hubert feature
#1
by
Smith1923
- opened
chinese-hubert-large/config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.1,
|
3 |
+
"apply_spec_augment": true,
|
4 |
+
"architectures": [
|
5 |
+
"HubertModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"classifier_proj_size": 256,
|
10 |
+
"conv_bias": false,
|
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": "sum",
|
39 |
+
"ctc_zero_infinity": false,
|
40 |
+
"do_stable_layer_norm": true,
|
41 |
+
"eos_token_id": 2,
|
42 |
+
"feat_extract_activation": "gelu",
|
43 |
+
"feat_extract_norm": "layer",
|
44 |
+
"feat_proj_dropout": 0.0,
|
45 |
+
"feat_proj_layer_norm": true,
|
46 |
+
"final_dropout": 0.1,
|
47 |
+
"hidden_act": "gelu",
|
48 |
+
"hidden_dropout": 0.1,
|
49 |
+
"hidden_size": 1024,
|
50 |
+
"initializer_range": 0.02,
|
51 |
+
"intermediate_size": 4096,
|
52 |
+
"layer_norm_eps": 1e-05,
|
53 |
+
"layerdrop": 0.1,
|
54 |
+
"mask_feature_length": 10,
|
55 |
+
"mask_feature_min_masks": 0,
|
56 |
+
"mask_feature_prob": 0.0,
|
57 |
+
"mask_time_length": 10,
|
58 |
+
"mask_time_min_masks": 2,
|
59 |
+
"mask_time_prob": 0.05,
|
60 |
+
"model_type": "hubert",
|
61 |
+
"num_attention_heads": 16,
|
62 |
+
"num_conv_pos_embedding_groups": 16,
|
63 |
+
"num_conv_pos_embeddings": 128,
|
64 |
+
"num_feat_extract_layers": 7,
|
65 |
+
"num_hidden_layers": 24,
|
66 |
+
"pad_token_id": 0,
|
67 |
+
"torch_dtype": "float32",
|
68 |
+
"transformers_version": "4.20.0.dev0",
|
69 |
+
"use_weighted_layer_sum": false,
|
70 |
+
"vocab_size": 32
|
71 |
+
}
|
chinese-hubert-large/preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0,
|
7 |
+
"return_attention_mask": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
chinese-hubert-large/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:482c19cd60877832995d790ed10dd1203b1f8c86ed7a69b4bd27f470fc27ee43
|
3 |
+
size 1261871939
|