update new multi voice modelcard

configuration.json

@@ -0,0 +1,127 @@
+{
+  "framework": "tensorflow",
+  "task" : "text-to-speech",
+  "model" : {
+    "type" : "sambert-hifigan",
+    "lang_type" : "zhcn",
+    "sample_rate" : 16000,
+    "am": {
+      "cleaners":"english_cleaners",
+
+      "num_mels":80,
+      "sample_rate":16000,
+      "frame_shift_ms":12.5,
+
+      
+      "embedding_dim":512,
+      "encoder_n_conv_layers":3,
+      "encoder_filters":256,
+      "encoder_kernel_size":5,
+
+      "encoder_num_layers":8,
+      "encoder_num_units":128,
+      "encoder_num_heads":8,
+      "encoder_ffn_inner_dim":1024,
+      "encoder_dropout":0.1,
+      "encoder_attention_dropout":0.1,
+      "encoder_relu_dropout":0.1,
+      "encoder_projection_units":32,
+
+      "predictor_filter_size":41,
+      "predictor_fsmn_num_layers":3,
+      "predictor_dnn_num_layers":0,
+      "predictor_num_memory_units":128,
+      "predictor_ffn_inner_dim":256,
+      "predictor_dropout":0.1,
+      "predictor_shift":0,
+
+      "predictor_prenet_units":[128, 128],
+      "predictor_lstm_units":128,
+
+      "prenet_units":[256, 256],
+      "prenet_proj_units":128,
+
+      "decoder_num_layers":12,
+      "decoder_num_units":128,
+      "decoder_num_heads":8,
+      "decoder_ffn_inner_dim":1024,
+      "decoder_dropout":0.1,
+      "decoder_attention_dropout":0.1,
+      "decoder_relu_dropout":0.1,
+
+      "outputs_per_step":3,
+
+      "postnet_filter_size":41,
+      "postnet_fsmn_num_layers":4,
+      "postnet_dnn_num_layers":0,
+      "postnet_num_memory_units":256,
+      "postnet_ffn_inner_dim":512,
+      "postnet_dropout":0.1,
+      "postnet_shift":17,
+      "postnet_lstm_units":128, 
+
+      
+      "dur_scale":1.0,
+
+      "batch_size":32,
+      "adam_beta1":0.9,
+      "adam_beta2":0.999,
+      "initial_learning_rate":0.002,
+      "decay_learning_rate":true,
+      "use_cmudict":false,                 
+
+      "lfeat_type_list":"sy,tone,syllable_flag,word_segment,emo_category,speaker",
+
+      "guided_attention":false,
+      "guided_attention_2g_squared":0.08,
+      "guided_attention_loss_weight":1.0,
+
+      "free_run":false,
+
+      "X_band_width":40,
+      "H_band_width":40,
+
+      "max_len":900
+    },
+    "vocoder" : {
+      "resblock": "1",
+      "num_gpus": 1,
+      "batch_size": 16,
+      "learning_rate": 0.0002,
+      "adam_b1": 0.8,
+      "adam_b2": 0.99,
+      "lr_decay": 0.999,
+      "seed": 1234,
+
+      "upsample_rates": [10,5,2,2],
+      "upsample_kernel_sizes": [20,11,4,4],
+      "upsample_initial_channel": 256,
+      "resblock_kernel_sizes": [3,7,11],
+      "resblock_dilation_sizes": [[1,3,5,7], [1,3,5,7], [1,3,5,7]],
+
+      "segment_size": 6400,
+      "num_mels": 80,
+      "num_freq": 1025,
+      "n_fft": 2048,
+      "hop_size": 200,
+      "win_size": 1000,
+
+      "sampling_rate": 16000,
+
+      "fmin": 0,
+      "fmax": 8000,
+      "fmax_for_loss": null,
+
+      "num_workers": 4,
+
+      "dist_config": {
+          "dist_backend": "nccl",
+          "dist_url": "tcp://localhost:54312",
+          "world_size": 1
+      }
+    }
+  },
+  "pipeline": {
+     "type": "sambert-hifigan-tts"
+  }
+}