Upload processor
Browse files- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +13 -0
- vocab.json +14 -0
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
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"replace_word_delimiter_char": " ",
|
9 |
+
"special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--patrickvonplaten--wav2vec2_tiny_random/snapshots/24bc33e6e5d824bef7eafd205bb0a70dcffec750/special_tokens_map.json",
|
10 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
11 |
+
"unk_token": "<unk>",
|
12 |
+
"word_delimiter_token": "|"
|
13 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 8,
|
3 |
+
"<pad>": 10,
|
4 |
+
"<s>": 7,
|
5 |
+
"<unk>": 9,
|
6 |
+
"a": 0,
|
7 |
+
"b": 1,
|
8 |
+
"c": 2,
|
9 |
+
"d": 3,
|
10 |
+
"e": 4,
|
11 |
+
"f": 5,
|
12 |
+
"g": 6,
|
13 |
+
"|": 11
|
14 |
+
}
|