patrickvonplaten
commited on
Commit
•
ae296b3
1
Parent(s):
9b9e82b
upload firsts probably incorrect version
Browse files- config.json +68 -0
- preprocessor_config.json +8 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.1,
|
3 |
+
"apply_spec_augment": true,
|
4 |
+
"architectures": [
|
5 |
+
"Wav2Vec2ForCTC"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"conv_bias": true,
|
10 |
+
"conv_dim": [
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512
|
18 |
+
],
|
19 |
+
"conv_kernel": [
|
20 |
+
10,
|
21 |
+
3,
|
22 |
+
3,
|
23 |
+
3,
|
24 |
+
3,
|
25 |
+
2,
|
26 |
+
2
|
27 |
+
],
|
28 |
+
"conv_stride": [
|
29 |
+
5,
|
30 |
+
2,
|
31 |
+
2,
|
32 |
+
2,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2
|
36 |
+
],
|
37 |
+
"ctc_loss_reduction": "sum",
|
38 |
+
"ctc_zero_infinity": false,
|
39 |
+
"do_stable_layer_norm": true,
|
40 |
+
"eos_token_id": 2,
|
41 |
+
"feat_extract_activation": "gelu",
|
42 |
+
"feat_extract_dropout": 0.0,
|
43 |
+
"feat_extract_norm": "layer",
|
44 |
+
"feat_proj_dropout": 0.1,
|
45 |
+
"final_dropout": 0.1,
|
46 |
+
"gradient_checkpointing": false,
|
47 |
+
"hidden_act": "gelu",
|
48 |
+
"hidden_dropout": 0.1,
|
49 |
+
"hidden_dropout_prob": 0.1,
|
50 |
+
"hidden_size": 1024,
|
51 |
+
"initializer_range": 0.02,
|
52 |
+
"intermediate_size": 4096,
|
53 |
+
"layer_norm_eps": 1e-05,
|
54 |
+
"layerdrop": 0.1,
|
55 |
+
"mask_feature_length": 10,
|
56 |
+
"mask_feature_prob": 0.0,
|
57 |
+
"mask_time_length": 10,
|
58 |
+
"mask_time_prob": 0.05,
|
59 |
+
"model_type": "wav2vec2",
|
60 |
+
"num_attention_heads": 16,
|
61 |
+
"num_conv_pos_embedding_groups": 16,
|
62 |
+
"num_conv_pos_embeddings": 128,
|
63 |
+
"num_feat_extract_layers": 7,
|
64 |
+
"num_hidden_layers": 24,
|
65 |
+
"pad_token_id": 0,
|
66 |
+
"transformers_version": "4.4.0.dev0",
|
67 |
+
"vocab_size": 50
|
68 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_size": 1,
|
4 |
+
"padding_side": "right",
|
5 |
+
"padding_value": 0.0,
|
6 |
+
"return_attention_mask": true,
|
7 |
+
"sampling_rate": 16000
|
8 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c803055f87112ce0b28b3169f6c0960a792ba43c301cb6b9eea8de2179e2d8b0
|
3 |
+
size 1262132951
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-dutch/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-dutch"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "E": 4, "N": 5, "A": 6, "I": 7, "T": 8, "S": 9, "D": 10, "R": 11, "|": 12, "L": 13, "O": 14, "H": 15, "G": 16, "M": 17, "K": 18, "V": 19, "J": 20, "P": 21, "Z": 22, "U": 23, "C": 24, "W": 25, "F": 26, "B": 27, "Y": 28, "'": 29, "É": 30, "Ä": 31, "X": 32, "Q": 33, "Ë": 34, "Ê": 35, "È": 36, "Ï": 37, "-": 38, "Ö": 39, "Â": 40, "À": 41, "Ü": 42, "Ô": 43, "Î": 44, "Æ": 45, "Û": 46, "Ç": 47, "Ù": 48, "Œ": 49}
|