Hugging Face's logo

alexandreacff
/
sew-ft-fake-detection

Audio Classification
Transformers
TensorBoard
Safetensors
sew
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
alexandreacff commited on
Commit
89663e5
•
1 Parent(s): 0ea51a7

Training in progress, epoch 0

Browse files
Files changed (5) hide show
  1. config.json +100 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +9 -0
  4. runs/May09_16-59-59_5c7bc4386fe7/events.out.tfevents.1715274039.5c7bc4386fe7.1797.0 +3 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "asapp/sew-mid-100k",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "SEWForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 64,
14
+ 128,
15
+ 128,
16
+ 128,
17
+ 128,
18
+ 256,
19
+ 256,
20
+ 256,
21
+ 256,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 1,
31
+ 3,
32
+ 1,
33
+ 3,
34
+ 1,
35
+ 3,
36
+ 1,
37
+ 2,
38
+ 1,
39
+ 2,
40
+ 1
41
+ ],
42
+ "conv_stride": [
43
+ 5,
44
+ 2,
45
+ 1,
46
+ 2,
47
+ 1,
48
+ 2,
49
+ 1,
50
+ 2,
51
+ 1,
52
+ 2,
53
+ 1,
54
+ 2,
55
+ 1
56
+ ],
57
+ "ctc_loss_reduction": "sum",
58
+ "ctc_zero_infinity": false,
59
+ "eos_token_id": 2,
60
+ "feat_extract_activation": "gelu",
61
+ "feat_extract_norm": "group",
62
+ "feat_proj_dropout": 0.1,
63
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
64
+ "final_dropout": 0.0,
65
+ "finetuning_task": "audio-classification",
66
+ "hidden_act": "gelu",
67
+ "hidden_dropout": 0.1,
68
+ "hidden_size": 768,
69
+ "id2label": {
70
+ "0": "real",
71
+ "1": "fake"
72
+ },
73
+ "initializer_range": 0.02,
74
+ "intermediate_size": 3072,
75
+ "label2id": {
76
+ "fake": "1",
77
+ "real": "0"
78
+ },
79
+ "layer_norm_eps": 1e-05,
80
+ "layerdrop": 0.2,
81
+ "mask_feature_length": 10,
82
+ "mask_feature_min_masks": 0,
83
+ "mask_feature_prob": 0.0,
84
+ "mask_time_length": 10,
85
+ "mask_time_min_masks": 2,
86
+ "mask_time_prob": 0.65,
87
+ "model_type": "sew",
88
+ "num_attention_heads": 12,
89
+ "num_conv_pos_embedding_groups": 16,
90
+ "num_conv_pos_embeddings": 31,
91
+ "num_feat_extract_layers": 13,
92
+ "num_hidden_layers": 24,
93
+ "pad_token_id": 0,
94
+ "squeeze_factor": 2,
95
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
96
+ "torch_dtype": "float32",
97
+ "transformers_version": "4.41.0.dev0",
98
+ "use_weighted_layer_sum": false,
99
+ "vocab_size": 32
100
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66feeff8af06e00f99bdca1d0cb294bd80bb430a37c5b16263ff3f5ec2824aa9
3
+ size 699537900
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": false,
8
+ "sampling_rate": 16000
9
+ }
runs/May09_16-59-59_5c7bc4386fe7/events.out.tfevents.1715274039.5c7bc4386fe7.1797.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dcf02208a18b06c0de0410a043076e8a823ee897f5aa5596e0cc8c74ff11e83
3
+ size 6831
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9fe55a3543b4cbb31b6e8a7aba55c55ec39b47884528286bbb879c80dd7fee
3
+ size 5112