Upload leo.json

configs/leo.json

@@ -0,0 +1,54 @@
+{
+"convert2emo":"True",
+"data":
+{
+"add_blank":true,
+"cleaned_text":true,
+"filter_length":1024,
+"hop_length":256,
+"max_wav_value":32768.0,
+"mel_fmax":null,
+"mel_fmin":0.0,
+"n_mel_channels":80,
+"n_speakers":0,
+"sampling_rate":22050,
+"text_cleaners":["japanese_cleaners"],
+"training_files":"filelists/train.txt.cleaned",
+"validation_files":"filelists/val.txt.cleaned",
+"win_length":1024},
+"emotion_embedding":true,
+"model":
+{"filter_channels":768,
+"hidden_channels":192,
+"inter_channels":192,
+"kernel_size":3,
+"n_heads":2,
+"n_layers":6,
+"n_layers_q":3,
+"p_dropout":0.1,
+"resblock":"1",
+"resblock_dilation_sizes":[[1,3,5],[1,3,5],[1,3,5]],
+"resblock_kernel_sizes":[3,7,11],
+"upsample_initial_channel":512,
+"upsample_kernel_sizes":[16,16,4,4],
+"upsample_rates":[8,8,2,2],
+"use_spectral_norm":false},
+"speakers":["leo"],
+"symbols": ["_", ",", ".", "!", "?", "-", "A", "E", "I", "N", "O", "Q", "U", "a", "b", "d", "e", "f", "g", "h", "i", "j", "k", "m", "n", "o", "p", "r", "s", "t", "u", "v", "w", "y", "z", "\u0283", "\u02a7", "\u2193", "\u2191", " "],
+"train":
+{
+"batch_size":24,
+"betas":[0.8,0.99],
+"c_kl":1.0,"c_mel":45,
+"epochs":10000,
+"eps":1e-09,
+"eval_interval":200,
+"fp16_run":true,"init_lr_ratio":1,
+"learning_rate":0.0004,
+"log_interval":200,
+"lr_decay":0.999875,
+"seed":1234,
+"segment_size":8192,
+"warmup_epochs":0
+}
+}