Training in progress, step 600
Browse files
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/w2v-bert-2.0",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_act": "relu",
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": true,
|
8 |
+
"apply_spec_augment": false,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2BertForCTC"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.0,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 768,
|
15 |
+
"codevector_dim": 768,
|
16 |
+
"conformer_conv_dropout": 0.1,
|
17 |
+
"contrastive_logits_temperature": 0.1,
|
18 |
+
"conv_depthwise_kernel_size": 31,
|
19 |
+
"ctc_loss_reduction": "mean",
|
20 |
+
"ctc_zero_infinity": false,
|
21 |
+
"diversity_loss_weight": 0.1,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"feat_proj_dropout": 0.0,
|
24 |
+
"feat_quantizer_dropout": 0.0,
|
25 |
+
"feature_projection_input_dim": 160,
|
26 |
+
"final_dropout": 0.1,
|
27 |
+
"hidden_act": "swish",
|
28 |
+
"hidden_dropout": 0.0,
|
29 |
+
"hidden_size": 1024,
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 4096,
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"layerdrop": 0.0,
|
34 |
+
"left_max_position_embeddings": 64,
|
35 |
+
"mask_feature_length": 10,
|
36 |
+
"mask_feature_min_masks": 0,
|
37 |
+
"mask_feature_prob": 0.0,
|
38 |
+
"mask_time_length": 10,
|
39 |
+
"mask_time_min_masks": 2,
|
40 |
+
"mask_time_prob": 0.0,
|
41 |
+
"max_source_positions": 5000,
|
42 |
+
"model_type": "wav2vec2-bert",
|
43 |
+
"num_adapter_layers": 1,
|
44 |
+
"num_attention_heads": 16,
|
45 |
+
"num_codevector_groups": 2,
|
46 |
+
"num_codevectors_per_group": 320,
|
47 |
+
"num_hidden_layers": 24,
|
48 |
+
"num_negatives": 100,
|
49 |
+
"output_hidden_size": 1024,
|
50 |
+
"pad_token_id": 34,
|
51 |
+
"position_embeddings_type": "relative_key",
|
52 |
+
"proj_codevector_dim": 768,
|
53 |
+
"right_max_position_embeddings": 8,
|
54 |
+
"rotary_embedding_base": 10000,
|
55 |
+
"tdnn_dilation": [
|
56 |
+
1,
|
57 |
+
2,
|
58 |
+
3,
|
59 |
+
1,
|
60 |
+
1
|
61 |
+
],
|
62 |
+
"tdnn_dim": [
|
63 |
+
512,
|
64 |
+
512,
|
65 |
+
512,
|
66 |
+
512,
|
67 |
+
1500
|
68 |
+
],
|
69 |
+
"tdnn_kernel": [
|
70 |
+
5,
|
71 |
+
3,
|
72 |
+
3,
|
73 |
+
1,
|
74 |
+
1
|
75 |
+
],
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.41.2",
|
78 |
+
"use_intermediate_ffn_before_adapter": false,
|
79 |
+
"use_weighted_layer_sum": false,
|
80 |
+
"vocab_size": 37,
|
81 |
+
"xvector_output_dim": 512
|
82 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eece8e6f5da2d306ba7601f4fecb9c6ad7f4ee47c75db4f970f6f909dea5f8f1
|
3 |
+
size 2422966260
|
runs/Jun08_01-12-04_587ec4209622/events.out.tfevents.1717809349.587ec4209622.447.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c74224d91b68b16cd19b9a043e6dbab2c5aa7d1302780a983fa585c84c80817
|
3 |
+
size 6080
|
runs/Jun08_01-17-21_587ec4209622/events.out.tfevents.1717809667.587ec4209622.447.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10252fb76d5a7cded4a1995bc5ce4708e57ea62f936b5a0b5651ad0a30c5b164
|
3 |
+
size 7137
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23add03c3d61747da730fd766299b39f13650b84bd44440f58a6f26dd6d5b063
|
3 |
+
size 5112
|