Training in progress, step 200
Browse files
config.json
CHANGED
@@ -1,19 +1,13 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
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 |
-
"
|
11 |
],
|
12 |
-
"attention_dropout": 0.
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
-
"codevector_dim": 768,
|
16 |
-
"contrastive_logits_temperature": 0.1,
|
17 |
"conv_bias": true,
|
18 |
"conv_dim": [
|
19 |
512,
|
@@ -44,23 +38,22 @@
|
|
44 |
],
|
45 |
"ctc_loss_reduction": "mean",
|
46 |
"ctc_zero_infinity": true,
|
47 |
-
"diversity_loss_weight": 0.1,
|
48 |
"do_stable_layer_norm": true,
|
49 |
"eos_token_id": 2,
|
50 |
"feat_extract_activation": "gelu",
|
51 |
"feat_extract_dropout": 0.0,
|
52 |
"feat_extract_norm": "layer",
|
53 |
"feat_proj_dropout": 0.0,
|
54 |
-
"
|
55 |
"final_dropout": 0.0,
|
56 |
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
-
"hidden_dropout": 0.
|
59 |
"hidden_size": 1024,
|
60 |
"initializer_range": 0.02,
|
61 |
"intermediate_size": 4096,
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
-
"layerdrop": 0.
|
64 |
"mask_channel_length": 10,
|
65 |
"mask_channel_min_space": 1,
|
66 |
"mask_channel_other": 0.0,
|
@@ -75,43 +68,16 @@
|
|
75 |
"mask_time_other": 0.0,
|
76 |
"mask_time_prob": 0.05,
|
77 |
"mask_time_selection": "static",
|
78 |
-
"model_type": "
|
79 |
-
"num_adapter_layers": 3,
|
80 |
"num_attention_heads": 16,
|
81 |
-
"num_codevector_groups": 2,
|
82 |
-
"num_codevectors_per_group": 320,
|
83 |
"num_conv_pos_embedding_groups": 16,
|
84 |
"num_conv_pos_embeddings": 128,
|
85 |
"num_feat_extract_layers": 7,
|
86 |
"num_hidden_layers": 24,
|
87 |
-
"num_negatives": 100,
|
88 |
-
"output_hidden_size": 1024,
|
89 |
"pad_token_id": 109,
|
90 |
-
"
|
91 |
-
"tdnn_dilation": [
|
92 |
-
1,
|
93 |
-
2,
|
94 |
-
3,
|
95 |
-
1,
|
96 |
-
1
|
97 |
-
],
|
98 |
-
"tdnn_dim": [
|
99 |
-
512,
|
100 |
-
512,
|
101 |
-
512,
|
102 |
-
512,
|
103 |
-
1500
|
104 |
-
],
|
105 |
-
"tdnn_kernel": [
|
106 |
-
5,
|
107 |
-
3,
|
108 |
-
3,
|
109 |
-
1,
|
110 |
-
1
|
111 |
-
],
|
112 |
"torch_dtype": "float32",
|
113 |
"transformers_version": "4.37.0.dev0",
|
114 |
"use_weighted_layer_sum": false,
|
115 |
-
"vocab_size": 112
|
116 |
-
"xvector_output_dim": 512
|
117 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "omarxadel/hubert-large-arabic-egyptian",
|
3 |
"activation_dropout": 0.0,
|
|
|
|
|
|
|
|
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
+
"HubertForCTC"
|
7 |
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
"bos_token_id": 1,
|
10 |
"classifier_proj_size": 256,
|
|
|
|
|
11 |
"conv_bias": true,
|
12 |
"conv_dim": [
|
13 |
512,
|
|
|
38 |
],
|
39 |
"ctc_loss_reduction": "mean",
|
40 |
"ctc_zero_infinity": true,
|
|
|
41 |
"do_stable_layer_norm": true,
|
42 |
"eos_token_id": 2,
|
43 |
"feat_extract_activation": "gelu",
|
44 |
"feat_extract_dropout": 0.0,
|
45 |
"feat_extract_norm": "layer",
|
46 |
"feat_proj_dropout": 0.0,
|
47 |
+
"feat_proj_layer_norm": true,
|
48 |
"final_dropout": 0.0,
|
49 |
"gradient_checkpointing": false,
|
50 |
"hidden_act": "gelu",
|
51 |
+
"hidden_dropout": 0.0,
|
52 |
"hidden_size": 1024,
|
53 |
"initializer_range": 0.02,
|
54 |
"intermediate_size": 4096,
|
55 |
"layer_norm_eps": 1e-05,
|
56 |
+
"layerdrop": 0.0,
|
57 |
"mask_channel_length": 10,
|
58 |
"mask_channel_min_space": 1,
|
59 |
"mask_channel_other": 0.0,
|
|
|
68 |
"mask_time_other": 0.0,
|
69 |
"mask_time_prob": 0.05,
|
70 |
"mask_time_selection": "static",
|
71 |
+
"model_type": "hubert",
|
|
|
72 |
"num_attention_heads": 16,
|
|
|
|
|
73 |
"num_conv_pos_embedding_groups": 16,
|
74 |
"num_conv_pos_embeddings": 128,
|
75 |
"num_feat_extract_layers": 7,
|
76 |
"num_hidden_layers": 24,
|
|
|
|
|
77 |
"pad_token_id": 109,
|
78 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
79 |
"torch_dtype": "float32",
|
80 |
"transformers_version": "4.37.0.dev0",
|
81 |
"use_weighted_layer_sum": false,
|
82 |
+
"vocab_size": 112
|
|
|
83 |
}
|
model.safetensors
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:d4d833c3bab5cde51d816cf96c8ac2fc05a265a28e440de827a7847c3ff1d5df
|
3 |
+
size 1267694072
|
preprocessor_config.json
CHANGED
@@ -4,7 +4,6 @@
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
-
"processor_class": "Wav2Vec2Processor",
|
8 |
"return_attention_mask": true,
|
9 |
"sampling_rate": 16000
|
10 |
}
|
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
|
|
7 |
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
runs/Dec27_18-12-36_e130e727b7e8/events.out.tfevents.1703700960.e130e727b7e8.2076.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93374a52d9b2f8d69e57f40230f0af40d2ec4b09b1ad94e8132c92fb32918503
|
3 |
+
size 17932
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23f6dfe6ae20e95915e4d3e13d589b74ca187f3cb20395c322743e471387f738
|
3 |
size 4664
|