Update hyperparams.yaml

hyperparams.yaml

@@ -1,65 +1,21 @@
 
 # ################################
-# Model: Tacotroon2 for TTS
+# Model: German HiFIGAN
 # Authors: Jonas Freiknecht
 # ################################
 
-mask_padding: True
-n_mel_channels: 80
-n_symbols: 148
-symbols_embedding_dim: 256
-encoder_kernel_size: 5
-encoder_n_convolutions: 3
-encoder_embedding_dim: 256
-attention_rnn_dim: 1024
-attention_dim: 128
-attention_location_n_filters: 32
-attention_location_kernel_size: 31
-n_frames_per_step: 1
-decoder_rnn_dim: 512
-prenet_dim: 128
-max_decoder_steps: 1000
-gate_threshold: 0.5
-p_attention_dropout: 0.1
-p_decoder_dropout: 0.1
-postnet_embedding_dim: 256
-postnet_kernel_size: 5
-postnet_n_convolutions: 5
-decoder_no_early_stopping: False
-sample_rate: 22050
+in_channels: 80
+out_channels: 1
+resblock_type: "1"
+resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+resblock_kernel_sizes: [3, 7, 11]
+upsample_kernel_sizes: [16, 16, 4, 4]
+upsample_initial_channel: 512
+upsample_factors: [8, 8, 2, 2]
+inference_padding: 5
+cond_channels: 0
+conv_post_bias: True
 
-# Model
-model: !new:speechbrain.lobes.models.Tacotron2.Tacotron2
-  mask_padding: !ref <mask_padding>
-  n_mel_channels: !ref <n_mel_channels>
-  # symbols
-  n_symbols: !ref <n_symbols>
-  symbols_embedding_dim: !ref <symbols_embedding_dim>
-  # encoder
-  encoder_kernel_size: !ref <encoder_kernel_size>
-  encoder_n_convolutions: !ref <encoder_n_convolutions>
-  encoder_embedding_dim: !ref <encoder_embedding_dim>
-  # attention
-  attention_rnn_dim: !ref <attention_rnn_dim>
-  attention_dim: !ref <attention_dim>
-  # attention location
-  attention_location_n_filters: !ref <attention_location_n_filters>
-  attention_location_kernel_size: !ref <attention_location_kernel_size>
-  # decoder
-  n_frames_per_step: !ref <n_frames_per_step>
-  decoder_rnn_dim: !ref <decoder_rnn_dim>
-  prenet_dim: !ref <prenet_dim>
-  max_decoder_steps: !ref <max_decoder_steps>
-  gate_threshold: !ref <gate_threshold>
-  p_attention_dropout: !ref <p_attention_dropout>
-  p_decoder_dropout: !ref <p_decoder_dropout>
-  # postnet
-  postnet_embedding_dim: !ref <postnet_embedding_dim>
-  postnet_kernel_size: !ref <postnet_kernel_size>
-  postnet_n_convolutions: !ref <postnet_n_convolutions>
-  decoder_no_early_stopping: !ref <decoder_no_early_stopping>
-
-# Function that converts the text into a sequence of valid characters.
 generator: !new:speechbrain.lobes.models.HifiGAN.HifiganGenerator
   in_channels: !ref <in_channels>
   out_channels: !ref <out_channels>
@@ -81,4 +37,3 @@ pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
         generator: !ref <generator>
 
 
-