add config file

vits2_vctk_cat_inference.json

@@ -0,0 +1,62 @@
+{
+    "train": {
+      "log_interval": 200,
+      "eval_interval": 5000,
+      "seed": 1234,
+      "epochs": 10000,
+      "learning_rate": 2e-4,
+      "betas": [0.8, 0.99],
+      "eps": 1e-9,
+      "batch_size": 64,
+      "fp16_run": true,
+      "lr_decay": 0.999875,
+      "segment_size": 8192,
+      "init_lr_ratio": 1,
+      "warmup_epochs": 0,
+      "c_mel": 45,
+      "c_kl": 1.0
+    },
+    "data": {
+      "use_mel_posterior_encoder": true,
+      "training_files": "train_filelis.txt",
+      "validation_files": "val_filelist.txt",
+      "text_cleaners":["catalan_cleaners"],
+      "max_wav_value": 32768.0,
+      "sampling_rate": 22050,
+      "filter_length": 1024,
+      "hop_length": 256,
+      "win_length": 1024,
+      "n_mel_channels": 80,
+      "mel_fmin": 0.0,
+      "mel_fmax": null,
+      "add_blank": false,
+      "n_speakers": 47,
+      "cleaned_text": false
+    },
+    "model": {
+      "use_mel_posterior_encoder": true,
+      "use_transformer_flows": true,
+      "transformer_flow_type": "pre_conv2",
+      "use_spk_conditioned_encoder": true,
+      "use_noise_scaled_mas": true,
+      "use_duration_discriminator": true,
+      "duration_discriminator_type": "dur_disc_2",
+      "inter_channels": 192,
+      "hidden_channels": 192,
+      "filter_channels": 768,
+      "n_heads": 2,
+      "n_layers": 6,
+      "kernel_size": 3,
+      "p_dropout": 0.1,
+      "resblock": "1",
+      "resblock_kernel_sizes": [3,7,11],
+      "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+      "upsample_rates": [8,8,2,2],
+      "upsample_initial_channel": 512,
+      "upsample_kernel_sizes": [16,16,4,4],
+      "n_layers_q": 3,
+      "use_spectral_norm": false,
+      "use_sdp": true,
+      "gin_channels": 256
+    }
+}