", "\u00e9", "\u00ed", "\u00f1", "\u00f3", "\u00fa", "\u00fc", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
language_model/4gram_correct.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b8242a372633f08cac675f3d0ce638509392cea3bb8cec5eafdad3569f2b573
|
3 |
+
size 3594701740
|
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
@@ -4,6 +4,7 @@
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0,
|
|
|
7 |
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
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 |
}
|
special_tokens_map.json
CHANGED
@@ -21,6 +21,20 @@
|
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
{
|
25 |
"content": "</s>",
|
26 |
"lstrip": false,
|
|
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
},
|
24 |
+
{
|
25 |
+
"content": "</s>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "<s>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": true,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
{
|
39 |
"content": "</s>",
|
40 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -2,8 +2,9 @@
|
|
2 |
"bos_token": "<s>",
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
5 |
-
"name_or_path": "
|
6 |
"pad_token": "[PAD]",
|
|
|
7 |
"replace_word_delimiter_char": " ",
|
8 |
"special_tokens_map_file": null,
|
9 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
5 |
+
"name_or_path": "/vol/tensusers4/aparikh/Generic_Wav2vec2_models/Spanish_wav2vec2/wav2vec2-common_voice-es-xls-r-300m",
|
6 |
"pad_token": "[PAD]",
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"special_tokens_map_file": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|