Upload 5 files
Browse files- config.json +2 -3
- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +11 -0
- vocab.json +39 -0
config.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"activation_dropout": 0.1,
|
4 |
-
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
6 |
"adapter_stride": 2,
|
7 |
"add_adapter": false,
|
@@ -104,7 +103,7 @@
|
|
104 |
1
|
105 |
],
|
106 |
"torch_dtype": "float32",
|
107 |
-
"transformers_version": "4.
|
108 |
"use_weighted_layer_sum": false,
|
109 |
"vocab_size": 37,
|
110 |
"xvector_output_dim": 512
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "GroNLP/wav2vec2-dutch-large-ft-cgn",
|
3 |
"activation_dropout": 0.1,
|
|
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
6 |
"add_adapter": false,
|
|
|
103 |
1
|
104 |
],
|
105 |
"torch_dtype": "float32",
|
106 |
+
"transformers_version": "4.24.0",
|
107 |
"use_weighted_layer_sum": false,
|
108 |
"vocab_size": 37,
|
109 |
"xvector_output_dim": 512
|
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": true,
|
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 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"processor_class": "Wav2Vec2Processor",
|
7 |
+
"replace_word_delimiter_char": " ",
|
8 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
9 |
+
"unk_token": "<unk>",
|
10 |
+
"word_delimiter_token": "|"
|
11 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"'": 35,
|
3 |
+
"-": 36,
|
4 |
+
"</s>": 2,
|
5 |
+
"<pad>": 0,
|
6 |
+
"<s>": 1,
|
7 |
+
"<unk>": 3,
|
8 |
+
"?": 34,
|
9 |
+
"a": 5,
|
10 |
+
"b": 6,
|
11 |
+
"c": 7,
|
12 |
+
"d": 8,
|
13 |
+
"e": 9,
|
14 |
+
"f": 10,
|
15 |
+
"g": 11,
|
16 |
+
"h": 12,
|
17 |
+
"i": 13,
|
18 |
+
"j": 14,
|
19 |
+
"k": 15,
|
20 |
+
"l": 16,
|
21 |
+
"m": 17,
|
22 |
+
"n": 18,
|
23 |
+
"o": 19,
|
24 |
+
"p": 20,
|
25 |
+
"q": 21,
|
26 |
+
"r": 22,
|
27 |
+
"s": 23,
|
28 |
+
"t": 24,
|
29 |
+
"u": 25,
|
30 |
+
"v": 26,
|
31 |
+
"w": 27,
|
32 |
+
"x": 28,
|
33 |
+
"y": 29,
|
34 |
+
"z": 30,
|
35 |
+
"|": 4,
|
36 |
+
"è": 31,
|
37 |
+
"é": 32,
|
38 |
+
"ë": 33
|
39 |
+
}
|