diff --git a/voice_conversion/configs/32k.json b/voice_conversion/configs/32k.json
deleted file mode 100644
index d5f16d6..0000000
--- a/voice_conversion/configs/32k.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.999875,
-    "segment_size": 12800,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 32000,
-    "filter_length": 1024,
-    "hop_length": 320,
-    "win_length": 1024,
-    "n_mel_channels": 80,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,4,2,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16,16,4,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}
diff --git a/voice_conversion/configs/32k_v2.json b/voice_conversion/configs/32k_v2.json
deleted file mode 100644
index 70e534f..0000000
--- a/voice_conversion/configs/32k_v2.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.999875,
-    "segment_size": 12800,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 32000,
-    "filter_length": 1024,
-    "hop_length": 320,
-    "win_length": 1024,
-    "n_mel_channels": 80,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,8,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [20,16,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}
diff --git a/voice_conversion/configs/40k.json b/voice_conversion/configs/40k.json
deleted file mode 100644
index 4ffc87b..0000000
--- a/voice_conversion/configs/40k.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.999875,
-    "segment_size": 12800,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 40000,
-    "filter_length": 2048,
-    "hop_length": 400,
-    "win_length": 2048,
-    "n_mel_channels": 125,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,10,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16,16,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}
diff --git a/voice_conversion/configs/48k.json b/voice_conversion/configs/48k.json
deleted file mode 100644
index 2d0e05b..0000000
--- a/voice_conversion/configs/48k.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.999875,
-    "segment_size": 11520,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 48000,
-    "filter_length": 2048,
-    "hop_length": 480,
-    "win_length": 2048,
-    "n_mel_channels": 128,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [10,6,2,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [16,16,4,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}
diff --git a/voice_conversion/configs/48k_v2.json b/voice_conversion/configs/48k_v2.json
deleted file mode 100644
index 10f1ce7..0000000
--- a/voice_conversion/configs/48k_v2.json
+++ /dev/null
@@ -1,46 +0,0 @@
-{
-  "train": {
-    "log_interval": 200,
-    "seed": 1234,
-    "epochs": 20000,
-    "learning_rate": 1e-4,
-    "betas": [0.8, 0.99],
-    "eps": 1e-9,
-    "batch_size": 4,
-    "fp16_run": true,
-    "lr_decay": 0.999875,
-    "segment_size": 11520,
-    "init_lr_ratio": 1,
-    "warmup_epochs": 0,
-    "c_mel": 45,
-    "c_kl": 1.0
-  },
-  "data": {
-    "max_wav_value": 32768.0,
-    "sampling_rate": 48000,
-    "filter_length": 2048,
-    "hop_length": 480,
-    "win_length": 2048,
-    "n_mel_channels": 128,
-    "mel_fmin": 0.0,
-    "mel_fmax": null
-  },
-  "model": {
-    "inter_channels": 192,
-    "hidden_channels": 192,
-    "filter_channels": 768,
-    "n_heads": 2,
-    "n_layers": 6,
-    "kernel_size": 3,
-    "p_dropout": 0,
-    "resblock": "1",
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-    "upsample_rates": [12,10,2,2],
-    "upsample_initial_channel": 512,
-    "upsample_kernel_sizes": [24,20,4,4],
-    "use_spectral_norm": false,
-    "gin_channels": 256,
-    "spk_embed_dim": 109
-  }
-}