HamzaSidhu786
commited on
Commit
•
41f8ff8
1
Parent(s):
337bd3e
Upload processor
Browse files- preprocessor_config.json +1 -0
- special_tokens_map.json +28 -4
- tokenizer_config.json +1 -0
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": false,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
"return_attention_mask": false,
|
9 |
"sampling_rate": 16000
|
10 |
}
|
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
@@ -63,6 +63,7 @@
|
|
63 |
"eos_token": "</s>",
|
64 |
"model_max_length": 1000000000000000019884624838656,
|
65 |
"pad_token": "[PAD]",
|
|
|
66 |
"replace_word_delimiter_char": " ",
|
67 |
"target_lang": null,
|
68 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
63 |
"eos_token": "</s>",
|
64 |
"model_max_length": 1000000000000000019884624838656,
|
65 |
"pad_token": "[PAD]",
|
66 |
+
"processor_class": "Wav2Vec2Processor",
|
67 |
"replace_word_delimiter_char": " ",
|
68 |
"target_lang": null,
|
69 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|