patrickvonplaten
commited on
Commit
•
8ad7fe9
1
Parent(s):
c151215
add first try model
Browse files- config.json +69 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.1,
|
3 |
+
"add_adapter": false,
|
4 |
+
"architectures": [
|
5 |
+
"Data2VecForAudioModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"attention_probs_dropout_prob": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": null,
|
11 |
+
"conv_bias": false,
|
12 |
+
"conv_dim": [
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512
|
20 |
+
],
|
21 |
+
"conv_kernel": [
|
22 |
+
10,
|
23 |
+
3,
|
24 |
+
3,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
2,
|
28 |
+
2
|
29 |
+
],
|
30 |
+
"conv_pos_kernel_size": 19,
|
31 |
+
"conv_stride": [
|
32 |
+
5,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2
|
39 |
+
],
|
40 |
+
"do_stable_layer_norm": false,
|
41 |
+
"eos_token_id": 2,
|
42 |
+
"feat_extract_activation": "gelu",
|
43 |
+
"feat_extract_norm": "layer",
|
44 |
+
"feat_proj_dropout": 0.0,
|
45 |
+
"final_dropout": 0.1,
|
46 |
+
"hidden_act": "gelu",
|
47 |
+
"hidden_dropout": 0.1,
|
48 |
+
"hidden_dropout_prob": 0.1,
|
49 |
+
"hidden_size": 768,
|
50 |
+
"initializer_range": 0.02,
|
51 |
+
"intermediate_size": 3072,
|
52 |
+
"layer_norm_eps": 1e-05,
|
53 |
+
"mask_time_prob": 0.05,
|
54 |
+
"max_position_embeddings": 512,
|
55 |
+
"model_type": "data2vec",
|
56 |
+
"num_attention_heads": 12,
|
57 |
+
"num_conv_pos_embedding_groups": 16,
|
58 |
+
"num_conv_pos_embeddings": 5,
|
59 |
+
"num_feat_extract_layers": 7,
|
60 |
+
"num_hidden_layers": 12,
|
61 |
+
"pad_token_id": 1,
|
62 |
+
"position_embedding_type": "absolute",
|
63 |
+
"proj_codevector_dim": 256,
|
64 |
+
"torch_dtype": "float32",
|
65 |
+
"transformers_version": "4.17.0.dev0",
|
66 |
+
"type_vocab_size": 2,
|
67 |
+
"use_cache": true,
|
68 |
+
"vocab_size": 32
|
69 |
+
}
|
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": 0.0,
|
7 |
+
"return_attention_mask": true,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c61a644c4607cae1961a4b3d36fcc66b9e716068458af0c742de598f522b361
|
3 |
+
size 372742325
|