kingabzpro
commited on
Commit
•
af64454
1
Parent(s):
90eeb5d
Training in progress, step 100
Browse files- config.json +17 -22
- preprocessor_config.json +2 -2
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation_dropout": 0.
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
6 |
"add_adapter": false,
|
@@ -9,12 +9,11 @@
|
|
9 |
"Wav2Vec2ForCTC"
|
10 |
],
|
11 |
"attention_dropout": 0.1,
|
12 |
-
"
|
13 |
-
"bos_token_id": 0,
|
14 |
"classifier_proj_size": 256,
|
15 |
-
"codevector_dim":
|
16 |
"contrastive_logits_temperature": 0.1,
|
17 |
-
"conv_bias":
|
18 |
"conv_dim": [
|
19 |
512,
|
20 |
512,
|
@@ -45,23 +44,22 @@
|
|
45 |
"ctc_loss_reduction": "mean",
|
46 |
"ctc_zero_infinity": false,
|
47 |
"diversity_loss_weight": 0.1,
|
48 |
-
"
|
49 |
-
"do_stable_layer_norm": false,
|
50 |
-
"eos_token": "</s>",
|
51 |
"eos_token_id": 2,
|
52 |
"feat_extract_activation": "gelu",
|
53 |
-
"
|
|
|
54 |
"feat_proj_dropout": 0.0,
|
55 |
"feat_quantizer_dropout": 0.0,
|
56 |
-
"final_dropout": 0.
|
57 |
"gradient_checkpointing": false,
|
58 |
"hidden_act": "gelu",
|
59 |
"hidden_dropout": 0.1,
|
60 |
-
"hidden_size":
|
61 |
"initializer_range": 0.02,
|
62 |
-
"intermediate_size":
|
63 |
"layer_norm_eps": 1e-05,
|
64 |
-
"layerdrop": 0.
|
65 |
"mask_feature_length": 10,
|
66 |
"mask_feature_min_masks": 0,
|
67 |
"mask_feature_prob": 0.0,
|
@@ -70,18 +68,17 @@
|
|
70 |
"mask_time_prob": 0.05,
|
71 |
"model_type": "wav2vec2",
|
72 |
"num_adapter_layers": 3,
|
73 |
-
"num_attention_heads":
|
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":
|
80 |
"num_negatives": 100,
|
81 |
-
"output_hidden_size":
|
82 |
-
"
|
83 |
-
"
|
84 |
-
"proj_codevector_dim": 256,
|
85 |
"tdnn_dilation": [
|
86 |
1,
|
87 |
2,
|
@@ -105,9 +102,7 @@
|
|
105 |
],
|
106 |
"torch_dtype": "float32",
|
107 |
"transformers_version": "4.16.0.dev0",
|
108 |
-
"unk_token": "[UNK]",
|
109 |
"use_weighted_layer_sum": false,
|
110 |
"vocab_size": 48,
|
111 |
-
"word_delimiter_token": "|",
|
112 |
"xvector_output_dim": 512
|
113 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
6 |
"add_adapter": false,
|
|
|
9 |
"Wav2Vec2ForCTC"
|
10 |
],
|
11 |
"attention_dropout": 0.1,
|
12 |
+
"bos_token_id": 1,
|
|
|
13 |
"classifier_proj_size": 256,
|
14 |
+
"codevector_dim": 768,
|
15 |
"contrastive_logits_temperature": 0.1,
|
16 |
+
"conv_bias": true,
|
17 |
"conv_dim": [
|
18 |
512,
|
19 |
512,
|
|
|
44 |
"ctc_loss_reduction": "mean",
|
45 |
"ctc_zero_infinity": false,
|
46 |
"diversity_loss_weight": 0.1,
|
47 |
+
"do_stable_layer_norm": true,
|
|
|
|
|
48 |
"eos_token_id": 2,
|
49 |
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "layer",
|
52 |
"feat_proj_dropout": 0.0,
|
53 |
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
"gradient_checkpointing": false,
|
56 |
"hidden_act": "gelu",
|
57 |
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 1024,
|
59 |
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 4096,
|
61 |
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.1,
|
63 |
"mask_feature_length": 10,
|
64 |
"mask_feature_min_masks": 0,
|
65 |
"mask_feature_prob": 0.0,
|
|
|
68 |
"mask_time_prob": 0.05,
|
69 |
"model_type": "wav2vec2",
|
70 |
"num_adapter_layers": 3,
|
71 |
+
"num_attention_heads": 16,
|
72 |
"num_codevector_groups": 2,
|
73 |
"num_codevectors_per_group": 320,
|
74 |
"num_conv_pos_embedding_groups": 16,
|
75 |
"num_conv_pos_embeddings": 128,
|
76 |
"num_feat_extract_layers": 7,
|
77 |
+
"num_hidden_layers": 24,
|
78 |
"num_negatives": 100,
|
79 |
+
"output_hidden_size": 1024,
|
80 |
+
"pad_token_id": 1,
|
81 |
+
"proj_codevector_dim": 768,
|
|
|
82 |
"tdnn_dilation": [
|
83 |
1,
|
84 |
2,
|
|
|
102 |
],
|
103 |
"torch_dtype": "float32",
|
104 |
"transformers_version": "4.16.0.dev0",
|
|
|
105 |
"use_weighted_layer_sum": false,
|
106 |
"vocab_size": 48,
|
|
|
107 |
"xvector_output_dim": 512
|
108 |
}
|
preprocessor_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
-
"padding_value": 0
|
7 |
-
"return_attention_mask":
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
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 |
}
|
pytorch_model.bin
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 sha256:705ee585b0bfaa9a70529ef35c83ff8d1eed4f133ffa65c450d6d88b0563ed2f
|
3 |
+
size 1262120497
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3055
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f21b48f8d666ecd4de0da288dcc94b7348e892d4eed1aa091560f7fdf940c6cf
|
3 |
size 3055
|