patrickvonplaten
commited on
Commit
•
a8ea9b1
1
Parent(s):
3dfd745
add model
Browse files- config.json +27 -1
- tf_model.h5 +2 -2
config.json
CHANGED
@@ -1,7 +1,14 @@
|
|
1 |
{
|
|
|
|
|
|
|
2 |
"architectures": [
|
3 |
"Wav2Vec2ForCTC"
|
4 |
],
|
|
|
|
|
|
|
|
|
5 |
"conv_bias": false,
|
6 |
"conv_dim": [
|
7 |
512,
|
@@ -30,22 +37,41 @@
|
|
30 |
2,
|
31 |
2
|
32 |
],
|
|
|
|
|
|
|
33 |
"do_stable_layer_norm": false,
|
|
|
34 |
"feat_extract_activation": "gelu",
|
35 |
"feat_extract_dropout": 0.0,
|
36 |
"feat_extract_norm": "group",
|
|
|
|
|
|
|
|
|
37 |
"hidden_act": "gelu",
|
|
|
38 |
"hidden_dropout_prob": 0.1,
|
39 |
"hidden_size": 768,
|
40 |
"initializer_range": 0.02,
|
41 |
"intermediate_size": 3072,
|
42 |
"layer_norm_eps": 1e-05,
|
|
|
|
|
|
|
|
|
|
|
43 |
"model_type": "wav2vec2",
|
44 |
"num_attention_heads": 12,
|
|
|
|
|
45 |
"num_conv_pos_embedding_groups": 16,
|
46 |
"num_conv_pos_embeddings": 128,
|
47 |
"num_feat_extract_layers": 7,
|
48 |
"num_hidden_layers": 12,
|
49 |
-
"
|
|
|
|
|
|
|
50 |
"vocab_size": 32
|
51 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"Wav2Vec2ForCTC"
|
7 |
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"codevector_dim": 256,
|
11 |
+
"contrastive_logits_temperature": 0.1,
|
12 |
"conv_bias": false,
|
13 |
"conv_dim": [
|
14 |
512,
|
|
|
37 |
2,
|
38 |
2
|
39 |
],
|
40 |
+
"ctc_loss_reduction": "sum",
|
41 |
+
"ctc_zero_infinity": false,
|
42 |
+
"diversity_loss_weight": 0.1,
|
43 |
"do_stable_layer_norm": false,
|
44 |
+
"eos_token_id": 2,
|
45 |
"feat_extract_activation": "gelu",
|
46 |
"feat_extract_dropout": 0.0,
|
47 |
"feat_extract_norm": "group",
|
48 |
+
"feat_proj_dropout": 0.1,
|
49 |
+
"feat_quantizer_dropout": 0.0,
|
50 |
+
"final_dropout": 0.1,
|
51 |
+
"gradient_checkpointing": false,
|
52 |
"hidden_act": "gelu",
|
53 |
+
"hidden_dropout": 0.1,
|
54 |
"hidden_dropout_prob": 0.1,
|
55 |
"hidden_size": 768,
|
56 |
"initializer_range": 0.02,
|
57 |
"intermediate_size": 3072,
|
58 |
"layer_norm_eps": 1e-05,
|
59 |
+
"layerdrop": 0.1,
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_prob": 0.0,
|
62 |
+
"mask_time_length": 10,
|
63 |
+
"mask_time_prob": 0.05,
|
64 |
"model_type": "wav2vec2",
|
65 |
"num_attention_heads": 12,
|
66 |
+
"num_codevector_groups": 2,
|
67 |
+
"num_codevectors_per_group": 320,
|
68 |
"num_conv_pos_embedding_groups": 16,
|
69 |
"num_conv_pos_embeddings": 128,
|
70 |
"num_feat_extract_layers": 7,
|
71 |
"num_hidden_layers": 12,
|
72 |
+
"num_negatives": 100,
|
73 |
+
"pad_token_id": 0,
|
74 |
+
"proj_codevector_dim": 256,
|
75 |
+
"transformers_version": "4.7.0.dev0",
|
76 |
"vocab_size": 32
|
77 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:412742825972a6e2e877255ccd8b3416e618df15a7f1e5e4f736aa3632ce33b5
|
3 |
+
size 377840624
|