krishnateja
commited on
Commit
·
3da88f3
1
Parent(s):
afce653
modified files after adding lm
Browse files- alphabet.json +1 -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": [" ", "\u0c01", "\u0c02", "\u0c03", "\u0c05", "\u0c06", "\u0c07", "\u0c08", "\u0c09", "\u0c0a", "\u0c0b", "\u0c0e", "\u0c0f", "\u0c10", "\u0c12", "\u0c13", "\u0c14", "\u0c15", "\u0c16", "\u0c17", "\u0c18", "\u0c19", "\u0c1a", "\u0c1b", "\u0c1c", "\u0c1e", "\u0c1f", "\u0c20", "\u0c21", "\u0c22", "\u0c23", "\u0c24", "\u0c25", "\u0c26", "\u0c27", "\u0c28", "\u0c2a", "\u0c2b", "\u0c2c", "\u0c2d", "\u0c2e", "\u0c2f", "\u0c30", "\u0c31", "\u0c32", "\u0c33", "\u0c35", "\u0c36", "\u0c37", "\u0c38", "\u0c39", "\u0c3e", "\u0c3f", "\u0c40", "\u0c41", "\u0c42", "\u0c43", "\u0c46", "\u0c47", "\u0c48", "\u0c4a", "\u0c4b", "\u0c4c", "\u0c4d", "\u2019", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
preprocessor_config.json
CHANGED
@@ -4,6 +4,7 @@
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
|
|
7 |
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
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
@@ -1,5 +1,19 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
{
|
4 |
"content": "<s>",
|
5 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "</s>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
{
|
18 |
"content": "<s>",
|
19 |
"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": "krishnateja/wav2vec2-telugu_150",
|
6 |
"pad_token": "[PAD]",
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"special_tokens_map_file": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|