Text-to-Speech
ONNX
Safetensors
English
Chinese

Update model.json

#4
by pkufool - opened
Files changed (1) hide show
  1. model.json +18 -18
model.json CHANGED
@@ -1,23 +1,23 @@
1
  {
2
  "model" : {
3
- "fm-decoder-downsampling-factor" : "1,2,4,2,1",
4
- "fm-decoder-num-layers" : "2,2,4,4,4",
5
- "fm-decoder-cnn-module-kernel" : "31,15,7,15,31",
6
- "fm-decoder-feedforward-dim" : 1536,
7
- "fm-decoder-num-heads" : 4,
8
- "fm-decoder-dim" : 512,
9
- "text-encoder-downsampling-factor" : "1",
10
- "text-encoder-num-layers" : "4",
11
- "text-encoder-feedforward-dim" : 512,
12
- "text-encoder-cnn-module-kernel" : 9,
13
- "text-encoder-num-heads" : 4,
14
- "text-encoder-dim" : 192,
15
- "query-head-dim" : 32,
16
- "value-head-dim" : 32,
17
- "pos-head-dim" : 4,
18
- "pos-dim" : 48,
19
- "time-embed-dim" : 192,
20
- "text-embed-dim" : 192
21
  },
22
  "feature" : {
23
  "sampling_rate": 24000,
 
1
  {
2
  "model" : {
3
+ "fm_decoder_downsampling_factor" : "1,2,4,2,1",
4
+ "fm_decoder_num_layers" : "2,2,4,4,4",
5
+ "fm_decoder_cnn_module_kernel" : "31,15,7,15,31",
6
+ "fm_decoder_feedforward_dim" : 1536,
7
+ "fm_decoder_num_heads" : 4,
8
+ "fm_decoder_dim" : 512,
9
+ "text_encoder_downsampling_factor" : "1",
10
+ "text_encoder_num_layers" : "4",
11
+ "text_encoder_feedforward_dim" : 512,
12
+ "text_encoder_cnn_module_kernel" : 9,
13
+ "text_encoder_num_heads" : 4,
14
+ "text_encoder_dim" : 192,
15
+ "query_head_dim" : 32,
16
+ "value_head_dim" : 32,
17
+ "pos_head_dim" : 4,
18
+ "pos_dim" : 48,
19
+ "time_embed_dim" : 192,
20
+ "text_embed_dim" : 192
21
  },
22
  "feature" : {
23
  "sampling_rate": 24000,