Hugging Face's logo

duwuonline
/
speecht5_finetuned_voxpopuli_nl

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_finetuned_voxpopuli_nl
File size: 3,322 Bytes 
ab73ed6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
 
{
  "_name_or_path": "facebook/mms-tts-vie",
  "activation_dropout": 0.1,
  "apply_spec_augment": true,
  "architectures": [
    "SpeechT5ForTextToSpeech"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 0,
  "conv_bias": false,
  "conv_dim": [
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "conv_kernel": [
    10,
    3,
    3,
    3,
    3,
    2,
    2
  ],
  "conv_stride": [
    5,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "decoder_attention_heads": 12,
  "decoder_ffn_dim": 3072,
  "decoder_layerdrop": 0.1,
  "decoder_layers": 6,
  "decoder_start_token_id": 2,
  "depth_separable_channels": 2,
  "depth_separable_num_layers": 3,
  "duration_predictor_dropout": 0.5,
  "duration_predictor_filter_channels": 256,
  "duration_predictor_flow_bins": 10,
  "duration_predictor_kernel_size": 3,
  "duration_predictor_num_flows": 4,
  "duration_predictor_tail_bound": 5.0,
  "encoder_attention_heads": 2,
  "encoder_ffn_dim": 3072,
  "encoder_layerdrop": 0.1,
  "encoder_layers": 6,
  "encoder_max_relative_position": 160,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.0,
  "ffn_dim": 768,
  "ffn_kernel_size": 3,
  "flow_size": 192,
  "guided_attention_loss_num_heads": 2,
  "guided_attention_loss_scale": 10.0,
  "guided_attention_loss_sigma": 0.4,
  "hidden_act": "relu",
  "hidden_dropout": 0.1,
  "hidden_size": 192,
  "initializer_range": 0.02,
  "is_encoder_decoder": true,
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "leaky_relu_slope": 0.1,
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_time_prob": 0.05,
  "max_speech_positions": 4000,
  "max_text_positions": 450,
  "model_type": "speecht5",
  "noise_scale": 0.667,
  "noise_scale_duration": 0.8,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_feat_extract_layers": 7,
  "num_mel_bins": 80,
  "num_speakers": 1,
  "pad_token_id": 1,
  "positional_dropout": 0.1,
  "posterior_encoder_num_wavenet_layers": 16,
  "prior_encoder_num_flows": 4,
  "prior_encoder_num_wavenet_layers": 4,
  "reduction_factor": 2,
  "resblock_dilation_sizes": [
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ]
  ],
  "resblock_kernel_sizes": [
    3,
    7,
    11
  ],
  "sampling_rate": 16000,
  "scale_embedding": false,
  "speaker_embedding_dim": 512,
  "speaker_embedding_size": 0,
  "speaking_rate": 1.0,
  "spectrogram_bins": 513,
  "speech_decoder_postnet_dropout": 0.5,
  "speech_decoder_postnet_kernel": 5,
  "speech_decoder_postnet_layers": 5,
  "speech_decoder_postnet_units": 256,
  "speech_decoder_prenet_dropout": 0.5,
  "speech_decoder_prenet_layers": 2,
  "speech_decoder_prenet_units": 256,
  "torch_dtype": "float32",
  "transformers_version": "4.35.2",
  "upsample_initial_channel": 512,
  "upsample_kernel_sizes": [
    16,
    16,
    4,
    4
  ],
  "upsample_rates": [
    8,
    8,
    2,
    2
  ],
  "use_bias": true,
  "use_cache": false,
  "use_guided_attention_loss": true,
  "use_stochastic_duration_prediction": true,
  "vocab_size": 95,
  "wavenet_dilation_rate": 1,
  "wavenet_dropout": 0.0,
  "wavenet_kernel_size": 5,
  "window_size": 4
}