Training in progress, epoch 1
Browse files
config.json
CHANGED
|
@@ -1,20 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/
|
| 3 |
-
"activation_dropout": 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": 0.1,
|
| 13 |
"bos_token_id": 1,
|
| 14 |
"classifier_proj_size": 256,
|
| 15 |
-
"
|
| 16 |
-
"contrastive_logits_temperature": 0.1,
|
| 17 |
-
"conv_bias": false,
|
| 18 |
"conv_dim": [
|
| 19 |
512,
|
| 20 |
512,
|
|
@@ -45,74 +39,38 @@
|
|
| 45 |
"ctc_loss_reduction": "sum",
|
| 46 |
"ctc_zero_infinity": false,
|
| 47 |
"diversity_loss_weight": 0.1,
|
| 48 |
-
"do_stable_layer_norm":
|
| 49 |
"eos_token_id": 2,
|
| 50 |
"feat_extract_activation": "gelu",
|
| 51 |
-
"
|
|
|
|
| 52 |
"feat_proj_dropout": 0.1,
|
| 53 |
-
"
|
| 54 |
-
"final_dropout": 0.
|
| 55 |
-
"
|
| 56 |
"hidden_act": "gelu",
|
| 57 |
"hidden_dropout": 0.1,
|
| 58 |
-
"
|
|
|
|
| 59 |
"initializer_range": 0.02,
|
| 60 |
-
"intermediate_size":
|
| 61 |
"layer_norm_eps": 1e-05,
|
| 62 |
-
"layerdrop": 0.
|
| 63 |
-
"mask_channel_length": 10,
|
| 64 |
-
"mask_channel_min_space": 1,
|
| 65 |
-
"mask_channel_other": 0.0,
|
| 66 |
-
"mask_channel_prob": 0.0,
|
| 67 |
-
"mask_channel_selection": "static",
|
| 68 |
"mask_feature_length": 10,
|
| 69 |
"mask_feature_min_masks": 0,
|
| 70 |
"mask_feature_prob": 0.0,
|
| 71 |
"mask_time_length": 10,
|
| 72 |
"mask_time_min_masks": 2,
|
| 73 |
-
"mask_time_min_space": 1,
|
| 74 |
-
"mask_time_other": 0.0,
|
| 75 |
"mask_time_prob": 0.05,
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"no_mask_channel_overlap": false,
|
| 79 |
-
"no_mask_time_overlap": false,
|
| 80 |
-
"num_adapter_layers": 3,
|
| 81 |
-
"num_attention_heads": 12,
|
| 82 |
-
"num_codevector_groups": 2,
|
| 83 |
-
"num_codevectors_per_group": 320,
|
| 84 |
"num_conv_pos_embedding_groups": 16,
|
| 85 |
"num_conv_pos_embeddings": 128,
|
| 86 |
"num_feat_extract_layers": 7,
|
| 87 |
-
"num_hidden_layers":
|
| 88 |
-
"num_negatives": 100,
|
| 89 |
-
"output_hidden_size": 768,
|
| 90 |
"pad_token_id": 0,
|
| 91 |
-
"proj_codevector_dim": 256,
|
| 92 |
-
"tdnn_dilation": [
|
| 93 |
-
1,
|
| 94 |
-
2,
|
| 95 |
-
3,
|
| 96 |
-
1,
|
| 97 |
-
1
|
| 98 |
-
],
|
| 99 |
-
"tdnn_dim": [
|
| 100 |
-
512,
|
| 101 |
-
512,
|
| 102 |
-
512,
|
| 103 |
-
512,
|
| 104 |
-
1500
|
| 105 |
-
],
|
| 106 |
-
"tdnn_kernel": [
|
| 107 |
-
5,
|
| 108 |
-
3,
|
| 109 |
-
3,
|
| 110 |
-
1,
|
| 111 |
-
1
|
| 112 |
-
],
|
| 113 |
"torch_dtype": "float32",
|
| 114 |
"transformers_version": "4.40.2",
|
| 115 |
"use_weighted_layer_sum": false,
|
| 116 |
-
"vocab_size": 32
|
| 117 |
-
"xvector_output_dim": 512
|
| 118 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/hubert-large-ls960-ft",
|
| 3 |
+
"activation_dropout": 0.1,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"apply_spec_augment": true,
|
| 5 |
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.1,
|
| 9 |
"bos_token_id": 1,
|
| 10 |
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": true,
|
|
|
|
|
|
|
| 12 |
"conv_dim": [
|
| 13 |
512,
|
| 14 |
512,
|
|
|
|
| 39 |
"ctc_loss_reduction": "sum",
|
| 40 |
"ctc_zero_infinity": false,
|
| 41 |
"diversity_loss_weight": 0.1,
|
| 42 |
+
"do_stable_layer_norm": true,
|
| 43 |
"eos_token_id": 2,
|
| 44 |
"feat_extract_activation": "gelu",
|
| 45 |
+
"feat_extract_dropout": 0.0,
|
| 46 |
+
"feat_extract_norm": "layer",
|
| 47 |
"feat_proj_dropout": 0.1,
|
| 48 |
+
"feat_proj_layer_norm": true,
|
| 49 |
+
"final_dropout": 0.1,
|
| 50 |
+
"gradient_checkpointing": false,
|
| 51 |
"hidden_act": "gelu",
|
| 52 |
"hidden_dropout": 0.1,
|
| 53 |
+
"hidden_dropout_prob": 0.1,
|
| 54 |
+
"hidden_size": 1024,
|
| 55 |
"initializer_range": 0.02,
|
| 56 |
+
"intermediate_size": 4096,
|
| 57 |
"layer_norm_eps": 1e-05,
|
| 58 |
+
"layerdrop": 0.1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
"mask_feature_length": 10,
|
| 60 |
"mask_feature_min_masks": 0,
|
| 61 |
"mask_feature_prob": 0.0,
|
| 62 |
"mask_time_length": 10,
|
| 63 |
"mask_time_min_masks": 2,
|
|
|
|
|
|
|
| 64 |
"mask_time_prob": 0.05,
|
| 65 |
+
"model_type": "hubert",
|
| 66 |
+
"num_attention_heads": 16,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
"num_conv_pos_embedding_groups": 16,
|
| 68 |
"num_conv_pos_embeddings": 128,
|
| 69 |
"num_feat_extract_layers": 7,
|
| 70 |
+
"num_hidden_layers": 24,
|
|
|
|
|
|
|
| 71 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
"torch_dtype": "float32",
|
| 73 |
"transformers_version": "4.40.2",
|
| 74 |
"use_weighted_layer_sum": false,
|
| 75 |
+
"vocab_size": 32
|
|
|
|
| 76 |
}
|
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 sha256:373d5387b40e572ae88383d0ec3f03c172e26162a61001faef5651507b245418
|
| 3 |
+
size 1262858408
|
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": true,
|
| 8 |
"sampling_rate": 16000
|
| 9 |
}
|
runs/Jun14_20-35-04_WIN-CEJF2NB9KFH/events.out.tfevents.1718368505.WIN-CEJF2NB9KFH.18880.0
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 sha256:9103acaf08b180a0d9b2f49688e5292f8163d64030fd2330cc78512067f805b1
|
| 3 |
+
size 14681
|
runs/Jun14_20-44-02_WIN-CEJF2NB9KFH/events.out.tfevents.1718369042.WIN-CEJF2NB9KFH.36688.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39cc475d98723c8a3ddb75d2b9de9430abbb28baa7a66212284d70355e08c77c
|
| 3 |
+
size 6133
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4539
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a036e8ae43a4f80d452b222297f95d085931cbdaa111203794f6c2278197abe
|
| 3 |
size 4539
|