NickoSELI commited on
Commit
3fc2688
1 Parent(s): 88b9182

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. config.json +106 -0
  2. model_weights2.pt +3 -0
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/speecht5_tts",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "SpeechT5ForTextToSpeech"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "d_ff": 2048,
40
+ "d_kv": 64,
41
+ "d_model": 768,
42
+ "decoder_attention_heads": 12,
43
+ "decoder_ffn_dim": 3072,
44
+ "decoder_layerdrop": 0.1,
45
+ "decoder_layers": 6,
46
+ "decoder_start_token_id": 2,
47
+ "dense_act_fn": "relu",
48
+ "dropout_rate": 0.1,
49
+ "encoder_attention_heads": 12,
50
+ "encoder_ffn_dim": 3072,
51
+ "encoder_layerdrop": 0.1,
52
+ "encoder_layers": 12,
53
+ "encoder_max_relative_position": 160,
54
+ "eos_token_id": 2,
55
+ "feat_extract_activation": "gelu",
56
+ "feat_extract_norm": "group",
57
+ "feat_proj_dropout": 0.0,
58
+ "feed_forward_proj": "relu",
59
+ "guided_attention_loss_num_heads": 2,
60
+ "guided_attention_loss_scale": 10.0,
61
+ "guided_attention_loss_sigma": 0.4,
62
+ "hidden_act": "gelu",
63
+ "hidden_dropout": 0.1,
64
+ "initializer_factor": 1.0,
65
+ "initializer_range": 0.02,
66
+ "is_encoder_decoder": true,
67
+ "is_gated_act": false,
68
+ "layer_norm_eps": 1e-05,
69
+ "layer_norm_epsilon": 1e-06,
70
+ "mask_feature_length": 10,
71
+ "mask_feature_min_masks": 0,
72
+ "mask_feature_prob": 0.0,
73
+ "mask_time_length": 10,
74
+ "mask_time_min_masks": 2,
75
+ "mask_time_prob": 0.05,
76
+ "max_length": 1876,
77
+ "max_speech_positions": 1876,
78
+ "max_text_positions": 600,
79
+ "model_type": "t5",
80
+ "num_conv_pos_embedding_groups": 16,
81
+ "num_conv_pos_embeddings": 128,
82
+ "num_decoder_layers": 6,
83
+ "num_feat_extract_layers": 7,
84
+ "num_heads": 8,
85
+ "num_layers": 6,
86
+ "num_mel_bins": 80,
87
+ "pad_token_id": 1,
88
+ "positional_dropout": 0.1,
89
+ "reduction_factor": 2,
90
+ "relative_attention_max_distance": 128,
91
+ "relative_attention_num_buckets": 32,
92
+ "scale_embedding": false,
93
+ "speaker_embedding_dim": 512,
94
+ "speech_decoder_postnet_dropout": 0.5,
95
+ "speech_decoder_postnet_kernel": 5,
96
+ "speech_decoder_postnet_layers": 5,
97
+ "speech_decoder_postnet_units": 256,
98
+ "speech_decoder_prenet_dropout": 0.5,
99
+ "speech_decoder_prenet_layers": 2,
100
+ "speech_decoder_prenet_units": 256,
101
+ "torch_dtype": "float32",
102
+ "transformers_version": "4.39.1",
103
+ "use_cache": true,
104
+ "use_guided_attention_loss": true,
105
+ "vocab_size": 81
106
+ }
model_weights2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5ab3808ca4b3effa149902fa18df7ce8f9b022202dc74f522178938aa180973
3
+ size 2462