Upload config_768v2.json

configs/config_768v2.json

@@ -0,0 +1,165 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 800,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "fp16_run": false,
+    "half_type": "fp16",
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3,
+    "all_in_mem": false,
+    "vol_aug": true
+  },
+  "data": {
+    "training_files": "filelists/train.txt",
+    "validation_files": "filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050,
+    "unit_interpolate_mode": "nearest"
+  },
+  "model": {
+    "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,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "n_flow_layer": 4,
+    "use_spectral_norm": false,
+    "gin_channels": 768,
+    "ssl_dim": 768,
+    "n_speakers": 61,
+    "vocoder_name": "nsf-hifigan",
+    "speech_encoder": "vec768l12",
+    "speaker_embedding": false,
+    "vol_embedding": true,
+    "use_depthwise_conv": false,
+    "flow_share_parameter": false,
+    "use_automatic_f0_prediction": true
+  },
+  "spk": {
+    "AKIMOTO_MANATSU": 0,
+    "ENDO_SAKURA": 1,
+    "ETO_MISA": 2,
+    "HARUKA_KUROMI": 3,
+    "HASHIMOTO_NANAMI": 4,
+    "HAYAKAWA_SEIRA": 5,
+    "HIGUCHI_HINA": 6,
+    "HORI_MIONA": 7,
+    "HOSHINO_MINAMI": 8,
+    "ICHINOSE_MIKU": 9,
+    "IKEDA_TERESA": 10,
+    "IKUTA_ERIKA": 11,
+    "INOUE_NAGI": 12,
+    "INOUE_SAYURI": 13,
+    "IOKI_MAO": 14,
+    "ITO_JUNNA": 15,
+    "ITO_RIRIA": 16,
+    "IWAMOTO_RENKA": 17,
+    "KAKEHASHI_SAYAKA": 18,
+    "KAKI_HARUKA": 19,
+    "KANAGAWA_SAYA": 20,
+    "KAWAGO_HINA": 21,
+    "KAWASAKI_SAKURA": 22,
+    "KITAGAWA_YURI": 23,
+    "KITANO_HINAKO": 24,
+    "KUBO_SHIORI": 25,
+    "MATSUMURA_SAYURI": 26,
+    "MIYU_MATSUO": 27,
+    "MUKAI_HAZUKI": 28,
+    "NAKAMURA_RENO": 29,
+    "NAKANISHI_ARUNO": 30,
+    "NAO_YUMIKI": 31,
+    "NISHINO_NANASE": 32,
+    "OGAWA_AYA": 33,
+    "OKUDA_IROHA": 34,
+    "OZONO_MOMOKO": 35,
+    "RIKA_SATO": 36,
+    "RUNA_HAYASHI": 37,
+    "SAITO_ASUKA": 38,
+    "SAKAGUCHI_TAMAMI": 39,
+    "SAKURAI_REIKA": 40,
+    "SASAKI_KOTOKO": 41,
+    "SATO_KAEDE": 42,
+    "SATO_YUURI": 43,
+    "SEIMIYA_REI": 44,
+    "SHIBATA_YUNA": 45,
+    "SHINUCHI_MAI": 46,
+    "SHIRAISHI_MAI": 47,
+    "SUGAWARA_SATSUKI": 48,
+    "SUZUKI_AYANE": 49,
+    "TAKAYAMA_KAZUMI": 50,
+    "TAMURA_MAYU": 51,
+    "TERADA_RANZE": 52,
+    "TOMISATO_NAO": 53,
+    "TSUTSUI_AYAME": 54,
+    "UMEZAWA_MINAMI": 55,
+    "WAKATSUKI_YUMI": 56,
+    "WATANABE_MIRIA": 57,
+    "YAKUBO_MIO": 58,
+    "YAMASHITA_MIZUKI": 59,
+    "YODA_YUUKI": 60
+  }
+}