Text-to-Speech
PyTorch
ONNX
Catalan
matcha-tts
acoustic modelling
speech
multispeaker
AlexK-PL commited on
Commit
2842206
1 Parent(s): e77ae87

Upload model and config files

Browse files
Files changed (2) hide show
  1. config.yaml +43 -0
  2. pytorch_model.bin +3 -0
config.yaml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ cfm:
2
+ name: CFM
3
+ sigma_min: 0.0001
4
+ solver: euler
5
+ data_statistics:
6
+ mel_mean: -6.578195
7
+ mel_std: 2.538758
8
+ decoder:
9
+ act_fn: snakebeta
10
+ attention_head_dim: 64
11
+ channels:
12
+ - 256
13
+ - 256
14
+ dropout: 0.05
15
+ n_blocks: 1
16
+ num_heads: 2
17
+ num_mid_blocks: 2
18
+ encoder:
19
+ duration_predictor_params:
20
+ filter_channels_dp: 256
21
+ kernel_size: 3
22
+ p_dropout: 0.1
23
+ encoder_params:
24
+ filter_channels: 768
25
+ filter_channels_dp: 256
26
+ kernel_size: 3
27
+ n_channels: 192
28
+ n_feats: 80
29
+ n_heads: 2
30
+ n_layers: 6
31
+ n_spks: 47
32
+ p_dropout: 0.1
33
+ prenet: true
34
+ spk_emb_dim: 64
35
+ encoder_type: RoPE Encoder
36
+ n_feats: 80
37
+ n_spks: 47
38
+ n_vocab: 178
39
+ optimizer: null
40
+ out_size: null
41
+ prior_loss: true
42
+ scheduler: null
43
+ spk_emb_dim: 64
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b9640678f0d3be86a09484bbcf2cd55c9c4d2a92fc0eb3fb193ada6b5d01aa
3
+ size 83535314