Upload processor
Browse files- added_tokens.json +4 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +16 -0
- tokenizer_config.json +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 30,
|
3 |
+
"<s>": 29
|
4 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
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
@@ -1,4 +1,20 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
"pad_token": "[PAD]",
|
|
|
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 |
"bos_token": "<s>",
|
19 |
"eos_token": "</s>",
|
20 |
"pad_token": "[PAD]",
|
tokenizer_config.json
CHANGED
@@ -2,8 +2,11 @@
|
|
2 |
"bos_token": "<s>",
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
|
|
5 |
"pad_token": "[PAD]",
|
|
|
6 |
"replace_word_delimiter_char": " ",
|
|
|
7 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
8 |
"unk_token": "[UNK]",
|
9 |
"word_delimiter_token": "|"
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
5 |
+
"name_or_path": "/content/drive/MyDrive/data/wav2vec2-base-Med-ASR/checkpoint-9000",
|
6 |
"pad_token": "[PAD]",
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
+
"special_tokens_map_file": "/content/drive/MyDrive/data/wav2vec2-base-Med-ASR/checkpoint-9000/special_tokens_map.json",
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
11 |
"unk_token": "[UNK]",
|
12 |
"word_delimiter_token": "|"
|