Hugging Face's logo

mlx-community
/
kitten-tts-micro-0.8-8bit

Text-to-Speech
MLX
Safetensors
kitten_tts
kitten-tts
8-bit precision
Model card Files
xet
 Community
Reza2kn commited on
Commit
bbafffb
·
verified ·
1 Parent(s): 942cc57

Add MLX KittenTTS Micro 0.8 (selective 8-bit)

Browse files
Files changed (5) hide show
  1. README.md +34 -0
  2. config.json +78 -0
  3. model.safetensors +3 -0
  4. model.safetensors.index.json +542 -0
  5. voices.npz +3 -0
README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
4
+ # Kitten TTS Micro 0.8 (MLX, 8-bit selective)
5
+
6
+ This is a selectively quantized 8-bit MLX version of the KittenTTS Micro 0.8 model.
7
+
8
+ ## Source
9
+
10
+ - Original model: `KittenML/kitten-tts-micro-0.8`
11
+ - License: Apache-2.0
12
+
13
+ ## Usage
14
+
15
+ ````python
16
+ from mlx_audio.tts.utils import load_model
17
+ import soundfile as sf
18
+
19
+ model = load_model("mlx-community/kitten-tts-micro-0.8-8bit")
20
+
21
+ for out in model.generate("This model runs with MLX.", voice="Jasper"):
22
+ sf.write("out.wav", out.audio, model.sample_rate)
23
+ ````
24
+
25
+ Notes:
26
+ - `phonemizer` (espeak backend) is required for `generate()`.
27
+ - Available voices: Bella, Jasper, Luna, Bruno, Rosie, Hugo, Kiki, Leo.
28
+
29
+ ## Quantization
30
+
31
+ - Group size: 64
32
+ - Bits: 8
33
+ - Mode: affine
34
+ - Decoder/ISTFT generator kept in fp32 to avoid audio artifacts.
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "asr_res_dim": 64,
3
+ "hidden_dim": 512,
4
+ "istftnet": {
5
+ "resblock_kernel_sizes": [
6
+ 3,
7
+ 3
8
+ ],
9
+ "upsample_rates": [
10
+ 10,
11
+ 6
12
+ ],
13
+ "upsample_initial_channel": 256,
14
+ "resblock_dilation_sizes": [
15
+ [
16
+ 1,
17
+ 3,
18
+ 5
19
+ ],
20
+ [
21
+ 1,
22
+ 3,
23
+ 5
24
+ ]
25
+ ],
26
+ "upsample_kernel_sizes": [
27
+ 20,
28
+ 12
29
+ ],
30
+ "gen_istft_n_fft": 20,
31
+ "gen_istft_hop_size": 5
32
+ },
33
+ "max_conv_dim": 256,
34
+ "max_dur": 50,
35
+ "model_type": "kitten_tts",
36
+ "n_layer": 3,
37
+ "n_mels": 80,
38
+ "n_token": 178,
39
+ "plbert": {
40
+ "num_hidden_layers": 12,
41
+ "num_attention_heads": 12,
42
+ "hidden_size": 768,
43
+ "intermediate_size": 2048,
44
+ "max_position_embeddings": 512,
45
+ "embedding_size": 128,
46
+ "inner_group_num": 1,
47
+ "num_hidden_groups": 1,
48
+ "hidden_dropout_prob": 0.0,
49
+ "attention_probs_dropout_prob": 0.0,
50
+ "type_vocab_size": 2,
51
+ "layer_norm_eps": 1e-12
52
+ },
53
+ "quantization": {
54
+ "group_size": 64,
55
+ "bits": 8,
56
+ "mode": "affine"
57
+ },
58
+ "quantization_config": {
59
+ "group_size": 64,
60
+ "bits": 8,
61
+ "mode": "affine"
62
+ },
63
+ "sample_rate": 24000,
64
+ "speed_priors": {},
65
+ "style_dim": 128,
66
+ "text_encoder_kernel_size": 5,
67
+ "voice_aliases": {
68
+ "Bella": "expr-voice-2-f",
69
+ "Jasper": "expr-voice-2-m",
70
+ "Luna": "expr-voice-3-f",
71
+ "Bruno": "expr-voice-3-m",
72
+ "Rosie": "expr-voice-4-f",
73
+ "Hugo": "expr-voice-4-m",
74
+ "Kiki": "expr-voice-5-f",
75
+ "Leo": "expr-voice-5-m"
76
+ },
77
+ "voices_path": "voices.npz"
78
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb2cac60548d8ba1edab7dfe7c8d1ec873e816e9e28573fac665f7ba5fe127a
3
+ size 116444028
model.safetensors.index.json ADDED
@@ -0,0 +1,542 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 116385908,
4
+ "total_parameters": 35545426
5
+ },
6
+ "weight_map": {
7
+ "bert.embeddings.LayerNorm.bias": "model.safetensors",
8
+ "bert.embeddings.LayerNorm.weight": "model.safetensors",
9
+ "bert.embeddings.position_embeddings.biases": "model.safetensors",
10
+ "bert.embeddings.position_embeddings.scales": "model.safetensors",
11
+ "bert.embeddings.position_embeddings.weight": "model.safetensors",
12
+ "bert.embeddings.token_type_embeddings.biases": "model.safetensors",
13
+ "bert.embeddings.token_type_embeddings.scales": "model.safetensors",
14
+ "bert.embeddings.token_type_embeddings.weight": "model.safetensors",
15
+ "bert.embeddings.word_embeddings.biases": "model.safetensors",
16
+ "bert.embeddings.word_embeddings.scales": "model.safetensors",
17
+ "bert.embeddings.word_embeddings.weight": "model.safetensors",
18
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.LayerNorm.bias": "model.safetensors",
19
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.LayerNorm.weight": "model.safetensors",
20
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.dense.bias": "model.safetensors",
21
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.dense.biases": "model.safetensors",
22
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.dense.scales": "model.safetensors",
23
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.dense.weight": "model.safetensors",
24
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.key.bias": "model.safetensors",
25
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.key.biases": "model.safetensors",
26
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.key.scales": "model.safetensors",
27
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.key.weight": "model.safetensors",
28
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.query.bias": "model.safetensors",
29
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.query.biases": "model.safetensors",
30
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.query.scales": "model.safetensors",
31
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.query.weight": "model.safetensors",
32
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.value.bias": "model.safetensors",
33
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.value.biases": "model.safetensors",
34
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.value.scales": "model.safetensors",
35
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.attention.value.weight": "model.safetensors",
36
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn.bias": "model.safetensors",
37
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn.biases": "model.safetensors",
38
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn.scales": "model.safetensors",
39
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn.weight": "model.safetensors",
40
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn_output.bias": "model.safetensors",
41
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn_output.biases": "model.safetensors",
42
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn_output.scales": "model.safetensors",
43
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.ffn_output.weight": "model.safetensors",
44
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.full_layer_layer_norm.bias": "model.safetensors",
45
+ "bert.encoder.albert_layer_groups.0.albert_layers.0.full_layer_layer_norm.weight": "model.safetensors",
46
+ "bert.encoder.embedding_hidden_mapping_in.bias": "model.safetensors",
47
+ "bert.encoder.embedding_hidden_mapping_in.biases": "model.safetensors",
48
+ "bert.encoder.embedding_hidden_mapping_in.scales": "model.safetensors",
49
+ "bert.encoder.embedding_hidden_mapping_in.weight": "model.safetensors",
50
+ "bert.pooler.bias": "model.safetensors",
51
+ "bert.pooler.biases": "model.safetensors",
52
+ "bert.pooler.scales": "model.safetensors",
53
+ "bert.pooler.weight": "model.safetensors",
54
+ "bert_encoder.bias": "model.safetensors",
55
+ "bert_encoder.biases": "model.safetensors",
56
+ "bert_encoder.scales": "model.safetensors",
57
+ "bert_encoder.weight": "model.safetensors",
58
+ "decoder.F0_conv.bias": "model.safetensors",
59
+ "decoder.F0_conv.weight_g": "model.safetensors",
60
+ "decoder.F0_conv.weight_v": "model.safetensors",
61
+ "decoder.N_conv.bias": "model.safetensors",
62
+ "decoder.N_conv.weight_g": "model.safetensors",
63
+ "decoder.N_conv.weight_v": "model.safetensors",
64
+ "decoder.asr_res.0.bias": "model.safetensors",
65
+ "decoder.asr_res.0.weight_g": "model.safetensors",
66
+ "decoder.asr_res.0.weight_v": "model.safetensors",
67
+ "decoder.decode.0.conv1.bias": "model.safetensors",
68
+ "decoder.decode.0.conv1.weight_g": "model.safetensors",
69
+ "decoder.decode.0.conv1.weight_v": "model.safetensors",
70
+ "decoder.decode.0.conv1x1.weight_g": "model.safetensors",
71
+ "decoder.decode.0.conv1x1.weight_v": "model.safetensors",
72
+ "decoder.decode.0.conv2.bias": "model.safetensors",
73
+ "decoder.decode.0.conv2.weight_g": "model.safetensors",
74
+ "decoder.decode.0.conv2.weight_v": "model.safetensors",
75
+ "decoder.decode.0.norm1.fc.bias": "model.safetensors",
76
+ "decoder.decode.0.norm1.fc.weight": "model.safetensors",
77
+ "decoder.decode.0.norm2.fc.bias": "model.safetensors",
78
+ "decoder.decode.0.norm2.fc.weight": "model.safetensors",
79
+ "decoder.decode.1.conv1.bias": "model.safetensors",
80
+ "decoder.decode.1.conv1.weight_g": "model.safetensors",
81
+ "decoder.decode.1.conv1.weight_v": "model.safetensors",
82
+ "decoder.decode.1.conv1x1.weight_g": "model.safetensors",
83
+ "decoder.decode.1.conv1x1.weight_v": "model.safetensors",
84
+ "decoder.decode.1.conv2.bias": "model.safetensors",
85
+ "decoder.decode.1.conv2.weight_g": "model.safetensors",
86
+ "decoder.decode.1.conv2.weight_v": "model.safetensors",
87
+ "decoder.decode.1.norm1.fc.bias": "model.safetensors",
88
+ "decoder.decode.1.norm1.fc.weight": "model.safetensors",
89
+ "decoder.decode.1.norm2.fc.bias": "model.safetensors",
90
+ "decoder.decode.1.norm2.fc.weight": "model.safetensors",
91
+ "decoder.decode.2.conv1.bias": "model.safetensors",
92
+ "decoder.decode.2.conv1.weight_g": "model.safetensors",
93
+ "decoder.decode.2.conv1.weight_v": "model.safetensors",
94
+ "decoder.decode.2.conv1x1.weight_g": "model.safetensors",
95
+ "decoder.decode.2.conv1x1.weight_v": "model.safetensors",
96
+ "decoder.decode.2.conv2.bias": "model.safetensors",
97
+ "decoder.decode.2.conv2.weight_g": "model.safetensors",
98
+ "decoder.decode.2.conv2.weight_v": "model.safetensors",
99
+ "decoder.decode.2.norm1.fc.bias": "model.safetensors",
100
+ "decoder.decode.2.norm1.fc.weight": "model.safetensors",
101
+ "decoder.decode.2.norm2.fc.bias": "model.safetensors",
102
+ "decoder.decode.2.norm2.fc.weight": "model.safetensors",
103
+ "decoder.decode.3.conv1.bias": "model.safetensors",
104
+ "decoder.decode.3.conv1.weight_g": "model.safetensors",
105
+ "decoder.decode.3.conv1.weight_v": "model.safetensors",
106
+ "decoder.decode.3.conv1x1.weight_g": "model.safetensors",
107
+ "decoder.decode.3.conv1x1.weight_v": "model.safetensors",
108
+ "decoder.decode.3.conv2.bias": "model.safetensors",
109
+ "decoder.decode.3.conv2.weight_g": "model.safetensors",
110
+ "decoder.decode.3.conv2.weight_v": "model.safetensors",
111
+ "decoder.decode.3.norm1.fc.bias": "model.safetensors",
112
+ "decoder.decode.3.norm1.fc.weight": "model.safetensors",
113
+ "decoder.decode.3.norm2.fc.bias": "model.safetensors",
114
+ "decoder.decode.3.norm2.fc.weight": "model.safetensors",
115
+ "decoder.decode.3.pool.bias": "model.safetensors",
116
+ "decoder.decode.3.pool.weight_g": "model.safetensors",
117
+ "decoder.decode.3.pool.weight_v": "model.safetensors",
118
+ "decoder.encode.conv1.bias": "model.safetensors",
119
+ "decoder.encode.conv1.weight_g": "model.safetensors",
120
+ "decoder.encode.conv1.weight_v": "model.safetensors",
121
+ "decoder.encode.conv1x1.weight_g": "model.safetensors",
122
+ "decoder.encode.conv1x1.weight_v": "model.safetensors",
123
+ "decoder.encode.conv2.bias": "model.safetensors",
124
+ "decoder.encode.conv2.weight_g": "model.safetensors",
125
+ "decoder.encode.conv2.weight_v": "model.safetensors",
126
+ "decoder.encode.norm1.fc.bias": "model.safetensors",
127
+ "decoder.encode.norm1.fc.weight": "model.safetensors",
128
+ "decoder.encode.norm2.fc.bias": "model.safetensors",
129
+ "decoder.encode.norm2.fc.weight": "model.safetensors",
130
+ "decoder.generator.conv_post.bias": "model.safetensors",
131
+ "decoder.generator.conv_post.weight_g": "model.safetensors",
132
+ "decoder.generator.conv_post.weight_v": "model.safetensors",
133
+ "decoder.generator.m_source.l_linear.bias": "model.safetensors",
134
+ "decoder.generator.m_source.l_linear.weight": "model.safetensors",
135
+ "decoder.generator.noise_convs.0.bias": "model.safetensors",
136
+ "decoder.generator.noise_convs.0.weight": "model.safetensors",
137
+ "decoder.generator.noise_convs.1.bias": "model.safetensors",
138
+ "decoder.generator.noise_convs.1.weight": "model.safetensors",
139
+ "decoder.generator.noise_res.0.adain1.0.fc.bias": "model.safetensors",
140
+ "decoder.generator.noise_res.0.adain1.0.fc.weight": "model.safetensors",
141
+ "decoder.generator.noise_res.0.adain1.1.fc.bias": "model.safetensors",
142
+ "decoder.generator.noise_res.0.adain1.1.fc.weight": "model.safetensors",
143
+ "decoder.generator.noise_res.0.adain1.2.fc.bias": "model.safetensors",
144
+ "decoder.generator.noise_res.0.adain1.2.fc.weight": "model.safetensors",
145
+ "decoder.generator.noise_res.0.adain2.0.fc.bias": "model.safetensors",
146
+ "decoder.generator.noise_res.0.adain2.0.fc.weight": "model.safetensors",
147
+ "decoder.generator.noise_res.0.adain2.1.fc.bias": "model.safetensors",
148
+ "decoder.generator.noise_res.0.adain2.1.fc.weight": "model.safetensors",
149
+ "decoder.generator.noise_res.0.adain2.2.fc.bias": "model.safetensors",
150
+ "decoder.generator.noise_res.0.adain2.2.fc.weight": "model.safetensors",
151
+ "decoder.generator.noise_res.0.alpha1.0": "model.safetensors",
152
+ "decoder.generator.noise_res.0.alpha1.1": "model.safetensors",
153
+ "decoder.generator.noise_res.0.alpha1.2": "model.safetensors",
154
+ "decoder.generator.noise_res.0.alpha2.0": "model.safetensors",
155
+ "decoder.generator.noise_res.0.alpha2.1": "model.safetensors",
156
+ "decoder.generator.noise_res.0.alpha2.2": "model.safetensors",
157
+ "decoder.generator.noise_res.0.convs1.0.bias": "model.safetensors",
158
+ "decoder.generator.noise_res.0.convs1.0.weight_g": "model.safetensors",
159
+ "decoder.generator.noise_res.0.convs1.0.weight_v": "model.safetensors",
160
+ "decoder.generator.noise_res.0.convs1.1.bias": "model.safetensors",
161
+ "decoder.generator.noise_res.0.convs1.1.weight_g": "model.safetensors",
162
+ "decoder.generator.noise_res.0.convs1.1.weight_v": "model.safetensors",
163
+ "decoder.generator.noise_res.0.convs1.2.bias": "model.safetensors",
164
+ "decoder.generator.noise_res.0.convs1.2.weight_g": "model.safetensors",
165
+ "decoder.generator.noise_res.0.convs1.2.weight_v": "model.safetensors",
166
+ "decoder.generator.noise_res.0.convs2.0.bias": "model.safetensors",
167
+ "decoder.generator.noise_res.0.convs2.0.weight_g": "model.safetensors",
168
+ "decoder.generator.noise_res.0.convs2.0.weight_v": "model.safetensors",
169
+ "decoder.generator.noise_res.0.convs2.1.bias": "model.safetensors",
170
+ "decoder.generator.noise_res.0.convs2.1.weight_g": "model.safetensors",
171
+ "decoder.generator.noise_res.0.convs2.1.weight_v": "model.safetensors",
172
+ "decoder.generator.noise_res.0.convs2.2.bias": "model.safetensors",
173
+ "decoder.generator.noise_res.0.convs2.2.weight_g": "model.safetensors",
174
+ "decoder.generator.noise_res.0.convs2.2.weight_v": "model.safetensors",
175
+ "decoder.generator.noise_res.1.adain1.0.fc.bias": "model.safetensors",
176
+ "decoder.generator.noise_res.1.adain1.0.fc.weight": "model.safetensors",
177
+ "decoder.generator.noise_res.1.adain1.1.fc.bias": "model.safetensors",
178
+ "decoder.generator.noise_res.1.adain1.1.fc.weight": "model.safetensors",
179
+ "decoder.generator.noise_res.1.adain1.2.fc.bias": "model.safetensors",
180
+ "decoder.generator.noise_res.1.adain1.2.fc.weight": "model.safetensors",
181
+ "decoder.generator.noise_res.1.adain2.0.fc.bias": "model.safetensors",
182
+ "decoder.generator.noise_res.1.adain2.0.fc.weight": "model.safetensors",
183
+ "decoder.generator.noise_res.1.adain2.1.fc.bias": "model.safetensors",
184
+ "decoder.generator.noise_res.1.adain2.1.fc.weight": "model.safetensors",
185
+ "decoder.generator.noise_res.1.adain2.2.fc.bias": "model.safetensors",
186
+ "decoder.generator.noise_res.1.adain2.2.fc.weight": "model.safetensors",
187
+ "decoder.generator.noise_res.1.alpha1.0": "model.safetensors",
188
+ "decoder.generator.noise_res.1.alpha1.1": "model.safetensors",
189
+ "decoder.generator.noise_res.1.alpha1.2": "model.safetensors",
190
+ "decoder.generator.noise_res.1.alpha2.0": "model.safetensors",
191
+ "decoder.generator.noise_res.1.alpha2.1": "model.safetensors",
192
+ "decoder.generator.noise_res.1.alpha2.2": "model.safetensors",
193
+ "decoder.generator.noise_res.1.convs1.0.bias": "model.safetensors",
194
+ "decoder.generator.noise_res.1.convs1.0.weight_g": "model.safetensors",
195
+ "decoder.generator.noise_res.1.convs1.0.weight_v": "model.safetensors",
196
+ "decoder.generator.noise_res.1.convs1.1.bias": "model.safetensors",
197
+ "decoder.generator.noise_res.1.convs1.1.weight_g": "model.safetensors",
198
+ "decoder.generator.noise_res.1.convs1.1.weight_v": "model.safetensors",
199
+ "decoder.generator.noise_res.1.convs1.2.bias": "model.safetensors",
200
+ "decoder.generator.noise_res.1.convs1.2.weight_g": "model.safetensors",
201
+ "decoder.generator.noise_res.1.convs1.2.weight_v": "model.safetensors",
202
+ "decoder.generator.noise_res.1.convs2.0.bias": "model.safetensors",
203
+ "decoder.generator.noise_res.1.convs2.0.weight_g": "model.safetensors",
204
+ "decoder.generator.noise_res.1.convs2.0.weight_v": "model.safetensors",
205
+ "decoder.generator.noise_res.1.convs2.1.bias": "model.safetensors",
206
+ "decoder.generator.noise_res.1.convs2.1.weight_g": "model.safetensors",
207
+ "decoder.generator.noise_res.1.convs2.1.weight_v": "model.safetensors",
208
+ "decoder.generator.noise_res.1.convs2.2.bias": "model.safetensors",
209
+ "decoder.generator.noise_res.1.convs2.2.weight_g": "model.safetensors",
210
+ "decoder.generator.noise_res.1.convs2.2.weight_v": "model.safetensors",
211
+ "decoder.generator.resblocks.0.adain1.0.fc.bias": "model.safetensors",
212
+ "decoder.generator.resblocks.0.adain1.0.fc.weight": "model.safetensors",
213
+ "decoder.generator.resblocks.0.adain1.1.fc.bias": "model.safetensors",
214
+ "decoder.generator.resblocks.0.adain1.1.fc.weight": "model.safetensors",
215
+ "decoder.generator.resblocks.0.adain1.2.fc.bias": "model.safetensors",
216
+ "decoder.generator.resblocks.0.adain1.2.fc.weight": "model.safetensors",
217
+ "decoder.generator.resblocks.0.adain2.0.fc.bias": "model.safetensors",
218
+ "decoder.generator.resblocks.0.adain2.0.fc.weight": "model.safetensors",
219
+ "decoder.generator.resblocks.0.adain2.1.fc.bias": "model.safetensors",
220
+ "decoder.generator.resblocks.0.adain2.1.fc.weight": "model.safetensors",
221
+ "decoder.generator.resblocks.0.adain2.2.fc.bias": "model.safetensors",
222
+ "decoder.generator.resblocks.0.adain2.2.fc.weight": "model.safetensors",
223
+ "decoder.generator.resblocks.0.alpha1.0": "model.safetensors",
224
+ "decoder.generator.resblocks.0.alpha1.1": "model.safetensors",
225
+ "decoder.generator.resblocks.0.alpha1.2": "model.safetensors",
226
+ "decoder.generator.resblocks.0.alpha2.0": "model.safetensors",
227
+ "decoder.generator.resblocks.0.alpha2.1": "model.safetensors",
228
+ "decoder.generator.resblocks.0.alpha2.2": "model.safetensors",
229
+ "decoder.generator.resblocks.0.convs1.0.bias": "model.safetensors",
230
+ "decoder.generator.resblocks.0.convs1.0.weight_g": "model.safetensors",
231
+ "decoder.generator.resblocks.0.convs1.0.weight_v": "model.safetensors",
232
+ "decoder.generator.resblocks.0.convs1.1.bias": "model.safetensors",
233
+ "decoder.generator.resblocks.0.convs1.1.weight_g": "model.safetensors",
234
+ "decoder.generator.resblocks.0.convs1.1.weight_v": "model.safetensors",
235
+ "decoder.generator.resblocks.0.convs1.2.bias": "model.safetensors",
236
+ "decoder.generator.resblocks.0.convs1.2.weight_g": "model.safetensors",
237
+ "decoder.generator.resblocks.0.convs1.2.weight_v": "model.safetensors",
238
+ "decoder.generator.resblocks.0.convs2.0.bias": "model.safetensors",
239
+ "decoder.generator.resblocks.0.convs2.0.weight_g": "model.safetensors",
240
+ "decoder.generator.resblocks.0.convs2.0.weight_v": "model.safetensors",
241
+ "decoder.generator.resblocks.0.convs2.1.bias": "model.safetensors",
242
+ "decoder.generator.resblocks.0.convs2.1.weight_g": "model.safetensors",
243
+ "decoder.generator.resblocks.0.convs2.1.weight_v": "model.safetensors",
244
+ "decoder.generator.resblocks.0.convs2.2.bias": "model.safetensors",
245
+ "decoder.generator.resblocks.0.convs2.2.weight_g": "model.safetensors",
246
+ "decoder.generator.resblocks.0.convs2.2.weight_v": "model.safetensors",
247
+ "decoder.generator.resblocks.1.adain1.0.fc.bias": "model.safetensors",
248
+ "decoder.generator.resblocks.1.adain1.0.fc.weight": "model.safetensors",
249
+ "decoder.generator.resblocks.1.adain1.1.fc.bias": "model.safetensors",
250
+ "decoder.generator.resblocks.1.adain1.1.fc.weight": "model.safetensors",
251
+ "decoder.generator.resblocks.1.adain1.2.fc.bias": "model.safetensors",
252
+ "decoder.generator.resblocks.1.adain1.2.fc.weight": "model.safetensors",
253
+ "decoder.generator.resblocks.1.adain2.0.fc.bias": "model.safetensors",
254
+ "decoder.generator.resblocks.1.adain2.0.fc.weight": "model.safetensors",
255
+ "decoder.generator.resblocks.1.adain2.1.fc.bias": "model.safetensors",
256
+ "decoder.generator.resblocks.1.adain2.1.fc.weight": "model.safetensors",
257
+ "decoder.generator.resblocks.1.adain2.2.fc.bias": "model.safetensors",
258
+ "decoder.generator.resblocks.1.adain2.2.fc.weight": "model.safetensors",
259
+ "decoder.generator.resblocks.1.alpha1.0": "model.safetensors",
260
+ "decoder.generator.resblocks.1.alpha1.1": "model.safetensors",
261
+ "decoder.generator.resblocks.1.alpha1.2": "model.safetensors",
262
+ "decoder.generator.resblocks.1.alpha2.0": "model.safetensors",
263
+ "decoder.generator.resblocks.1.alpha2.1": "model.safetensors",
264
+ "decoder.generator.resblocks.1.alpha2.2": "model.safetensors",
265
+ "decoder.generator.resblocks.1.convs1.0.bias": "model.safetensors",
266
+ "decoder.generator.resblocks.1.convs1.0.weight_g": "model.safetensors",
267
+ "decoder.generator.resblocks.1.convs1.0.weight_v": "model.safetensors",
268
+ "decoder.generator.resblocks.1.convs1.1.bias": "model.safetensors",
269
+ "decoder.generator.resblocks.1.convs1.1.weight_g": "model.safetensors",
270
+ "decoder.generator.resblocks.1.convs1.1.weight_v": "model.safetensors",
271
+ "decoder.generator.resblocks.1.convs1.2.bias": "model.safetensors",
272
+ "decoder.generator.resblocks.1.convs1.2.weight_g": "model.safetensors",
273
+ "decoder.generator.resblocks.1.convs1.2.weight_v": "model.safetensors",
274
+ "decoder.generator.resblocks.1.convs2.0.bias": "model.safetensors",
275
+ "decoder.generator.resblocks.1.convs2.0.weight_g": "model.safetensors",
276
+ "decoder.generator.resblocks.1.convs2.0.weight_v": "model.safetensors",
277
+ "decoder.generator.resblocks.1.convs2.1.bias": "model.safetensors",
278
+ "decoder.generator.resblocks.1.convs2.1.weight_g": "model.safetensors",
279
+ "decoder.generator.resblocks.1.convs2.1.weight_v": "model.safetensors",
280
+ "decoder.generator.resblocks.1.convs2.2.bias": "model.safetensors",
281
+ "decoder.generator.resblocks.1.convs2.2.weight_g": "model.safetensors",
282
+ "decoder.generator.resblocks.1.convs2.2.weight_v": "model.safetensors",
283
+ "decoder.generator.resblocks.2.adain1.0.fc.bias": "model.safetensors",
284
+ "decoder.generator.resblocks.2.adain1.0.fc.weight": "model.safetensors",
285
+ "decoder.generator.resblocks.2.adain1.1.fc.bias": "model.safetensors",
286
+ "decoder.generator.resblocks.2.adain1.1.fc.weight": "model.safetensors",
287
+ "decoder.generator.resblocks.2.adain1.2.fc.bias": "model.safetensors",
288
+ "decoder.generator.resblocks.2.adain1.2.fc.weight": "model.safetensors",
289
+ "decoder.generator.resblocks.2.adain2.0.fc.bias": "model.safetensors",
290
+ "decoder.generator.resblocks.2.adain2.0.fc.weight": "model.safetensors",
291
+ "decoder.generator.resblocks.2.adain2.1.fc.bias": "model.safetensors",
292
+ "decoder.generator.resblocks.2.adain2.1.fc.weight": "model.safetensors",
293
+ "decoder.generator.resblocks.2.adain2.2.fc.bias": "model.safetensors",
294
+ "decoder.generator.resblocks.2.adain2.2.fc.weight": "model.safetensors",
295
+ "decoder.generator.resblocks.2.alpha1.0": "model.safetensors",
296
+ "decoder.generator.resblocks.2.alpha1.1": "model.safetensors",
297
+ "decoder.generator.resblocks.2.alpha1.2": "model.safetensors",
298
+ "decoder.generator.resblocks.2.alpha2.0": "model.safetensors",
299
+ "decoder.generator.resblocks.2.alpha2.1": "model.safetensors",
300
+ "decoder.generator.resblocks.2.alpha2.2": "model.safetensors",
301
+ "decoder.generator.resblocks.2.convs1.0.bias": "model.safetensors",
302
+ "decoder.generator.resblocks.2.convs1.0.weight_g": "model.safetensors",
303
+ "decoder.generator.resblocks.2.convs1.0.weight_v": "model.safetensors",
304
+ "decoder.generator.resblocks.2.convs1.1.bias": "model.safetensors",
305
+ "decoder.generator.resblocks.2.convs1.1.weight_g": "model.safetensors",
306
+ "decoder.generator.resblocks.2.convs1.1.weight_v": "model.safetensors",
307
+ "decoder.generator.resblocks.2.convs1.2.bias": "model.safetensors",
308
+ "decoder.generator.resblocks.2.convs1.2.weight_g": "model.safetensors",
309
+ "decoder.generator.resblocks.2.convs1.2.weight_v": "model.safetensors",
310
+ "decoder.generator.resblocks.2.convs2.0.bias": "model.safetensors",
311
+ "decoder.generator.resblocks.2.convs2.0.weight_g": "model.safetensors",
312
+ "decoder.generator.resblocks.2.convs2.0.weight_v": "model.safetensors",
313
+ "decoder.generator.resblocks.2.convs2.1.bias": "model.safetensors",
314
+ "decoder.generator.resblocks.2.convs2.1.weight_g": "model.safetensors",
315
+ "decoder.generator.resblocks.2.convs2.1.weight_v": "model.safetensors",
316
+ "decoder.generator.resblocks.2.convs2.2.bias": "model.safetensors",
317
+ "decoder.generator.resblocks.2.convs2.2.weight_g": "model.safetensors",
318
+ "decoder.generator.resblocks.2.convs2.2.weight_v": "model.safetensors",
319
+ "decoder.generator.resblocks.3.adain1.0.fc.bias": "model.safetensors",
320
+ "decoder.generator.resblocks.3.adain1.0.fc.weight": "model.safetensors",
321
+ "decoder.generator.resblocks.3.adain1.1.fc.bias": "model.safetensors",
322
+ "decoder.generator.resblocks.3.adain1.1.fc.weight": "model.safetensors",
323
+ "decoder.generator.resblocks.3.adain1.2.fc.bias": "model.safetensors",
324
+ "decoder.generator.resblocks.3.adain1.2.fc.weight": "model.safetensors",
325
+ "decoder.generator.resblocks.3.adain2.0.fc.bias": "model.safetensors",
326
+ "decoder.generator.resblocks.3.adain2.0.fc.weight": "model.safetensors",
327
+ "decoder.generator.resblocks.3.adain2.1.fc.bias": "model.safetensors",
328
+ "decoder.generator.resblocks.3.adain2.1.fc.weight": "model.safetensors",
329
+ "decoder.generator.resblocks.3.adain2.2.fc.bias": "model.safetensors",
330
+ "decoder.generator.resblocks.3.adain2.2.fc.weight": "model.safetensors",
331
+ "decoder.generator.resblocks.3.alpha1.0": "model.safetensors",
332
+ "decoder.generator.resblocks.3.alpha1.1": "model.safetensors",
333
+ "decoder.generator.resblocks.3.alpha1.2": "model.safetensors",
334
+ "decoder.generator.resblocks.3.alpha2.0": "model.safetensors",
335
+ "decoder.generator.resblocks.3.alpha2.1": "model.safetensors",
336
+ "decoder.generator.resblocks.3.alpha2.2": "model.safetensors",
337
+ "decoder.generator.resblocks.3.convs1.0.bias": "model.safetensors",
338
+ "decoder.generator.resblocks.3.convs1.0.weight_g": "model.safetensors",
339
+ "decoder.generator.resblocks.3.convs1.0.weight_v": "model.safetensors",
340
+ "decoder.generator.resblocks.3.convs1.1.bias": "model.safetensors",
341
+ "decoder.generator.resblocks.3.convs1.1.weight_g": "model.safetensors",
342
+ "decoder.generator.resblocks.3.convs1.1.weight_v": "model.safetensors",
343
+ "decoder.generator.resblocks.3.convs1.2.bias": "model.safetensors",
344
+ "decoder.generator.resblocks.3.convs1.2.weight_g": "model.safetensors",
345
+ "decoder.generator.resblocks.3.convs1.2.weight_v": "model.safetensors",
346
+ "decoder.generator.resblocks.3.convs2.0.bias": "model.safetensors",
347
+ "decoder.generator.resblocks.3.convs2.0.weight_g": "model.safetensors",
348
+ "decoder.generator.resblocks.3.convs2.0.weight_v": "model.safetensors",
349
+ "decoder.generator.resblocks.3.convs2.1.bias": "model.safetensors",
350
+ "decoder.generator.resblocks.3.convs2.1.weight_g": "model.safetensors",
351
+ "decoder.generator.resblocks.3.convs2.1.weight_v": "model.safetensors",
352
+ "decoder.generator.resblocks.3.convs2.2.bias": "model.safetensors",
353
+ "decoder.generator.resblocks.3.convs2.2.weight_g": "model.safetensors",
354
+ "decoder.generator.resblocks.3.convs2.2.weight_v": "model.safetensors",
355
+ "decoder.generator.ups.0.bias": "model.safetensors",
356
+ "decoder.generator.ups.0.weight_g": "model.safetensors",
357
+ "decoder.generator.ups.0.weight_v": "model.safetensors",
358
+ "decoder.generator.ups.1.bias": "model.safetensors",
359
+ "decoder.generator.ups.1.weight_g": "model.safetensors",
360
+ "decoder.generator.ups.1.weight_v": "model.safetensors",
361
+ "predictor.F0.0.conv1.bias": "model.safetensors",
362
+ "predictor.F0.0.conv1.weight_g": "model.safetensors",
363
+ "predictor.F0.0.conv1.weight_v": "model.safetensors",
364
+ "predictor.F0.0.conv2.bias": "model.safetensors",
365
+ "predictor.F0.0.conv2.weight_g": "model.safetensors",
366
+ "predictor.F0.0.conv2.weight_v": "model.safetensors",
367
+ "predictor.F0.0.norm1.fc.bias": "model.safetensors",
368
+ "predictor.F0.0.norm1.fc.biases": "model.safetensors",
369
+ "predictor.F0.0.norm1.fc.scales": "model.safetensors",
370
+ "predictor.F0.0.norm1.fc.weight": "model.safetensors",
371
+ "predictor.F0.0.norm2.fc.bias": "model.safetensors",
372
+ "predictor.F0.0.norm2.fc.biases": "model.safetensors",
373
+ "predictor.F0.0.norm2.fc.scales": "model.safetensors",
374
+ "predictor.F0.0.norm2.fc.weight": "model.safetensors",
375
+ "predictor.F0.1.conv1.bias": "model.safetensors",
376
+ "predictor.F0.1.conv1.weight_g": "model.safetensors",
377
+ "predictor.F0.1.conv1.weight_v": "model.safetensors",
378
+ "predictor.F0.1.conv1x1.weight_g": "model.safetensors",
379
+ "predictor.F0.1.conv1x1.weight_v": "model.safetensors",
380
+ "predictor.F0.1.conv2.bias": "model.safetensors",
381
+ "predictor.F0.1.conv2.weight_g": "model.safetensors",
382
+ "predictor.F0.1.conv2.weight_v": "model.safetensors",
383
+ "predictor.F0.1.norm1.fc.bias": "model.safetensors",
384
+ "predictor.F0.1.norm1.fc.biases": "model.safetensors",
385
+ "predictor.F0.1.norm1.fc.scales": "model.safetensors",
386
+ "predictor.F0.1.norm1.fc.weight": "model.safetensors",
387
+ "predictor.F0.1.norm2.fc.bias": "model.safetensors",
388
+ "predictor.F0.1.norm2.fc.biases": "model.safetensors",
389
+ "predictor.F0.1.norm2.fc.scales": "model.safetensors",
390
+ "predictor.F0.1.norm2.fc.weight": "model.safetensors",
391
+ "predictor.F0.1.pool.bias": "model.safetensors",
392
+ "predictor.F0.1.pool.weight_g": "model.safetensors",
393
+ "predictor.F0.1.pool.weight_v": "model.safetensors",
394
+ "predictor.F0.2.conv1.bias": "model.safetensors",
395
+ "predictor.F0.2.conv1.weight_g": "model.safetensors",
396
+ "predictor.F0.2.conv1.weight_v": "model.safetensors",
397
+ "predictor.F0.2.conv2.bias": "model.safetensors",
398
+ "predictor.F0.2.conv2.weight_g": "model.safetensors",
399
+ "predictor.F0.2.conv2.weight_v": "model.safetensors",
400
+ "predictor.F0.2.norm1.fc.bias": "model.safetensors",
401
+ "predictor.F0.2.norm1.fc.biases": "model.safetensors",
402
+ "predictor.F0.2.norm1.fc.scales": "model.safetensors",
403
+ "predictor.F0.2.norm1.fc.weight": "model.safetensors",
404
+ "predictor.F0.2.norm2.fc.bias": "model.safetensors",
405
+ "predictor.F0.2.norm2.fc.biases": "model.safetensors",
406
+ "predictor.F0.2.norm2.fc.scales": "model.safetensors",
407
+ "predictor.F0.2.norm2.fc.weight": "model.safetensors",
408
+ "predictor.F0_proj.bias": "model.safetensors",
409
+ "predictor.F0_proj.weight": "model.safetensors",
410
+ "predictor.N.0.conv1.bias": "model.safetensors",
411
+ "predictor.N.0.conv1.weight_g": "model.safetensors",
412
+ "predictor.N.0.conv1.weight_v": "model.safetensors",
413
+ "predictor.N.0.conv2.bias": "model.safetensors",
414
+ "predictor.N.0.conv2.weight_g": "model.safetensors",
415
+ "predictor.N.0.conv2.weight_v": "model.safetensors",
416
+ "predictor.N.0.norm1.fc.bias": "model.safetensors",
417
+ "predictor.N.0.norm1.fc.biases": "model.safetensors",
418
+ "predictor.N.0.norm1.fc.scales": "model.safetensors",
419
+ "predictor.N.0.norm1.fc.weight": "model.safetensors",
420
+ "predictor.N.0.norm2.fc.bias": "model.safetensors",
421
+ "predictor.N.0.norm2.fc.biases": "model.safetensors",
422
+ "predictor.N.0.norm2.fc.scales": "model.safetensors",
423
+ "predictor.N.0.norm2.fc.weight": "model.safetensors",
424
+ "predictor.N.1.conv1.bias": "model.safetensors",
425
+ "predictor.N.1.conv1.weight_g": "model.safetensors",
426
+ "predictor.N.1.conv1.weight_v": "model.safetensors",
427
+ "predictor.N.1.conv1x1.weight_g": "model.safetensors",
428
+ "predictor.N.1.conv1x1.weight_v": "model.safetensors",
429
+ "predictor.N.1.conv2.bias": "model.safetensors",
430
+ "predictor.N.1.conv2.weight_g": "model.safetensors",
431
+ "predictor.N.1.conv2.weight_v": "model.safetensors",
432
+ "predictor.N.1.norm1.fc.bias": "model.safetensors",
433
+ "predictor.N.1.norm1.fc.biases": "model.safetensors",
434
+ "predictor.N.1.norm1.fc.scales": "model.safetensors",
435
+ "predictor.N.1.norm1.fc.weight": "model.safetensors",
436
+ "predictor.N.1.norm2.fc.bias": "model.safetensors",
437
+ "predictor.N.1.norm2.fc.biases": "model.safetensors",
438
+ "predictor.N.1.norm2.fc.scales": "model.safetensors",
439
+ "predictor.N.1.norm2.fc.weight": "model.safetensors",
440
+ "predictor.N.1.pool.bias": "model.safetensors",
441
+ "predictor.N.1.pool.weight_g": "model.safetensors",
442
+ "predictor.N.1.pool.weight_v": "model.safetensors",
443
+ "predictor.N.2.conv1.bias": "model.safetensors",
444
+ "predictor.N.2.conv1.weight_g": "model.safetensors",
445
+ "predictor.N.2.conv1.weight_v": "model.safetensors",
446
+ "predictor.N.2.conv2.bias": "model.safetensors",
447
+ "predictor.N.2.conv2.weight_g": "model.safetensors",
448
+ "predictor.N.2.conv2.weight_v": "model.safetensors",
449
+ "predictor.N.2.norm1.fc.bias": "model.safetensors",
450
+ "predictor.N.2.norm1.fc.biases": "model.safetensors",
451
+ "predictor.N.2.norm1.fc.scales": "model.safetensors",
452
+ "predictor.N.2.norm1.fc.weight": "model.safetensors",
453
+ "predictor.N.2.norm2.fc.bias": "model.safetensors",
454
+ "predictor.N.2.norm2.fc.biases": "model.safetensors",
455
+ "predictor.N.2.norm2.fc.scales": "model.safetensors",
456
+ "predictor.N.2.norm2.fc.weight": "model.safetensors",
457
+ "predictor.N_proj.bias": "model.safetensors",
458
+ "predictor.N_proj.weight": "model.safetensors",
459
+ "predictor.duration_proj.linear_layer.bias": "model.safetensors",
460
+ "predictor.duration_proj.linear_layer.biases": "model.safetensors",
461
+ "predictor.duration_proj.linear_layer.scales": "model.safetensors",
462
+ "predictor.duration_proj.linear_layer.weight": "model.safetensors",
463
+ "predictor.lstm.Wh_backward": "model.safetensors",
464
+ "predictor.lstm.Wh_forward": "model.safetensors",
465
+ "predictor.lstm.Wx_backward": "model.safetensors",
466
+ "predictor.lstm.Wx_forward": "model.safetensors",
467
+ "predictor.lstm.bias_hh_backward": "model.safetensors",
468
+ "predictor.lstm.bias_hh_forward": "model.safetensors",
469
+ "predictor.lstm.bias_ih_backward": "model.safetensors",
470
+ "predictor.lstm.bias_ih_forward": "model.safetensors",
471
+ "predictor.shared.Wh_backward": "model.safetensors",
472
+ "predictor.shared.Wh_forward": "model.safetensors",
473
+ "predictor.shared.Wx_backward": "model.safetensors",
474
+ "predictor.shared.Wx_forward": "model.safetensors",
475
+ "predictor.shared.bias_hh_backward": "model.safetensors",
476
+ "predictor.shared.bias_hh_forward": "model.safetensors",
477
+ "predictor.shared.bias_ih_backward": "model.safetensors",
478
+ "predictor.shared.bias_ih_forward": "model.safetensors",
479
+ "predictor.text_encoder.lstms.0.Wh_backward": "model.safetensors",
480
+ "predictor.text_encoder.lstms.0.Wh_forward": "model.safetensors",
481
+ "predictor.text_encoder.lstms.0.Wx_backward": "model.safetensors",
482
+ "predictor.text_encoder.lstms.0.Wx_forward": "model.safetensors",
483
+ "predictor.text_encoder.lstms.0.bias_hh_backward": "model.safetensors",
484
+ "predictor.text_encoder.lstms.0.bias_hh_forward": "model.safetensors",
485
+ "predictor.text_encoder.lstms.0.bias_ih_backward": "model.safetensors",
486
+ "predictor.text_encoder.lstms.0.bias_ih_forward": "model.safetensors",
487
+ "predictor.text_encoder.lstms.1.fc.bias": "model.safetensors",
488
+ "predictor.text_encoder.lstms.1.fc.biases": "model.safetensors",
489
+ "predictor.text_encoder.lstms.1.fc.scales": "model.safetensors",
490
+ "predictor.text_encoder.lstms.1.fc.weight": "model.safetensors",
491
+ "predictor.text_encoder.lstms.2.Wh_backward": "model.safetensors",
492
+ "predictor.text_encoder.lstms.2.Wh_forward": "model.safetensors",
493
+ "predictor.text_encoder.lstms.2.Wx_backward": "model.safetensors",
494
+ "predictor.text_encoder.lstms.2.Wx_forward": "model.safetensors",
495
+ "predictor.text_encoder.lstms.2.bias_hh_backward": "model.safetensors",
496
+ "predictor.text_encoder.lstms.2.bias_hh_forward": "model.safetensors",
497
+ "predictor.text_encoder.lstms.2.bias_ih_backward": "model.safetensors",
498
+ "predictor.text_encoder.lstms.2.bias_ih_forward": "model.safetensors",
499
+ "predictor.text_encoder.lstms.3.fc.bias": "model.safetensors",
500
+ "predictor.text_encoder.lstms.3.fc.biases": "model.safetensors",
501
+ "predictor.text_encoder.lstms.3.fc.scales": "model.safetensors",
502
+ "predictor.text_encoder.lstms.3.fc.weight": "model.safetensors",
503
+ "predictor.text_encoder.lstms.4.Wh_backward": "model.safetensors",
504
+ "predictor.text_encoder.lstms.4.Wh_forward": "model.safetensors",
505
+ "predictor.text_encoder.lstms.4.Wx_backward": "model.safetensors",
506
+ "predictor.text_encoder.lstms.4.Wx_forward": "model.safetensors",
507
+ "predictor.text_encoder.lstms.4.bias_hh_backward": "model.safetensors",
508
+ "predictor.text_encoder.lstms.4.bias_hh_forward": "model.safetensors",
509
+ "predictor.text_encoder.lstms.4.bias_ih_backward": "model.safetensors",
510
+ "predictor.text_encoder.lstms.4.bias_ih_forward": "model.safetensors",
511
+ "predictor.text_encoder.lstms.5.fc.bias": "model.safetensors",
512
+ "predictor.text_encoder.lstms.5.fc.biases": "model.safetensors",
513
+ "predictor.text_encoder.lstms.5.fc.scales": "model.safetensors",
514
+ "predictor.text_encoder.lstms.5.fc.weight": "model.safetensors",
515
+ "text_encoder.cnn.0.0.bias": "model.safetensors",
516
+ "text_encoder.cnn.0.0.weight_g": "model.safetensors",
517
+ "text_encoder.cnn.0.0.weight_v": "model.safetensors",
518
+ "text_encoder.cnn.0.1.bias": "model.safetensors",
519
+ "text_encoder.cnn.0.1.weight": "model.safetensors",
520
+ "text_encoder.cnn.1.0.bias": "model.safetensors",
521
+ "text_encoder.cnn.1.0.weight_g": "model.safetensors",
522
+ "text_encoder.cnn.1.0.weight_v": "model.safetensors",
523
+ "text_encoder.cnn.1.1.bias": "model.safetensors",
524
+ "text_encoder.cnn.1.1.weight": "model.safetensors",
525
+ "text_encoder.cnn.2.0.bias": "model.safetensors",
526
+ "text_encoder.cnn.2.0.weight_g": "model.safetensors",
527
+ "text_encoder.cnn.2.0.weight_v": "model.safetensors",
528
+ "text_encoder.cnn.2.1.bias": "model.safetensors",
529
+ "text_encoder.cnn.2.1.weight": "model.safetensors",
530
+ "text_encoder.embedding.biases": "model.safetensors",
531
+ "text_encoder.embedding.scales": "model.safetensors",
532
+ "text_encoder.embedding.weight": "model.safetensors",
533
+ "text_encoder.lstm.Wh_backward": "model.safetensors",
534
+ "text_encoder.lstm.Wh_forward": "model.safetensors",
535
+ "text_encoder.lstm.Wx_backward": "model.safetensors",
536
+ "text_encoder.lstm.Wx_forward": "model.safetensors",
537
+ "text_encoder.lstm.bias_hh_backward": "model.safetensors",
538
+ "text_encoder.lstm.bias_hh_forward": "model.safetensors",
539
+ "text_encoder.lstm.bias_ih_backward": "model.safetensors",
540
+ "text_encoder.lstm.bias_ih_forward": "model.safetensors"
541
+ }
542
+ }
voices.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:112710c1be8ad0e967c190fb0fd95cbe5848ec4791b93209f20b28b7da20dac1
3
+ size 3278902