Upload 7 files

server/models/glowtts-v2/best_model.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9103e1b1cd49e0e28a44ab6c61ec70ac97b43effff02adcdc491191ed96585
+size 343835368

server/models/glowtts-v2/config.json

@@ -0,0 +1,109 @@
+{
+    "model": "glow_tts",
+    "run_name": "glowtts-v2",
+    "run_description": "glow-tts model for sce-tts project",
+    "epochs": 10000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "mixed_precision": false,
+    "run_eval": true,
+    "test_delay_epochs": 0,
+    "print_eval": false,
+    "print_step": 25,
+    "tb_plot_step": 100,
+    "tb_model_param_stats": false,
+    "save_step": 1000,
+    "checkpoint": true,
+    "keep_all_best": false,
+    "keep_after": 10000,
+    "num_loader_workers": 2,
+    "num_val_loader_workers": 2,
+    "use_noise_augment": true,
+    "output_path": "/content/drive/My Drive/Colab Notebooks/data/glowtts-v2/",
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 22050,
+        "resample": false,
+        "preemphasis": 0.98,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "do_trim_silence": false,
+        "trim_db": 60,
+        "power": 1.1,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": 8000.0,
+        "spec_gain": 20,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": "D:\\myown-tts\\server\\models\\glowtts-v2\\scale_stats.npy"
+    },
+    "use_phonemes": false,
+    "phoneme_language": "ko",
+    "compute_input_seq_cache": true,
+    "text_cleaner": "korean_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "/content/TTS/test_sentences.txt",
+    "phoneme_cache_path": null,
+    "characters": {
+        "pad": "_",
+        "eos": "~",
+        "bos": "^",
+        "characters": " .!?\u1100\u1101\u1102\u1103\u1104\u1105\u1106\u1107\u1108\u1109\u110a\u110b\u110c\u110d\u110e\u110f\u1110\u1111\u1112\u1161\u1162\u1163\u1164\u1165\u1166\u1167\u1168\u1169\u116a\u116b\u116c\u116d\u116e\u116f\u1170\u1171\u1172\u1173\u1174\u1175\u11a8\u11a9\u11aa\u11ab\u11ac\u11ad\u11ae\u11af\u11b0\u11b1\u11b2\u11b3\u11b4\u11b5\u11b6\u11b7\u11b8\u11b9\u11ba\u11bb\u11bc\u11bd\u11be\u11bf\u11c0\u11c1\u11c2",
+        "punctuations": " .!?",
+        "phonemes": "\u1100\u1101\u1102\u1103\u1104\u1105\u1106\u1107\u1108\u1109\u110a\u110b\u110c\u110d\u110e\u110f\u1110\u1111\u1112\u1161\u1162\u1163\u1164\u1165\u1166\u1167\u1168\u1169\u116a\u116b\u116c\u116d\u116e\u116f\u1170\u1171\u1172\u1173\u1174\u1175\u11a8\u11a9\u11aa\u11ab\u11ac\u11ad\u11ae\u11af\u11b0\u11b1\u11b2\u11b3\u11b4\u11b5\u11b6\u11b7\u11b8\u11b9\u11ba\u11bb\u11bc\u11bd\u11be\u11bf\u11c0\u11c1\u11c2",
+        "unique": true
+    },
+    "batch_group_size": 4,
+    "loss_masking": true,
+    "min_seq_len": 3,
+    "max_seq_len": 500,
+    "compute_f0": false,
+    "add_blank": false,
+    "datasets": [
+        {
+            "name": "ljspeech",
+            "path": "/content/TTS/filelists",
+            "meta_file_train": "metadata.csv",
+            "ununsed_speakers": null,
+            "meta_file_val": null,
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "encoder_type": "rel_pos_transformer",
+    "encoder_params": {
+        "kernel_size": 3,
+        "dropout_p": 0.1,
+        "num_layers": 6,
+        "num_heads": 2,
+        "hidden_channels_ffn": 768,
+        "input_length": null
+    },
+    "use_encoder_prenet": true,
+    "hidden_channels_encoder": 192,
+    "hidden_channels_decoder": 192,
+    "hidden_channels_duration_predictor": 256,
+    "data_dep_init_steps": 10,
+    "style_wav_for_test": null,
+    "inference_noise_scale": 0.0,
+    "use_speaker_embedding": false,
+    "use_external_speaker_embedding_file": false,
+    "external_speaker_embedding_file": false,
+    "noam_schedule": true,
+    "warmup_steps": 4000,
+    "grad_clip": 0.05,
+    "lr": 0.0001,
+    "wd": 1e-06,
+    "r": 1
+}

server/models/glowtts-v2/scale_stats.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df69167ebc20f1e26aa53fa3d8cc2e59690c7580044481596aca393a814f6165
+size 10680

server/models/hifigan-v2/best_model.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76398204c01edd116faaac6f11fc17b2bca20659847c0dba752ef021bfe2e6d8
+size 860280509

server/models/hifigan-v2/config.json

@@ -0,0 +1,165 @@
+{
+    "model": "hifigan",
+    "run_name": "hifigan-v2",
+    "run_description": "hifigan model for sce-tts project",
+    "epochs": 10000,
+    "batch_size": 16,
+    "eval_batch_size": 16,
+    "mixed_precision": false,
+    "run_eval": true,
+    "test_delay_epochs": 0,
+    "print_eval": false,
+    "print_step": 25,
+    "tb_plot_step": 100,
+    "tb_model_param_stats": false,
+    "save_step": 5000,
+    "checkpoint": true,
+    "keep_all_best": false,
+    "keep_after": 10000,
+    "num_loader_workers": 2,
+    "num_val_loader_workers": 2,
+    "use_noise_augment": false,
+    "output_path": "/content/drive/My Drive/Colab Notebooks/data/hifigan-v2/",
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 22050,
+        "resample": false,
+        "preemphasis": 0.98,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "do_trim_silence": false,
+        "trim_db": 60,
+        "power": 1.1,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": 8000.0,
+        "spec_gain": 20,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": "D:\\myown-tts\\server\\models\\hifigan-v2\\scale_stats.npy"
+    },
+    "eval_split_size": 10,
+    "data_path": "/content/TTS/filelists/wavs",
+    "feature_path": null,
+    "seq_len": 8192,
+    "pad_short": 2000,
+    "conv_pad": 0,
+    "use_cache": true,
+    "wd": 0.0,
+    "use_stft_loss": false,
+    "use_subband_stft_loss": false,
+    "use_mse_gan_loss": true,
+    "use_hinge_gan_loss": false,
+    "use_feat_match_loss": true,
+    "use_l1_spec_loss": true,
+    "stft_loss_weight": 0.0,
+    "subband_stft_loss_weight": 0.0,
+    "mse_G_loss_weight": 1.0,
+    "hinge_G_loss_weight": 0.0,
+    "feat_match_loss_weight": 10.0,
+    "l1_spec_loss_weight": 45.0,
+    "stft_loss_params": {
+        "n_ffts": [
+            1024,
+            2048,
+            512
+        ],
+        "hop_lengths": [
+            120,
+            240,
+            50
+        ],
+        "win_lengths": [
+            600,
+            1200,
+            240
+        ]
+    },
+    "l1_spec_loss_params": {
+        "use_mel": true,
+        "sample_rate": 22050,
+        "n_fft": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null
+    },
+    "target_loss": "avg_G_loss",
+    "gen_clip_grad": -1.0,
+    "disc_clip_grad": -1.0,
+    "lr_gen": 0.0002,
+    "lr_disc": 0.0002,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "weight_decay": 0.0
+    },
+    "lr_scheduler_gen": "ExponentialLR",
+    "lr_scheduler_gen_params": {
+        "gamma": 0.99,
+        "last_epoch": -1
+    },
+    "lr_scheduler_disc": "ExponentialLR",
+    "lr_scheduler_disc_params": {
+        "gamma": 0.99,
+        "last_epoch": -1
+    },
+    "use_pqmf": false,
+    "diff_samples_for_G_and_D": false,
+    "discriminator_model": "hifigan_discriminator",
+    "generator_model": "hifigan_generator",
+    "generator_model_params": {
+        "resblock_type": "1",
+        "upsample_factors": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "upsample_initial_channel": 128,
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ]
+    },
+    "lr": 0.0001
+}

server/models/hifigan-v2/hifigan.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4095979afe120b8cd8addd0f617bf8a456b6c6c187e1bb5057f0b3166af241e9
+size 3731575

server/models/hifigan-v2/scale_stats.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df565ffd01d51ae8894063f0281a029f22b091e99187745f6838ebe750682181
+size 10680