hifi-GAN

hifi-GAN/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

hifi-GAN/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": 0,
+    "num_val_loader_workers": 0,
+    "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": "/content/drive/My Drive/Colab Notebooks/data/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
+}

hifi-GAN/hifigan.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36be9f4b23132bafb015bf8c70519c38a3f4b2b04b94911b3bbf59b4eb6ea51
+size 3728970

hifi-GAN/model_file.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0dabdd041a7e24231513941f740e9e08cd1d843cdcf5906258412ea0c8013f0
+size 860304463

hifi-GAN/scale_stats.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17eb58e8fd0bf2e3a0c4cf558278470caf080ff061221b83628d1b3afd1aa8dd
+size 10650

hifi-GAN/scale_stats_new.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7f342d97766ea8bf4d626af96f16b74e809880fae8d2201be99614086b4076
+size 10684

hifi-GAN/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/soohyunn/hifi-GAN

hifi-gan.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4a59a7b1624f7f6779b679299fc53e51ccb92fc106722f5504814f28b40089
+size 1273530