Nhut DOANNGUYEN
commited on
Commit
•
4d727a2
1
Parent(s):
0103479
Version 18
Browse files- .DS_Store +0 -0
- added_tokens.json +1 -0
- config.json +76 -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
.DS_Store
ADDED
Binary file (6.15 kB). View file
|
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 91, "</s>": 92}
|
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/gdrive/MyDrive/Colab\\ Notebooks/XLSR_V17/wav2vec-large-xlsr-vietnamese-demo",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"Wav2Vec2ForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"conv_bias": true,
|
11 |
+
"conv_dim": [
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512
|
19 |
+
],
|
20 |
+
"conv_kernel": [
|
21 |
+
10,
|
22 |
+
3,
|
23 |
+
3,
|
24 |
+
3,
|
25 |
+
3,
|
26 |
+
2,
|
27 |
+
2
|
28 |
+
],
|
29 |
+
"conv_stride": [
|
30 |
+
5,
|
31 |
+
2,
|
32 |
+
2,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2
|
37 |
+
],
|
38 |
+
"ctc_loss_reduction": "mean",
|
39 |
+
"ctc_zero_infinity": false,
|
40 |
+
"do_stable_layer_norm": true,
|
41 |
+
"eos_token_id": 2,
|
42 |
+
"feat_extract_activation": "gelu",
|
43 |
+
"feat_extract_dropout": 0.0,
|
44 |
+
"feat_extract_norm": "layer",
|
45 |
+
"feat_proj_dropout": 0.0,
|
46 |
+
"final_dropout": 0.0,
|
47 |
+
"gradient_checkpointing": true,
|
48 |
+
"hidden_act": "gelu",
|
49 |
+
"hidden_dropout": 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_channel_length": 10,
|
56 |
+
"mask_channel_min_space": 1,
|
57 |
+
"mask_channel_other": 0.0,
|
58 |
+
"mask_channel_prob": 0.0,
|
59 |
+
"mask_channel_selection": "static",
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_prob": 0.0,
|
62 |
+
"mask_time_length": 10,
|
63 |
+
"mask_time_min_space": 1,
|
64 |
+
"mask_time_other": 0.0,
|
65 |
+
"mask_time_prob": 0.05,
|
66 |
+
"mask_time_selection": "static",
|
67 |
+
"model_type": "wav2vec2",
|
68 |
+
"num_attention_heads": 16,
|
69 |
+
"num_conv_pos_embedding_groups": 16,
|
70 |
+
"num_conv_pos_embeddings": 128,
|
71 |
+
"num_feat_extract_layers": 7,
|
72 |
+
"num_hidden_layers": 24,
|
73 |
+
"pad_token_id": 90,
|
74 |
+
"transformers_version": "4.4.0",
|
75 |
+
"vocab_size": 93
|
76 |
+
}
|
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:f11e7457f7d31e0e9356d860f44acbbea43e719a816a53ac9bdf5cbb67f1bca7
|
3 |
+
size 1262315159
|
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": "/content/gdrive/MyDrive/Colab\\ Notebooks/XLSR_24_1938-0.71+0/wav2vec-large-xlsr-vietnamese-demo/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/content/gdrive/MyDrive/Colab\\ Notebooks/XLSR_V17/wav2vec-large-xlsr-vietnamese-demo"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"|": 0, "ồ": 1, "ẳ": 2, "ử": 3, "ụ": 4, "ê": 5, "ự": 6, "s": 7, "ơ": 8, "h": 9, "ẹ": 10, "ế": 11, "ẫ": 12, "ứ": 13, "ỷ": 14, "ý": 15, "ỏ": 16, "ò": 17, "ả": 18, "ề": 19, "g": 20, "ố": 21, "e": 22, "d": 23, "ẽ": 24, "ủ": 25, "ễ": 26, "ậ": 27, "ù": 28, "i": 29, "ổ": 30, "v": 31, "p": 32, "ắ": 33, "x": 34, "a": 35, "r": 36, "m": 37, "ẵ": 38, "ị": 39, "y": 40, "ỹ": 41, "ú": 42, "ấ": 43, "n": 44, "ể": 45, "ợ": 46, "ừ": 47, "ó": 48, "ộ": 49, "ì": 50, "à": 51, "ũ": 52, "đ": 53, "ỡ": 54, "ờ": 55, "é": 56, "ớ": 57, "ỗ": 58, "ẩ": 59, "ữ": 60, "õ": 61, "t": 62, "ã": 63, "â": 64, "í": 65, "ô": 66, "ư": 67, "ỉ": 68, "ở": 70, "u": 71, "o": 72, "k": 73, "ằ": 74, "ọ": 75, "ă": 76, "á": 77, "ệ": 78, "ĩ": 79, "ầ": 80, "ỳ": 81, "ặ": 82, "c": 83, "b": 84, "q": 85, "ẻ": 86, "l": 87, "è": 88, "ạ": 69, "[UNK]": 89, "[PAD]": 90}
|