flipwooyoung commited on
Commit
475c991
1 Parent(s): f95b90c

hideo/asr1

Browse files
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base-960h
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: results
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # results
15
+
16
+ This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0001
36
+ - train_batch_size: 1
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 10
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.40.2
50
+ - Pytorch 2.3.0+cu121
51
+ - Datasets 2.19.2.dev0
52
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
3
+ "activation_dropout": 0.1,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 3072,
63
+ "layer_norm_eps": 1e-05,
64
+ "layerdrop": 0.1,
65
+ "mask_feature_length": 10,
66
+ "mask_feature_min_masks": 0,
67
+ "mask_feature_prob": 0.0,
68
+ "mask_time_length": 10,
69
+ "mask_time_min_masks": 2,
70
+ "mask_time_prob": 0.05,
71
+ "model_type": "wav2vec2",
72
+ "num_adapter_layers": 3,
73
+ "num_attention_heads": 12,
74
+ "num_codevector_groups": 2,
75
+ "num_codevectors_per_group": 320,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 12,
80
+ "num_negatives": 100,
81
+ "output_hidden_size": 768,
82
+ "pad_token_id": 0,
83
+ "proj_codevector_dim": 256,
84
+ "tdnn_dilation": [
85
+ 1,
86
+ 2,
87
+ 3,
88
+ 1,
89
+ 1
90
+ ],
91
+ "tdnn_dim": [
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 512,
96
+ 1500
97
+ ],
98
+ "tdnn_kernel": [
99
+ 5,
100
+ 3,
101
+ 3,
102
+ 1,
103
+ 1
104
+ ],
105
+ "torch_dtype": "float32",
106
+ "transformers_version": "4.40.2",
107
+ "use_weighted_layer_sum": false,
108
+ "vocab_size": 32,
109
+ "xvector_output_dim": 512
110
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef69fd7f3d601dc3d4a272aca3bef13fc5626e2b504b2d1bf64ed3c01306d0a3
3
+ size 377611120
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": false,
8
+ "sampling_rate": 16000
9
+ }
runs/May22_14-05-33_instance-hideo-is-working/events.out.tfevents.1716386735.instance-hideo-is-working ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e33cf0b7db335006ce2c1186e1171374f12b9693ac73ec0059efb8208729ca3
3
+ size 12419
runs/May22_14-20-13_instance-hideo-is-working/events.out.tfevents.1716387614.instance-hideo-is-working ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62bdfda083e3a0921d3a4474ea09812572d6fcfb20e1282fe715444923065c75
3
+ size 12416
runs/May23_03-37-30_instance-hideo-is-working/events.out.tfevents.1716435455.instance-hideo-is-working ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b711eba3925b6e5f4fa5accb7ae2cead11e68c4cc7bc63d50bd9e0ac4e625f8a
3
+ size 6417
runs/May23_05-42-20_instance-hideo-is-working/events.out.tfevents.1716442944.instance-hideo-is-working ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484254be0b79200cdbe0cf0ee307f01e3f0945500f4dc2d9623eb77e22a438b1
3
+ size 6417
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39d2fa181a070866bb2f2b2ca0ba2edf422ad77ac5e16f2ee8998709d0f36221
3
+ size 4984