Upload Wav2Vec2MultiTasks
Browse files- config.json +134 -3
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,6 +1,137 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"num_emotions": 14,
|
|
|
|
|
|
|
|
|
|
| 4 |
"num_phonemes": 33,
|
| 5 |
-
"num_speakers": 373
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"activation_dropout": 0.1,
|
| 3 |
+
"adapter_attn_dim": null,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2MultiTasks"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 256,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": false,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "mean",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"d_model": 768,
|
| 47 |
+
"decoder": {
|
| 48 |
+
"activation_dropout": 0.0,
|
| 49 |
+
"activation_function": "gelu",
|
| 50 |
+
"add_cross_attention": false,
|
| 51 |
+
"attention_dropout": 0.0,
|
| 52 |
+
"bos_token_id": 1,
|
| 53 |
+
"decoder_start_token_id": 2,
|
| 54 |
+
"dropout": 0.1,
|
| 55 |
+
"eos_token_id": 2,
|
| 56 |
+
"hidden_size": 768,
|
| 57 |
+
"initializer_range": 0.02,
|
| 58 |
+
"layer_norm_eps": 1e-05,
|
| 59 |
+
"max_position_embeddings": 512,
|
| 60 |
+
"num_attention_heads": 12,
|
| 61 |
+
"num_hidden_layers": 6,
|
| 62 |
+
"pad_token_id": 0,
|
| 63 |
+
"vocab_size": 32
|
| 64 |
+
},
|
| 65 |
+
"diversity_loss_weight": 0.1,
|
| 66 |
+
"do_stable_layer_norm": false,
|
| 67 |
+
"dtype": "float32",
|
| 68 |
+
"eos_token_id": 2,
|
| 69 |
+
"feat_extract_activation": "gelu",
|
| 70 |
+
"feat_extract_norm": "group",
|
| 71 |
+
"feat_proj_dropout": 0.0,
|
| 72 |
+
"feat_quantizer_dropout": 0.0,
|
| 73 |
+
"final_dropout": 0.1,
|
| 74 |
+
"hidden_act": "gelu",
|
| 75 |
+
"hidden_dropout": 0.1,
|
| 76 |
+
"hidden_size": 768,
|
| 77 |
+
"initializer_range": 0.02,
|
| 78 |
+
"intermediate_size": 3072,
|
| 79 |
+
"layer_norm_eps": 1e-05,
|
| 80 |
+
"layerdrop": 0.1,
|
| 81 |
+
"mask_channel_length": 10,
|
| 82 |
+
"mask_channel_min_space": 1,
|
| 83 |
+
"mask_channel_other": 0.0,
|
| 84 |
+
"mask_channel_prob": 0.0,
|
| 85 |
+
"mask_channel_selection": "static",
|
| 86 |
+
"mask_feature_length": 10,
|
| 87 |
+
"mask_feature_min_masks": 0,
|
| 88 |
+
"mask_feature_min_space": 1,
|
| 89 |
+
"mask_feature_prob": 0.0,
|
| 90 |
+
"mask_time_length": 10,
|
| 91 |
+
"mask_time_min_masks": 2,
|
| 92 |
+
"mask_time_min_space": 1,
|
| 93 |
+
"mask_time_other": 0.0,
|
| 94 |
+
"mask_time_prob": 0.05,
|
| 95 |
+
"mask_time_selection": "static",
|
| 96 |
+
"model_type": "wav2vec2",
|
| 97 |
+
"num_adapter_layers": 3,
|
| 98 |
+
"num_attention_heads": 12,
|
| 99 |
+
"num_codevector_groups": 2,
|
| 100 |
+
"num_codevectors_per_group": 320,
|
| 101 |
+
"num_conv_pos_embedding_groups": 16,
|
| 102 |
+
"num_conv_pos_embeddings": 128,
|
| 103 |
"num_emotions": 14,
|
| 104 |
+
"num_feat_extract_layers": 7,
|
| 105 |
+
"num_hidden_layers": 12,
|
| 106 |
+
"num_negatives": 100,
|
| 107 |
"num_phonemes": 33,
|
| 108 |
+
"num_speakers": 373,
|
| 109 |
+
"output_hidden_size": 768,
|
| 110 |
+
"pad_token_id": 0,
|
| 111 |
+
"proj_codevector_dim": 256,
|
| 112 |
+
"tdnn_dilation": [
|
| 113 |
+
1,
|
| 114 |
+
2,
|
| 115 |
+
3,
|
| 116 |
+
1,
|
| 117 |
+
1
|
| 118 |
+
],
|
| 119 |
+
"tdnn_dim": [
|
| 120 |
+
512,
|
| 121 |
+
512,
|
| 122 |
+
512,
|
| 123 |
+
512,
|
| 124 |
+
1500
|
| 125 |
+
],
|
| 126 |
+
"tdnn_kernel": [
|
| 127 |
+
5,
|
| 128 |
+
3,
|
| 129 |
+
3,
|
| 130 |
+
1,
|
| 131 |
+
1
|
| 132 |
+
],
|
| 133 |
+
"transformers_version": "4.56.1",
|
| 134 |
+
"use_weighted_layer_sum": false,
|
| 135 |
+
"vocab_size": 32,
|
| 136 |
+
"xvector_output_dim": 512
|
| 137 |
+
}
|
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:e931729fabed920b202a959d6a859810e087335466131c7e9d590cf800c42820
|
| 3 |
+
size 378804784
|