Replace wrong model

config.yml

@@ -1,5 +1,5 @@
 
-multispeaker: true
+multispeaker: false
 
 dim_in: 64 
 hidden_dim: 512
@@ -15,16 +15,18 @@ dropout: 0.2
 
 # config for decoder
 decoder: 
-    type: 'hifigan' # either hifigan or istftnet
+    type: 'istftnet' # either hifigan or istftnet
     resblock_kernel_sizes: [3,7,11]
-    upsample_rates :  [10,5,3,2]
+    upsample_rates :  [10, 6]
     upsample_initial_channel: 512
     resblock_dilation_sizes: [[1,3,5], [1,3,5], [1,3,5]]
-    upsample_kernel_sizes: [20,10,6,4]
+    upsample_kernel_sizes: [20, 12]
+    gen_istft_n_fft: 20
+    gen_istft_hop_size: 5
     
 # speech language model config
 slm:
-    model: ''
+    model: 'openai/whisper-medium'
     sr: 16000 # sampling rate of SLM
     hidden: 768 # hidden size of SLM
     nlayers: 13 # number of layers of SLM
@@ -42,7 +44,7 @@ diffusion:
 
   # diffusion distribution config
   dist:
-    sigma_data: 0.19988229232390187 # placeholder for estimate_sigma_data set to false
+    sigma_data: 0.18 # placeholder for estimate_sigma_data set to false
     estimate_sigma_data: true # estimate sigma_data from the current batch if set to true
     mean: -3.0
     std: 1.0

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd0e06ecc528d25c5d6371c0a5dbfa742b008d0f83d843738e411efeb03f851
-size 766654558
+oid sha256:25e78d882ec4ee5a8a361749004edf6914137760f2be33a71ea24ce22da1a24a
+size 748848243