Hugging Face's logo

mlx-community
/
kitten-tts-mini

Text-to-Speech
Safetensors
MLX
mlx-audio
kitten_tts
speech
speech generation
voice cloning
tts
Model card Files
xet
 Community
roboalchemist commited on
Commit
d1f3a2c
·
verified ·
1 Parent(s): 5ffd64d

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +43 -0
  2. config.json +220 -0
  3. model.safetensors +3 -0
  4. model.safetensors.index.json +484 -0
  5. voices.npz +3 -0
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - mlx
5
+ - text-to-speech
6
+ - speech
7
+ - speech generation
8
+ - voice cloning
9
+ - tts
10
+ - mlx-audio
11
+ library_name: mlx-audio
12
+ ---
13
+ # mlx-community/kitten-tts-mini
14
+
15
+ This model was converted to MLX format from [`KittenML/kitten-tts-mini-0.8`](https://huggingface.co/KittenML/kitten-tts-mini-0.8) using mlx-audio version **0.2.8**.
16
+
17
+ Refer to the [original model card](https://huggingface.co/KittenML/kitten-tts-mini-0.8) for more details on the model.
18
+
19
+ ## Use with mlx-audio
20
+
21
+ ```bash
22
+ pip install -U mlx-audio
23
+ ```
24
+
25
+ ### CLI Example:
26
+ ```bash
27
+ python -m mlx_audio.tts.generate --model mlx-community/kitten-tts-mini --text "Hello, this is a test."
28
+ ```
29
+
30
+ ### Python Example:
31
+ ```python
32
+ from mlx_audio.tts.utils import load_model
33
+ from mlx_audio.tts.generate import generate_audio
34
+
35
+ model = load_model("mlx-community/kitten-tts-mini")
36
+ generate_audio(
37
+ model=model,
38
+ text="Hello, this is a test.",
39
+ ref_audio="path_to_audio.wav",
40
+ file_prefix="test_audio",
41
+ )
42
+
43
+ ```
config.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_quant_modules": [
3
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.dense",
4
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.key",
5
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.query",
6
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.value",
7
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn",
8
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn_output",
9
+ "bert.encoder.embedding_hidden_mapping_in",
10
+ "bert_encoder",
11
+ "decoder.asr_res.0",
12
+ "decoder.decode.0.conv1",
13
+ "decoder.decode.0.conv1x1",
14
+ "decoder.decode.0.conv2",
15
+ "decoder.decode.0.norm1.fc",
16
+ "decoder.decode.0.norm2.fc",
17
+ "decoder.decode.1.conv1",
18
+ "decoder.decode.1.conv1x1",
19
+ "decoder.decode.1.conv2",
20
+ "decoder.decode.1.norm1.fc",
21
+ "decoder.decode.1.norm2.fc",
22
+ "decoder.decode.2.conv1",
23
+ "decoder.decode.2.conv1x1",
24
+ "decoder.decode.2.conv2",
25
+ "decoder.decode.2.norm1.fc",
26
+ "decoder.decode.2.norm2.fc",
27
+ "decoder.decode.3.conv1",
28
+ "decoder.decode.3.conv1x1",
29
+ "decoder.decode.3.conv2",
30
+ "decoder.decode.3.norm1.fc",
31
+ "decoder.decode.3.norm2.fc",
32
+ "decoder.encode.conv1",
33
+ "decoder.encode.conv1x1",
34
+ "decoder.encode.conv2",
35
+ "decoder.encode.norm1.fc",
36
+ "decoder.encode.norm2.fc",
37
+ "decoder.generator.conv_post",
38
+ "decoder.generator.noise_convs.0",
39
+ "decoder.generator.noise_convs.1",
40
+ "decoder.generator.noise_res.0.adain1.0.fc",
41
+ "decoder.generator.noise_res.0.adain1.1.fc",
42
+ "decoder.generator.noise_res.0.adain1.2.fc",
43
+ "decoder.generator.noise_res.0.adain2.0.fc",
44
+ "decoder.generator.noise_res.0.adain2.1.fc",
45
+ "decoder.generator.noise_res.0.adain2.2.fc",
46
+ "decoder.generator.noise_res.0.convs1.0",
47
+ "decoder.generator.noise_res.0.convs1.1",
48
+ "decoder.generator.noise_res.0.convs1.2",
49
+ "decoder.generator.noise_res.0.convs2.0",
50
+ "decoder.generator.noise_res.0.convs2.1",
51
+ "decoder.generator.noise_res.0.convs2.2",
52
+ "decoder.generator.noise_res.1.adain1.0.fc",
53
+ "decoder.generator.noise_res.1.adain1.1.fc",
54
+ "decoder.generator.noise_res.1.adain1.2.fc",
55
+ "decoder.generator.noise_res.1.adain2.0.fc",
56
+ "decoder.generator.noise_res.1.adain2.1.fc",
57
+ "decoder.generator.noise_res.1.adain2.2.fc",
58
+ "decoder.generator.noise_res.1.convs1.0",
59
+ "decoder.generator.noise_res.1.convs1.1",
60
+ "decoder.generator.noise_res.1.convs1.2",
61
+ "decoder.generator.noise_res.1.convs2.0",
62
+ "decoder.generator.noise_res.1.convs2.1",
63
+ "decoder.generator.noise_res.1.convs2.2",
64
+ "decoder.generator.resblocks.0.adain1.0.fc",
65
+ "decoder.generator.resblocks.0.adain1.1.fc",
66
+ "decoder.generator.resblocks.0.adain1.2.fc",
67
+ "decoder.generator.resblocks.0.adain2.0.fc",
68
+ "decoder.generator.resblocks.0.adain2.1.fc",
69
+ "decoder.generator.resblocks.0.adain2.2.fc",
70
+ "decoder.generator.resblocks.0.convs1.0",
71
+ "decoder.generator.resblocks.0.convs1.1",
72
+ "decoder.generator.resblocks.0.convs1.2",
73
+ "decoder.generator.resblocks.0.convs2.0",
74
+ "decoder.generator.resblocks.0.convs2.1",
75
+ "decoder.generator.resblocks.0.convs2.2",
76
+ "decoder.generator.resblocks.1.adain1.0.fc",
77
+ "decoder.generator.resblocks.1.adain1.1.fc",
78
+ "decoder.generator.resblocks.1.adain1.2.fc",
79
+ "decoder.generator.resblocks.1.adain2.0.fc",
80
+ "decoder.generator.resblocks.1.adain2.1.fc",
81
+ "decoder.generator.resblocks.1.adain2.2.fc",
82
+ "decoder.generator.resblocks.1.convs1.0",
83
+ "decoder.generator.resblocks.1.convs1.1",
84
+ "decoder.generator.resblocks.1.convs1.2",
85
+ "decoder.generator.resblocks.1.convs2.0",
86
+ "decoder.generator.resblocks.1.convs2.1",
87
+ "decoder.generator.resblocks.1.convs2.2",
88
+ "decoder.generator.resblocks.2.adain1.0.fc",
89
+ "decoder.generator.resblocks.2.adain1.1.fc",
90
+ "decoder.generator.resblocks.2.adain1.2.fc",
91
+ "decoder.generator.resblocks.2.adain2.0.fc",
92
+ "decoder.generator.resblocks.2.adain2.1.fc",
93
+ "decoder.generator.resblocks.2.adain2.2.fc",
94
+ "decoder.generator.resblocks.2.convs1.0",
95
+ "decoder.generator.resblocks.2.convs1.1",
96
+ "decoder.generator.resblocks.2.convs1.2",
97
+ "decoder.generator.resblocks.2.convs2.0",
98
+ "decoder.generator.resblocks.2.convs2.1",
99
+ "decoder.generator.resblocks.2.convs2.2",
100
+ "decoder.generator.resblocks.3.adain1.0.fc",
101
+ "decoder.generator.resblocks.3.adain1.1.fc",
102
+ "decoder.generator.resblocks.3.adain1.2.fc",
103
+ "decoder.generator.resblocks.3.adain2.0.fc",
104
+ "decoder.generator.resblocks.3.adain2.1.fc",
105
+ "decoder.generator.resblocks.3.adain2.2.fc",
106
+ "decoder.generator.resblocks.3.convs1.0",
107
+ "decoder.generator.resblocks.3.convs1.1",
108
+ "decoder.generator.resblocks.3.convs1.2",
109
+ "decoder.generator.resblocks.3.convs2.0",
110
+ "decoder.generator.resblocks.3.convs2.1",
111
+ "decoder.generator.resblocks.3.convs2.2",
112
+ "predictor.F0.0.conv1",
113
+ "predictor.F0.0.conv2",
114
+ "predictor.F0.0.norm1.fc",
115
+ "predictor.F0.0.norm2.fc",
116
+ "predictor.F0.1.conv1",
117
+ "predictor.F0.1.conv1x1",
118
+ "predictor.F0.1.conv2",
119
+ "predictor.F0.1.norm1.fc",
120
+ "predictor.F0.1.norm2.fc",
121
+ "predictor.F0.2.conv1",
122
+ "predictor.F0.2.conv2",
123
+ "predictor.F0.2.norm1.fc",
124
+ "predictor.F0.2.norm2.fc",
125
+ "predictor.F0_proj",
126
+ "predictor.N.0.conv1",
127
+ "predictor.N.0.conv2",
128
+ "predictor.N.0.norm1.fc",
129
+ "predictor.N.0.norm2.fc",
130
+ "predictor.N.1.conv1",
131
+ "predictor.N.1.conv1x1",
132
+ "predictor.N.1.conv2",
133
+ "predictor.N.1.norm1.fc",
134
+ "predictor.N.1.norm2.fc",
135
+ "predictor.N.2.conv1",
136
+ "predictor.N.2.conv2",
137
+ "predictor.N.2.norm1.fc",
138
+ "predictor.N.2.norm2.fc",
139
+ "predictor.N_proj",
140
+ "predictor.lstm",
141
+ "predictor.shared",
142
+ "predictor.text_encoder.lstms.0",
143
+ "predictor.text_encoder.lstms.1.fc",
144
+ "predictor.text_encoder.lstms.2",
145
+ "predictor.text_encoder.lstms.3.fc",
146
+ "predictor.text_encoder.lstms.4",
147
+ "predictor.text_encoder.lstms.5.fc",
148
+ "text_encoder.cnn.0.0",
149
+ "text_encoder.cnn.1.0",
150
+ "text_encoder.cnn.2.0",
151
+ "text_encoder.lstm"
152
+ ],
153
+ "asr_res_dim": 64,
154
+ "decoder_out_dim": 512,
155
+ "hidden_dim": 512,
156
+ "istftnet": {
157
+ "resblock_kernel_sizes": [
158
+ 3,
159
+ 3
160
+ ],
161
+ "upsample_rates": [
162
+ 10,
163
+ 6
164
+ ],
165
+ "upsample_initial_channel": 512,
166
+ "resblock_dilation_sizes": [
167
+ [
168
+ 1,
169
+ 3,
170
+ 5
171
+ ],
172
+ [
173
+ 1,
174
+ 3,
175
+ 5
176
+ ]
177
+ ],
178
+ "upsample_kernel_sizes": [
179
+ 20,
180
+ 12
181
+ ],
182
+ "gen_istft_n_fft": 20,
183
+ "gen_istft_hop_size": 5
184
+ },
185
+ "max_conv_dim": 1024,
186
+ "max_dur": 50,
187
+ "model_type": "kitten_tts",
188
+ "n_layer": 3,
189
+ "n_mels": 80,
190
+ "n_token": 178,
191
+ "plbert": {
192
+ "num_hidden_layers": 12,
193
+ "num_attention_heads": 12,
194
+ "hidden_size": 768,
195
+ "intermediate_size": 2048,
196
+ "max_position_embeddings": 512,
197
+ "embedding_size": 128,
198
+ "inner_group_num": 1,
199
+ "num_hidden_groups": 1,
200
+ "hidden_dropout_prob": 0.0,
201
+ "attention_probs_dropout_prob": 0.0,
202
+ "type_vocab_size": 2,
203
+ "layer_norm_eps": 1e-12
204
+ },
205
+ "sample_rate": 24000,
206
+ "speed_priors": {},
207
+ "style_dim": 128,
208
+ "text_encoder_kernel_size": 5,
209
+ "voice_aliases": {
210
+ "Bella": "expr-voice-2-f",
211
+ "Jasper": "expr-voice-2-m",
212
+ "Luna": "expr-voice-3-f",
213
+ "Bruno": "expr-voice-3-m",
214
+ "Rosie": "expr-voice-4-f",
215
+ "Hugo": "expr-voice-4-m",
216
+ "Kiki": "expr-voice-5-f",
217
+ "Leo": "expr-voice-5-m"
218
+ },
219
+ "voices_path": "voices.npz"
220
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61f5336dd8ca3f5a63a1a9b458755f4dda39067d16806c7700977696a2ef600f
3
+ size 289104072
model.safetensors.index.json ADDED
@@ -0,0 +1,484 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 289051572,
4
+ "total_parameters": 73782354
5
+ },
6
+ "weight_map": {
7
+ "bert.embeddings.LayerNorm.bias": "model.safetensors",
8
+ "bert.embeddings.LayerNorm.weight": "model.safetensors",
9
+ "bert.embeddings.position_embeddings.weight": "model.safetensors",
10
+ "bert.embeddings.token_type_embeddings.weight": "model.safetensors",
11
+ "bert.embeddings.word_embeddings.weight": "model.safetensors",
12
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.LayerNorm.bias": "model.safetensors",
13
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.LayerNorm.weight": "model.safetensors",
14
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.dense.bias": "model.safetensors",
15
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.dense.weight": "model.safetensors",
16
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.key.bias": "model.safetensors",
17
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.key.weight": "model.safetensors",
18
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.query.bias": "model.safetensors",
19
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.query.weight": "model.safetensors",
20
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.value.bias": "model.safetensors",
21
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.value.weight": "model.safetensors",
22
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn.bias": "model.safetensors",
23
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn.weight": "model.safetensors",
24
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn_output.bias": "model.safetensors",
25
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn_output.weight": "model.safetensors",
26
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.full_layer_layer_norm.bias": "model.safetensors",
27
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.full_layer_layer_norm.weight": "model.safetensors",
28
+ "bert.encoder.embedding_hidden_mapping_in.bias": "model.safetensors",
29
+ "bert.encoder.embedding_hidden_mapping_in.weight": "model.safetensors",
30
+ "bert.pooler.bias": "model.safetensors",
31
+ "bert.pooler.weight": "model.safetensors",
32
+ "bert_encoder.bias": "model.safetensors",
33
+ "bert_encoder.weight": "model.safetensors",
34
+ "decoder.F0_conv.bias": "model.safetensors",
35
+ "decoder.F0_conv.weight_g": "model.safetensors",
36
+ "decoder.F0_conv.weight_v": "model.safetensors",
37
+ "decoder.N_conv.bias": "model.safetensors",
38
+ "decoder.N_conv.weight_g": "model.safetensors",
39
+ "decoder.N_conv.weight_v": "model.safetensors",
40
+ "decoder.asr_res.0.bias": "model.safetensors",
41
+ "decoder.asr_res.0.weight_g": "model.safetensors",
42
+ "decoder.asr_res.0.weight_v": "model.safetensors",
43
+ "decoder.decode.0.conv1.bias": "model.safetensors",
44
+ "decoder.decode.0.conv1.weight_g": "model.safetensors",
45
+ "decoder.decode.0.conv1.weight_v": "model.safetensors",
46
+ "decoder.decode.0.conv1x1.weight_g": "model.safetensors",
47
+ "decoder.decode.0.conv1x1.weight_v": "model.safetensors",
48
+ "decoder.decode.0.conv2.bias": "model.safetensors",
49
+ "decoder.decode.0.conv2.weight_g": "model.safetensors",
50
+ "decoder.decode.0.conv2.weight_v": "model.safetensors",
51
+ "decoder.decode.0.norm1.fc.bias": "model.safetensors",
52
+ "decoder.decode.0.norm1.fc.weight": "model.safetensors",
53
+ "decoder.decode.0.norm2.fc.bias": "model.safetensors",
54
+ "decoder.decode.0.norm2.fc.weight": "model.safetensors",
55
+ "decoder.decode.1.conv1.bias": "model.safetensors",
56
+ "decoder.decode.1.conv1.weight_g": "model.safetensors",
57
+ "decoder.decode.1.conv1.weight_v": "model.safetensors",
58
+ "decoder.decode.1.conv1x1.weight_g": "model.safetensors",
59
+ "decoder.decode.1.conv1x1.weight_v": "model.safetensors",
60
+ "decoder.decode.1.conv2.bias": "model.safetensors",
61
+ "decoder.decode.1.conv2.weight_g": "model.safetensors",
62
+ "decoder.decode.1.conv2.weight_v": "model.safetensors",
63
+ "decoder.decode.1.norm1.fc.bias": "model.safetensors",
64
+ "decoder.decode.1.norm1.fc.weight": "model.safetensors",
65
+ "decoder.decode.1.norm2.fc.bias": "model.safetensors",
66
+ "decoder.decode.1.norm2.fc.weight": "model.safetensors",
67
+ "decoder.decode.2.conv1.bias": "model.safetensors",
68
+ "decoder.decode.2.conv1.weight_g": "model.safetensors",
69
+ "decoder.decode.2.conv1.weight_v": "model.safetensors",
70
+ "decoder.decode.2.conv1x1.weight_g": "model.safetensors",
71
+ "decoder.decode.2.conv1x1.weight_v": "model.safetensors",
72
+ "decoder.decode.2.conv2.bias": "model.safetensors",
73
+ "decoder.decode.2.conv2.weight_g": "model.safetensors",
74
+ "decoder.decode.2.conv2.weight_v": "model.safetensors",
75
+ "decoder.decode.2.norm1.fc.bias": "model.safetensors",
76
+ "decoder.decode.2.norm1.fc.weight": "model.safetensors",
77
+ "decoder.decode.2.norm2.fc.bias": "model.safetensors",
78
+ "decoder.decode.2.norm2.fc.weight": "model.safetensors",
79
+ "decoder.decode.3.conv1.bias": "model.safetensors",
80
+ "decoder.decode.3.conv1.weight_g": "model.safetensors",
81
+ "decoder.decode.3.conv1.weight_v": "model.safetensors",
82
+ "decoder.decode.3.conv1x1.weight_g": "model.safetensors",
83
+ "decoder.decode.3.conv1x1.weight_v": "model.safetensors",
84
+ "decoder.decode.3.conv2.bias": "model.safetensors",
85
+ "decoder.decode.3.conv2.weight_g": "model.safetensors",
86
+ "decoder.decode.3.conv2.weight_v": "model.safetensors",
87
+ "decoder.decode.3.norm1.fc.bias": "model.safetensors",
88
+ "decoder.decode.3.norm1.fc.weight": "model.safetensors",
89
+ "decoder.decode.3.norm2.fc.bias": "model.safetensors",
90
+ "decoder.decode.3.norm2.fc.weight": "model.safetensors",
91
+ "decoder.decode.3.pool.bias": "model.safetensors",
92
+ "decoder.decode.3.pool.weight_g": "model.safetensors",
93
+ "decoder.decode.3.pool.weight_v": "model.safetensors",
94
+ "decoder.encode.conv1.bias": "model.safetensors",
95
+ "decoder.encode.conv1.weight_g": "model.safetensors",
96
+ "decoder.encode.conv1.weight_v": "model.safetensors",
97
+ "decoder.encode.conv1x1.weight_g": "model.safetensors",
98
+ "decoder.encode.conv1x1.weight_v": "model.safetensors",
99
+ "decoder.encode.conv2.bias": "model.safetensors",
100
+ "decoder.encode.conv2.weight_g": "model.safetensors",
101
+ "decoder.encode.conv2.weight_v": "model.safetensors",
102
+ "decoder.encode.norm1.fc.bias": "model.safetensors",
103
+ "decoder.encode.norm1.fc.weight": "model.safetensors",
104
+ "decoder.encode.norm2.fc.bias": "model.safetensors",
105
+ "decoder.encode.norm2.fc.weight": "model.safetensors",
106
+ "decoder.generator.conv_post.bias": "model.safetensors",
107
+ "decoder.generator.conv_post.weight_g": "model.safetensors",
108
+ "decoder.generator.conv_post.weight_v": "model.safetensors",
109
+ "decoder.generator.m_source.l_linear.bias": "model.safetensors",
110
+ "decoder.generator.m_source.l_linear.weight": "model.safetensors",
111
+ "decoder.generator.noise_convs.0.bias": "model.safetensors",
112
+ "decoder.generator.noise_convs.0.weight": "model.safetensors",
113
+ "decoder.generator.noise_convs.1.bias": "model.safetensors",
114
+ "decoder.generator.noise_convs.1.weight": "model.safetensors",
115
+ "decoder.generator.noise_res.0.adain1.0.fc.bias": "model.safetensors",
116
+ "decoder.generator.noise_res.0.adain1.0.fc.weight": "model.safetensors",
117
+ "decoder.generator.noise_res.0.adain1.1.fc.bias": "model.safetensors",
118
+ "decoder.generator.noise_res.0.adain1.1.fc.weight": "model.safetensors",
119
+ "decoder.generator.noise_res.0.adain1.2.fc.bias": "model.safetensors",
120
+ "decoder.generator.noise_res.0.adain1.2.fc.weight": "model.safetensors",
121
+ "decoder.generator.noise_res.0.adain2.0.fc.bias": "model.safetensors",
122
+ "decoder.generator.noise_res.0.adain2.0.fc.weight": "model.safetensors",
123
+ "decoder.generator.noise_res.0.adain2.1.fc.bias": "model.safetensors",
124
+ "decoder.generator.noise_res.0.adain2.1.fc.weight": "model.safetensors",
125
+ "decoder.generator.noise_res.0.adain2.2.fc.bias": "model.safetensors",
126
+ "decoder.generator.noise_res.0.adain2.2.fc.weight": "model.safetensors",
127
+ "decoder.generator.noise_res.0.alpha1_0": "model.safetensors",
128
+ "decoder.generator.noise_res.0.alpha1_1": "model.safetensors",
129
+ "decoder.generator.noise_res.0.alpha1_2": "model.safetensors",
130
+ "decoder.generator.noise_res.0.alpha2_0": "model.safetensors",
131
+ "decoder.generator.noise_res.0.alpha2_1": "model.safetensors",
132
+ "decoder.generator.noise_res.0.alpha2_2": "model.safetensors",
133
+ "decoder.generator.noise_res.0.convs1.0.bias": "model.safetensors",
134
+ "decoder.generator.noise_res.0.convs1.0.weight_g": "model.safetensors",
135
+ "decoder.generator.noise_res.0.convs1.0.weight_v": "model.safetensors",
136
+ "decoder.generator.noise_res.0.convs1.1.bias": "model.safetensors",
137
+ "decoder.generator.noise_res.0.convs1.1.weight_g": "model.safetensors",
138
+ "decoder.generator.noise_res.0.convs1.1.weight_v": "model.safetensors",
139
+ "decoder.generator.noise_res.0.convs1.2.bias": "model.safetensors",
140
+ "decoder.generator.noise_res.0.convs1.2.weight_g": "model.safetensors",
141
+ "decoder.generator.noise_res.0.convs1.2.weight_v": "model.safetensors",
142
+ "decoder.generator.noise_res.0.convs2.0.bias": "model.safetensors",
143
+ "decoder.generator.noise_res.0.convs2.0.weight_g": "model.safetensors",
144
+ "decoder.generator.noise_res.0.convs2.0.weight_v": "model.safetensors",
145
+ "decoder.generator.noise_res.0.convs2.1.bias": "model.safetensors",
146
+ "decoder.generator.noise_res.0.convs2.1.weight_g": "model.safetensors",
147
+ "decoder.generator.noise_res.0.convs2.1.weight_v": "model.safetensors",
148
+ "decoder.generator.noise_res.0.convs2.2.bias": "model.safetensors",
149
+ "decoder.generator.noise_res.0.convs2.2.weight_g": "model.safetensors",
150
+ "decoder.generator.noise_res.0.convs2.2.weight_v": "model.safetensors",
151
+ "decoder.generator.noise_res.1.adain1.0.fc.bias": "model.safetensors",
152
+ "decoder.generator.noise_res.1.adain1.0.fc.weight": "model.safetensors",
153
+ "decoder.generator.noise_res.1.adain1.1.fc.bias": "model.safetensors",
154
+ "decoder.generator.noise_res.1.adain1.1.fc.weight": "model.safetensors",
155
+ "decoder.generator.noise_res.1.adain1.2.fc.bias": "model.safetensors",
156
+ "decoder.generator.noise_res.1.adain1.2.fc.weight": "model.safetensors",
157
+ "decoder.generator.noise_res.1.adain2.0.fc.bias": "model.safetensors",
158
+ "decoder.generator.noise_res.1.adain2.0.fc.weight": "model.safetensors",
159
+ "decoder.generator.noise_res.1.adain2.1.fc.bias": "model.safetensors",
160
+ "decoder.generator.noise_res.1.adain2.1.fc.weight": "model.safetensors",
161
+ "decoder.generator.noise_res.1.adain2.2.fc.bias": "model.safetensors",
162
+ "decoder.generator.noise_res.1.adain2.2.fc.weight": "model.safetensors",
163
+ "decoder.generator.noise_res.1.alpha1_0": "model.safetensors",
164
+ "decoder.generator.noise_res.1.alpha1_1": "model.safetensors",
165
+ "decoder.generator.noise_res.1.alpha1_2": "model.safetensors",
166
+ "decoder.generator.noise_res.1.alpha2_0": "model.safetensors",
167
+ "decoder.generator.noise_res.1.alpha2_1": "model.safetensors",
168
+ "decoder.generator.noise_res.1.alpha2_2": "model.safetensors",
169
+ "decoder.generator.noise_res.1.convs1.0.bias": "model.safetensors",
170
+ "decoder.generator.noise_res.1.convs1.0.weight_g": "model.safetensors",
171
+ "decoder.generator.noise_res.1.convs1.0.weight_v": "model.safetensors",
172
+ "decoder.generator.noise_res.1.convs1.1.bias": "model.safetensors",
173
+ "decoder.generator.noise_res.1.convs1.1.weight_g": "model.safetensors",
174
+ "decoder.generator.noise_res.1.convs1.1.weight_v": "model.safetensors",
175
+ "decoder.generator.noise_res.1.convs1.2.bias": "model.safetensors",
176
+ "decoder.generator.noise_res.1.convs1.2.weight_g": "model.safetensors",
177
+ "decoder.generator.noise_res.1.convs1.2.weight_v": "model.safetensors",
178
+ "decoder.generator.noise_res.1.convs2.0.bias": "model.safetensors",
179
+ "decoder.generator.noise_res.1.convs2.0.weight_g": "model.safetensors",
180
+ "decoder.generator.noise_res.1.convs2.0.weight_v": "model.safetensors",
181
+ "decoder.generator.noise_res.1.convs2.1.bias": "model.safetensors",
182
+ "decoder.generator.noise_res.1.convs2.1.weight_g": "model.safetensors",
183
+ "decoder.generator.noise_res.1.convs2.1.weight_v": "model.safetensors",
184
+ "decoder.generator.noise_res.1.convs2.2.bias": "model.safetensors",
185
+ "decoder.generator.noise_res.1.convs2.2.weight_g": "model.safetensors",
186
+ "decoder.generator.noise_res.1.convs2.2.weight_v": "model.safetensors",
187
+ "decoder.generator.resblocks.0.adain1.0.fc.bias": "model.safetensors",
188
+ "decoder.generator.resblocks.0.adain1.0.fc.weight": "model.safetensors",
189
+ "decoder.generator.resblocks.0.adain1.1.fc.bias": "model.safetensors",
190
+ "decoder.generator.resblocks.0.adain1.1.fc.weight": "model.safetensors",
191
+ "decoder.generator.resblocks.0.adain1.2.fc.bias": "model.safetensors",
192
+ "decoder.generator.resblocks.0.adain1.2.fc.weight": "model.safetensors",
193
+ "decoder.generator.resblocks.0.adain2.0.fc.bias": "model.safetensors",
194
+ "decoder.generator.resblocks.0.adain2.0.fc.weight": "model.safetensors",
195
+ "decoder.generator.resblocks.0.adain2.1.fc.bias": "model.safetensors",
196
+ "decoder.generator.resblocks.0.adain2.1.fc.weight": "model.safetensors",
197
+ "decoder.generator.resblocks.0.adain2.2.fc.bias": "model.safetensors",
198
+ "decoder.generator.resblocks.0.adain2.2.fc.weight": "model.safetensors",
199
+ "decoder.generator.resblocks.0.alpha1_0": "model.safetensors",
200
+ "decoder.generator.resblocks.0.alpha1_1": "model.safetensors",
201
+ "decoder.generator.resblocks.0.alpha1_2": "model.safetensors",
202
+ "decoder.generator.resblocks.0.alpha2_0": "model.safetensors",
203
+ "decoder.generator.resblocks.0.alpha2_1": "model.safetensors",
204
+ "decoder.generator.resblocks.0.alpha2_2": "model.safetensors",
205
+ "decoder.generator.resblocks.0.convs1.0.bias": "model.safetensors",
206
+ "decoder.generator.resblocks.0.convs1.0.weight_g": "model.safetensors",
207
+ "decoder.generator.resblocks.0.convs1.0.weight_v": "model.safetensors",
208
+ "decoder.generator.resblocks.0.convs1.1.bias": "model.safetensors",
209
+ "decoder.generator.resblocks.0.convs1.1.weight_g": "model.safetensors",
210
+ "decoder.generator.resblocks.0.convs1.1.weight_v": "model.safetensors",
211
+ "decoder.generator.resblocks.0.convs1.2.bias": "model.safetensors",
212
+ "decoder.generator.resblocks.0.convs1.2.weight_g": "model.safetensors",
213
+ "decoder.generator.resblocks.0.convs1.2.weight_v": "model.safetensors",
214
+ "decoder.generator.resblocks.0.convs2.0.bias": "model.safetensors",
215
+ "decoder.generator.resblocks.0.convs2.0.weight_g": "model.safetensors",
216
+ "decoder.generator.resblocks.0.convs2.0.weight_v": "model.safetensors",
217
+ "decoder.generator.resblocks.0.convs2.1.bias": "model.safetensors",
218
+ "decoder.generator.resblocks.0.convs2.1.weight_g": "model.safetensors",
219
+ "decoder.generator.resblocks.0.convs2.1.weight_v": "model.safetensors",
220
+ "decoder.generator.resblocks.0.convs2.2.bias": "model.safetensors",
221
+ "decoder.generator.resblocks.0.convs2.2.weight_g": "model.safetensors",
222
+ "decoder.generator.resblocks.0.convs2.2.weight_v": "model.safetensors",
223
+ "decoder.generator.resblocks.1.adain1.0.fc.bias": "model.safetensors",
224
+ "decoder.generator.resblocks.1.adain1.0.fc.weight": "model.safetensors",
225
+ "decoder.generator.resblocks.1.adain1.1.fc.bias": "model.safetensors",
226
+ "decoder.generator.resblocks.1.adain1.1.fc.weight": "model.safetensors",
227
+ "decoder.generator.resblocks.1.adain1.2.fc.bias": "model.safetensors",
228
+ "decoder.generator.resblocks.1.adain1.2.fc.weight": "model.safetensors",
229
+ "decoder.generator.resblocks.1.adain2.0.fc.bias": "model.safetensors",
230
+ "decoder.generator.resblocks.1.adain2.0.fc.weight": "model.safetensors",
231
+ "decoder.generator.resblocks.1.adain2.1.fc.bias": "model.safetensors",
232
+ "decoder.generator.resblocks.1.adain2.1.fc.weight": "model.safetensors",
233
+ "decoder.generator.resblocks.1.adain2.2.fc.bias": "model.safetensors",
234
+ "decoder.generator.resblocks.1.adain2.2.fc.weight": "model.safetensors",
235
+ "decoder.generator.resblocks.1.alpha1_0": "model.safetensors",
236
+ "decoder.generator.resblocks.1.alpha1_1": "model.safetensors",
237
+ "decoder.generator.resblocks.1.alpha1_2": "model.safetensors",
238
+ "decoder.generator.resblocks.1.alpha2_0": "model.safetensors",
239
+ "decoder.generator.resblocks.1.alpha2_1": "model.safetensors",
240
+ "decoder.generator.resblocks.1.alpha2_2": "model.safetensors",
241
+ "decoder.generator.resblocks.1.convs1.0.bias": "model.safetensors",
242
+ "decoder.generator.resblocks.1.convs1.0.weight_g": "model.safetensors",
243
+ "decoder.generator.resblocks.1.convs1.0.weight_v": "model.safetensors",
244
+ "decoder.generator.resblocks.1.convs1.1.bias": "model.safetensors",
245
+ "decoder.generator.resblocks.1.convs1.1.weight_g": "model.safetensors",
246
+ "decoder.generator.resblocks.1.convs1.1.weight_v": "model.safetensors",
247
+ "decoder.generator.resblocks.1.convs1.2.bias": "model.safetensors",
248
+ "decoder.generator.resblocks.1.convs1.2.weight_g": "model.safetensors",
249
+ "decoder.generator.resblocks.1.convs1.2.weight_v": "model.safetensors",
250
+ "decoder.generator.resblocks.1.convs2.0.bias": "model.safetensors",
251
+ "decoder.generator.resblocks.1.convs2.0.weight_g": "model.safetensors",
252
+ "decoder.generator.resblocks.1.convs2.0.weight_v": "model.safetensors",
253
+ "decoder.generator.resblocks.1.convs2.1.bias": "model.safetensors",
254
+ "decoder.generator.resblocks.1.convs2.1.weight_g": "model.safetensors",
255
+ "decoder.generator.resblocks.1.convs2.1.weight_v": "model.safetensors",
256
+ "decoder.generator.resblocks.1.convs2.2.bias": "model.safetensors",
257
+ "decoder.generator.resblocks.1.convs2.2.weight_g": "model.safetensors",
258
+ "decoder.generator.resblocks.1.convs2.2.weight_v": "model.safetensors",
259
+ "decoder.generator.resblocks.2.adain1.0.fc.bias": "model.safetensors",
260
+ "decoder.generator.resblocks.2.adain1.0.fc.weight": "model.safetensors",
261
+ "decoder.generator.resblocks.2.adain1.1.fc.bias": "model.safetensors",
262
+ "decoder.generator.resblocks.2.adain1.1.fc.weight": "model.safetensors",
263
+ "decoder.generator.resblocks.2.adain1.2.fc.bias": "model.safetensors",
264
+ "decoder.generator.resblocks.2.adain1.2.fc.weight": "model.safetensors",
265
+ "decoder.generator.resblocks.2.adain2.0.fc.bias": "model.safetensors",
266
+ "decoder.generator.resblocks.2.adain2.0.fc.weight": "model.safetensors",
267
+ "decoder.generator.resblocks.2.adain2.1.fc.bias": "model.safetensors",
268
+ "decoder.generator.resblocks.2.adain2.1.fc.weight": "model.safetensors",
269
+ "decoder.generator.resblocks.2.adain2.2.fc.bias": "model.safetensors",
270
+ "decoder.generator.resblocks.2.adain2.2.fc.weight": "model.safetensors",
271
+ "decoder.generator.resblocks.2.alpha1_0": "model.safetensors",
272
+ "decoder.generator.resblocks.2.alpha1_1": "model.safetensors",
273
+ "decoder.generator.resblocks.2.alpha1_2": "model.safetensors",
274
+ "decoder.generator.resblocks.2.alpha2_0": "model.safetensors",
275
+ "decoder.generator.resblocks.2.alpha2_1": "model.safetensors",
276
+ "decoder.generator.resblocks.2.alpha2_2": "model.safetensors",
277
+ "decoder.generator.resblocks.2.convs1.0.bias": "model.safetensors",
278
+ "decoder.generator.resblocks.2.convs1.0.weight_g": "model.safetensors",
279
+ "decoder.generator.resblocks.2.convs1.0.weight_v": "model.safetensors",
280
+ "decoder.generator.resblocks.2.convs1.1.bias": "model.safetensors",
281
+ "decoder.generator.resblocks.2.convs1.1.weight_g": "model.safetensors",
282
+ "decoder.generator.resblocks.2.convs1.1.weight_v": "model.safetensors",
283
+ "decoder.generator.resblocks.2.convs1.2.bias": "model.safetensors",
284
+ "decoder.generator.resblocks.2.convs1.2.weight_g": "model.safetensors",
285
+ "decoder.generator.resblocks.2.convs1.2.weight_v": "model.safetensors",
286
+ "decoder.generator.resblocks.2.convs2.0.bias": "model.safetensors",
287
+ "decoder.generator.resblocks.2.convs2.0.weight_g": "model.safetensors",
288
+ "decoder.generator.resblocks.2.convs2.0.weight_v": "model.safetensors",
289
+ "decoder.generator.resblocks.2.convs2.1.bias": "model.safetensors",
290
+ "decoder.generator.resblocks.2.convs2.1.weight_g": "model.safetensors",
291
+ "decoder.generator.resblocks.2.convs2.1.weight_v": "model.safetensors",
292
+ "decoder.generator.resblocks.2.convs2.2.bias": "model.safetensors",
293
+ "decoder.generator.resblocks.2.convs2.2.weight_g": "model.safetensors",
294
+ "decoder.generator.resblocks.2.convs2.2.weight_v": "model.safetensors",
295
+ "decoder.generator.resblocks.3.adain1.0.fc.bias": "model.safetensors",
296
+ "decoder.generator.resblocks.3.adain1.0.fc.weight": "model.safetensors",
297
+ "decoder.generator.resblocks.3.adain1.1.fc.bias": "model.safetensors",
298
+ "decoder.generator.resblocks.3.adain1.1.fc.weight": "model.safetensors",
299
+ "decoder.generator.resblocks.3.adain1.2.fc.bias": "model.safetensors",
300
+ "decoder.generator.resblocks.3.adain1.2.fc.weight": "model.safetensors",
301
+ "decoder.generator.resblocks.3.adain2.0.fc.bias": "model.safetensors",
302
+ "decoder.generator.resblocks.3.adain2.0.fc.weight": "model.safetensors",
303
+ "decoder.generator.resblocks.3.adain2.1.fc.bias": "model.safetensors",
304
+ "decoder.generator.resblocks.3.adain2.1.fc.weight": "model.safetensors",
305
+ "decoder.generator.resblocks.3.adain2.2.fc.bias": "model.safetensors",
306
+ "decoder.generator.resblocks.3.adain2.2.fc.weight": "model.safetensors",
307
+ "decoder.generator.resblocks.3.alpha1_0": "model.safetensors",
308
+ "decoder.generator.resblocks.3.alpha1_1": "model.safetensors",
309
+ "decoder.generator.resblocks.3.alpha1_2": "model.safetensors",
310
+ "decoder.generator.resblocks.3.alpha2_0": "model.safetensors",
311
+ "decoder.generator.resblocks.3.alpha2_1": "model.safetensors",
312
+ "decoder.generator.resblocks.3.alpha2_2": "model.safetensors",
313
+ "decoder.generator.resblocks.3.convs1.0.bias": "model.safetensors",
314
+ "decoder.generator.resblocks.3.convs1.0.weight_g": "model.safetensors",
315
+ "decoder.generator.resblocks.3.convs1.0.weight_v": "model.safetensors",
316
+ "decoder.generator.resblocks.3.convs1.1.bias": "model.safetensors",
317
+ "decoder.generator.resblocks.3.convs1.1.weight_g": "model.safetensors",
318
+ "decoder.generator.resblocks.3.convs1.1.weight_v": "model.safetensors",
319
+ "decoder.generator.resblocks.3.convs1.2.bias": "model.safetensors",
320
+ "decoder.generator.resblocks.3.convs1.2.weight_g": "model.safetensors",
321
+ "decoder.generator.resblocks.3.convs1.2.weight_v": "model.safetensors",
322
+ "decoder.generator.resblocks.3.convs2.0.bias": "model.safetensors",
323
+ "decoder.generator.resblocks.3.convs2.0.weight_g": "model.safetensors",
324
+ "decoder.generator.resblocks.3.convs2.0.weight_v": "model.safetensors",
325
+ "decoder.generator.resblocks.3.convs2.1.bias": "model.safetensors",
326
+ "decoder.generator.resblocks.3.convs2.1.weight_g": "model.safetensors",
327
+ "decoder.generator.resblocks.3.convs2.1.weight_v": "model.safetensors",
328
+ "decoder.generator.resblocks.3.convs2.2.bias": "model.safetensors",
329
+ "decoder.generator.resblocks.3.convs2.2.weight_g": "model.safetensors",
330
+ "decoder.generator.resblocks.3.convs2.2.weight_v": "model.safetensors",
331
+ "decoder.generator.ups.0.bias": "model.safetensors",
332
+ "decoder.generator.ups.0.weight_g": "model.safetensors",
333
+ "decoder.generator.ups.0.weight_v": "model.safetensors",
334
+ "decoder.generator.ups.1.bias": "model.safetensors",
335
+ "decoder.generator.ups.1.weight_g": "model.safetensors",
336
+ "decoder.generator.ups.1.weight_v": "model.safetensors",
337
+ "predictor.F0.0.conv1.bias": "model.safetensors",
338
+ "predictor.F0.0.conv1.weight_g": "model.safetensors",
339
+ "predictor.F0.0.conv1.weight_v": "model.safetensors",
340
+ "predictor.F0.0.conv2.bias": "model.safetensors",
341
+ "predictor.F0.0.conv2.weight_g": "model.safetensors",
342
+ "predictor.F0.0.conv2.weight_v": "model.safetensors",
343
+ "predictor.F0.0.norm1.fc.bias": "model.safetensors",
344
+ "predictor.F0.0.norm1.fc.weight": "model.safetensors",
345
+ "predictor.F0.0.norm2.fc.bias": "model.safetensors",
346
+ "predictor.F0.0.norm2.fc.weight": "model.safetensors",
347
+ "predictor.F0.1.conv1.bias": "model.safetensors",
348
+ "predictor.F0.1.conv1.weight_g": "model.safetensors",
349
+ "predictor.F0.1.conv1.weight_v": "model.safetensors",
350
+ "predictor.F0.1.conv1x1.weight_g": "model.safetensors",
351
+ "predictor.F0.1.conv1x1.weight_v": "model.safetensors",
352
+ "predictor.F0.1.conv2.bias": "model.safetensors",
353
+ "predictor.F0.1.conv2.weight_g": "model.safetensors",
354
+ "predictor.F0.1.conv2.weight_v": "model.safetensors",
355
+ "predictor.F0.1.norm1.fc.bias": "model.safetensors",
356
+ "predictor.F0.1.norm1.fc.weight": "model.safetensors",
357
+ "predictor.F0.1.norm2.fc.bias": "model.safetensors",
358
+ "predictor.F0.1.norm2.fc.weight": "model.safetensors",
359
+ "predictor.F0.1.pool.bias": "model.safetensors",
360
+ "predictor.F0.1.pool.weight_g": "model.safetensors",
361
+ "predictor.F0.1.pool.weight_v": "model.safetensors",
362
+ "predictor.F0.2.conv1.bias": "model.safetensors",
363
+ "predictor.F0.2.conv1.weight_g": "model.safetensors",
364
+ "predictor.F0.2.conv1.weight_v": "model.safetensors",
365
+ "predictor.F0.2.conv2.bias": "model.safetensors",
366
+ "predictor.F0.2.conv2.weight_g": "model.safetensors",
367
+ "predictor.F0.2.conv2.weight_v": "model.safetensors",
368
+ "predictor.F0.2.norm1.fc.bias": "model.safetensors",
369
+ "predictor.F0.2.norm1.fc.weight": "model.safetensors",
370
+ "predictor.F0.2.norm2.fc.bias": "model.safetensors",
371
+ "predictor.F0.2.norm2.fc.weight": "model.safetensors",
372
+ "predictor.F0_proj.bias": "model.safetensors",
373
+ "predictor.F0_proj.weight": "model.safetensors",
374
+ "predictor.N.0.conv1.bias": "model.safetensors",
375
+ "predictor.N.0.conv1.weight_g": "model.safetensors",
376
+ "predictor.N.0.conv1.weight_v": "model.safetensors",
377
+ "predictor.N.0.conv2.bias": "model.safetensors",
378
+ "predictor.N.0.conv2.weight_g": "model.safetensors",
379
+ "predictor.N.0.conv2.weight_v": "model.safetensors",
380
+ "predictor.N.0.norm1.fc.bias": "model.safetensors",
381
+ "predictor.N.0.norm1.fc.weight": "model.safetensors",
382
+ "predictor.N.0.norm2.fc.bias": "model.safetensors",
383
+ "predictor.N.0.norm2.fc.weight": "model.safetensors",
384
+ "predictor.N.1.conv1.bias": "model.safetensors",
385
+ "predictor.N.1.conv1.weight_g": "model.safetensors",
386
+ "predictor.N.1.conv1.weight_v": "model.safetensors",
387
+ "predictor.N.1.conv1x1.weight_g": "model.safetensors",
388
+ "predictor.N.1.conv1x1.weight_v": "model.safetensors",
389
+ "predictor.N.1.conv2.bias": "model.safetensors",
390
+ "predictor.N.1.conv2.weight_g": "model.safetensors",
391
+ "predictor.N.1.conv2.weight_v": "model.safetensors",
392
+ "predictor.N.1.norm1.fc.bias": "model.safetensors",
393
+ "predictor.N.1.norm1.fc.weight": "model.safetensors",
394
+ "predictor.N.1.norm2.fc.bias": "model.safetensors",
395
+ "predictor.N.1.norm2.fc.weight": "model.safetensors",
396
+ "predictor.N.1.pool.bias": "model.safetensors",
397
+ "predictor.N.1.pool.weight_g": "model.safetensors",
398
+ "predictor.N.1.pool.weight_v": "model.safetensors",
399
+ "predictor.N.2.conv1.bias": "model.safetensors",
400
+ "predictor.N.2.conv1.weight_g": "model.safetensors",
401
+ "predictor.N.2.conv1.weight_v": "model.safetensors",
402
+ "predictor.N.2.conv2.bias": "model.safetensors",
403
+ "predictor.N.2.conv2.weight_g": "model.safetensors",
404
+ "predictor.N.2.conv2.weight_v": "model.safetensors",
405
+ "predictor.N.2.norm1.fc.bias": "model.safetensors",
406
+ "predictor.N.2.norm1.fc.weight": "model.safetensors",
407
+ "predictor.N.2.norm2.fc.bias": "model.safetensors",
408
+ "predictor.N.2.norm2.fc.weight": "model.safetensors",
409
+ "predictor.N_proj.bias": "model.safetensors",
410
+ "predictor.N_proj.weight": "model.safetensors",
411
+ "predictor.duration_proj.linear_layer.bias": "model.safetensors",
412
+ "predictor.duration_proj.linear_layer.weight": "model.safetensors",
413
+ "predictor.lstm.Wh_backward": "model.safetensors",
414
+ "predictor.lstm.Wh_forward": "model.safetensors",
415
+ "predictor.lstm.Wx_backward": "model.safetensors",
416
+ "predictor.lstm.Wx_forward": "model.safetensors",
417
+ "predictor.lstm.bias_hh_backward": "model.safetensors",
418
+ "predictor.lstm.bias_hh_forward": "model.safetensors",
419
+ "predictor.lstm.bias_ih_backward": "model.safetensors",
420
+ "predictor.lstm.bias_ih_forward": "model.safetensors",
421
+ "predictor.shared.Wh_backward": "model.safetensors",
422
+ "predictor.shared.Wh_forward": "model.safetensors",
423
+ "predictor.shared.Wx_backward": "model.safetensors",
424
+ "predictor.shared.Wx_forward": "model.safetensors",
425
+ "predictor.shared.bias_hh_backward": "model.safetensors",
426
+ "predictor.shared.bias_hh_forward": "model.safetensors",
427
+ "predictor.shared.bias_ih_backward": "model.safetensors",
428
+ "predictor.shared.bias_ih_forward": "model.safetensors",
429
+ "predictor.text_encoder.lstms.0.Wh_backward": "model.safetensors",
430
+ "predictor.text_encoder.lstms.0.Wh_forward": "model.safetensors",
431
+ "predictor.text_encoder.lstms.0.Wx_backward": "model.safetensors",
432
+ "predictor.text_encoder.lstms.0.Wx_forward": "model.safetensors",
433
+ "predictor.text_encoder.lstms.0.bias_hh_backward": "model.safetensors",
434
+ "predictor.text_encoder.lstms.0.bias_hh_forward": "model.safetensors",
435
+ "predictor.text_encoder.lstms.0.bias_ih_backward": "model.safetensors",
436
+ "predictor.text_encoder.lstms.0.bias_ih_forward": "model.safetensors",
437
+ "predictor.text_encoder.lstms.1.fc.bias": "model.safetensors",
438
+ "predictor.text_encoder.lstms.1.fc.weight": "model.safetensors",
439
+ "predictor.text_encoder.lstms.2.Wh_backward": "model.safetensors",
440
+ "predictor.text_encoder.lstms.2.Wh_forward": "model.safetensors",
441
+ "predictor.text_encoder.lstms.2.Wx_backward": "model.safetensors",
442
+ "predictor.text_encoder.lstms.2.Wx_forward": "model.safetensors",
443
+ "predictor.text_encoder.lstms.2.bias_hh_backward": "model.safetensors",
444
+ "predictor.text_encoder.lstms.2.bias_hh_forward": "model.safetensors",
445
+ "predictor.text_encoder.lstms.2.bias_ih_backward": "model.safetensors",
446
+ "predictor.text_encoder.lstms.2.bias_ih_forward": "model.safetensors",
447
+ "predictor.text_encoder.lstms.3.fc.bias": "model.safetensors",
448
+ "predictor.text_encoder.lstms.3.fc.weight": "model.safetensors",
449
+ "predictor.text_encoder.lstms.4.Wh_backward": "model.safetensors",
450
+ "predictor.text_encoder.lstms.4.Wh_forward": "model.safetensors",
451
+ "predictor.text_encoder.lstms.4.Wx_backward": "model.safetensors",
452
+ "predictor.text_encoder.lstms.4.Wx_forward": "model.safetensors",
453
+ "predictor.text_encoder.lstms.4.bias_hh_backward": "model.safetensors",
454
+ "predictor.text_encoder.lstms.4.bias_hh_forward": "model.safetensors",
455
+ "predictor.text_encoder.lstms.4.bias_ih_backward": "model.safetensors",
456
+ "predictor.text_encoder.lstms.4.bias_ih_forward": "model.safetensors",
457
+ "predictor.text_encoder.lstms.5.fc.bias": "model.safetensors",
458
+ "predictor.text_encoder.lstms.5.fc.weight": "model.safetensors",
459
+ "text_encoder.cnn.0.0.bias": "model.safetensors",
460
+ "text_encoder.cnn.0.0.weight_g": "model.safetensors",
461
+ "text_encoder.cnn.0.0.weight_v": "model.safetensors",
462
+ "text_encoder.cnn.0.1.bias": "model.safetensors",
463
+ "text_encoder.cnn.0.1.weight": "model.safetensors",
464
+ "text_encoder.cnn.1.0.bias": "model.safetensors",
465
+ "text_encoder.cnn.1.0.weight_g": "model.safetensors",
466
+ "text_encoder.cnn.1.0.weight_v": "model.safetensors",
467
+ "text_encoder.cnn.1.1.bias": "model.safetensors",
468
+ "text_encoder.cnn.1.1.weight": "model.safetensors",
469
+ "text_encoder.cnn.2.0.bias": "model.safetensors",
470
+ "text_encoder.cnn.2.0.weight_g": "model.safetensors",
471
+ "text_encoder.cnn.2.0.weight_v": "model.safetensors",
472
+ "text_encoder.cnn.2.1.bias": "model.safetensors",
473
+ "text_encoder.cnn.2.1.weight": "model.safetensors",
474
+ "text_encoder.embedding.weight": "model.safetensors",
475
+ "text_encoder.lstm.Wh_backward": "model.safetensors",
476
+ "text_encoder.lstm.Wh_forward": "model.safetensors",
477
+ "text_encoder.lstm.Wx_backward": "model.safetensors",
478
+ "text_encoder.lstm.Wx_forward": "model.safetensors",
479
+ "text_encoder.lstm.bias_hh_backward": "model.safetensors",
480
+ "text_encoder.lstm.bias_hh_forward": "model.safetensors",
481
+ "text_encoder.lstm.bias_ih_backward": "model.safetensors",
482
+ "text_encoder.lstm.bias_ih_forward": "model.safetensors"
483
+ }
484
+ }
voices.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ad2638952b77b7b2f30127e2608e169fc69dd256b53bd8aaa3409a33193c42
3
+ size 3278902