Upload 5 files

config.json

@@ -0,0 +1,183 @@
+{
+    "output_path": "/storage/output",
+    "logger_uri": null,
+    "run_name": "run",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 50,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "log_model_step": null,
+    "save_step": 10000,
+    "save_n_checkpoints": 2,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 5000,
+    "target_loss": null,
+    "print_eval": true,
+    "test_delay_epochs": -1,
+    "run_eval": true,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "epochs": 1000,
+    "batch_size": 64,
+    "eval_batch_size": 32,
+    "grad_clip": 5.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "RAdam",
+    "optimizer_params": {
+        "betas": [
+            0.9,
+            0.998
+        ],
+        "weight_decay": 1e-06
+    },
+    "lr_scheduler": "ExponentialLR",
+    "lr_scheduler_params": {
+        "gamma": 0.95,
+        "last_epoch": -1
+    },
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": true,
+    "training_seed": 54321,
+    "model": "glow_tts",
+    "num_loader_workers": 8,
+    "num_eval_loader_workers": 8,
+    "use_noise_augment": true,
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 16000,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log10",
+        "do_trim_silence": true,
+        "trim_db": 45,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 50.0,
+        "mel_fmax": 8000.0,
+        "spec_gain": 1,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 0.0,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": "/app/tts-config/scale_stats.npy"
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": false,
+    "text_cleaner": "belarusian_cleaners",
+    "enable_eos_bos_chars": true,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.Graphemes",
+        "vocab_dict": null,
+        "pad": "_",
+        "eos": "~",
+        "bos": "^",
+        "blank": "@",
+        "characters": "\u0430\u0431\u0432\u0433\u0434\u0435\u0451\u0436\u0437\u0456\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u045e\u0444\u0445\u0446\u0447\u0448\u044b\u044c\u044d\u044e\u044f'",
+        "punctuations": "!,.? \u2014",
+        "phonemes": null,
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "sort_by_audio_len": false,
+    "min_audio_len": 1,
+    "max_audio_len": Infinity,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "compute_f0": false,
+    "compute_linear_spec": false,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "datasets": [
+        {
+            "name": "commonvoice-be",
+            "path": "/storage/be",
+            "meta_file_train": "metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        "\u0422\u044d\u0441\u0442\u0430\u0432\u044b \u0441\u043a\u0430\u0437.",
+        "\u0423 \u0440\u0443\u0434\u043e\u0433\u0430 \u0432\u0435\u0440\u0430\u0431\u2019\u044f \u045e \u0441\u0445\u043e\u0432\u0456\u0448\u0447\u044b \u043f\u0430\u0434 \u0444\u0430\u0442\u044d\u043b\u0435\u043c \u043b\u044f\u0436\u0430\u0446\u044c \u043d\u0435\u0439\u043a\u0456\u044f \u0433\u0430\u044e\u0447\u044b\u044f \u0437\u0451\u043b\u043a\u0456",
+        "\u042f \u0436\u043e\u0440\u0441\u0442\u043a\u0430 \u0437\u0430\u0431\u2019\u044e \u043f\u0440\u043e\u0441\u0442\u0430 \u045e \u0441\u044d\u0440\u0446\u0430 \u0433\u044d\u0442\u044b \u0440\u0430\u0441\u043a\u0432\u0435\u0447\u0430\u043d\u044b \u043f\u0440\u043e\u0444\u0456\u043b\u044c, \u0448\u0442\u043e \u0445\u043e\u0434\u0437\u0456\u0446\u044c \u043b\u044f \u043c\u0430\u0451\u0439 \u0445\u0430\u0442\u044b"
+    ],
+    "eval_split_max_size": null,
+    "eval_split_size": 0.01,
+    "use_speaker_weighted_sampler": false,
+    "speaker_weighted_sampler_alpha": 1.0,
+    "use_language_weighted_sampler": false,
+    "language_weighted_sampler_alpha": 1.0,
+    "num_chars": 43,
+    "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_enc": 192,
+    "hidden_channels_dec": 192,
+    "hidden_channels_dp": 256,
+    "dropout_p_dp": 0.1,
+    "dropout_p_dec": 0.05,
+    "mean_only": true,
+    "out_channels": 80,
+    "num_flow_blocks_dec": 12,
+    "inference_noise_scale": 0.0,
+    "kernel_size_dec": 5,
+    "dilation_rate": 1,
+    "num_block_layers": 4,
+    "num_speakers": 0,
+    "c_in_channels": 0,
+    "num_splits": 4,
+    "num_squeeze": 2,
+    "sigmoid_scale": false,
+    "d_vector_dim": 0,
+    "data_dep_init_steps": 10,
+    "style_wav_for_test": null,
+    "length_scale": 1.0,
+    "use_speaker_embedding": false,
+    "speakers_file": null,
+    "use_d_vector_file": false,
+    "d_vector_file": false,
+    "min_seq_len": 3,
+    "max_seq_len": 500,
+    "r": 1,
+    "restore_path": "/storage/output/newer-glow/checkpoint_70000.pth",
+    "github_branch": "* main"
+}

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57bf5d9621527a536ca1439c579e19c7dd85576bf91e6310fe6c59233bc98dc1
+size 343613991

scale_stats.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:573b2b88b380c58cc019e0c54818bdfc4c88f489f3728161df0eb1e70115ef82
+size 10788

vocoder-config.json

@@ -0,0 +1,187 @@
+{
+    "output_path": "/storage/output",
+    "logger_uri": null,
+    "run_name": "run",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "log_model_step": 2000,
+    "save_step": 2000,
+    "save_n_checkpoints": 2,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": "loss_1",
+    "print_eval": true,
+    "test_delay_epochs": 5,
+    "run_eval": true,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": null,
+    "scheduler_after_epoch": true,
+    "lr": 0.0001,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "weight_decay": 0.0
+    },
+    "lr_scheduler": null,
+    "lr_scheduler_params": null,
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": true,
+    "training_seed": 54321,
+    "model": "hifigan",
+    "num_loader_workers": 8,
+    "num_eval_loader_workers": 8,
+    "use_noise_augment": true,
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 16000,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log10",
+        "do_trim_silence": true,
+        "trim_db": 45,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 50.0,
+        "mel_fmax": 8000.0,
+        "spec_gain": 1,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 0.0,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": "/app/tts-config/scale_stats.npy"
+    },
+    "eval_split_size": 15,
+    "data_path": "/storage/be",
+    "feature_path": null,
+    "seq_len": 8192,
+    "pad_short": 2000,
+    "conv_pad": 0,
+    "use_cache": false,
+    "wd": 1e-06,
+    "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": 108.0,
+    "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": 16000,
+        "n_fft": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mels": 80,
+        "mel_fmin": 50.0,
+        "mel_fmax": 8000
+    },
+    "lr_gen": 1e-05,
+    "lr_disc": 1e-05,
+    "lr_scheduler_gen": "ExponentialLR",
+    "lr_scheduler_gen_params": {
+        "gamma": 0.999,
+        "last_epoch": -1
+    },
+    "lr_scheduler_disc": "ExponentialLR",
+    "lr_scheduler_disc_params": {
+        "gamma": 0.999,
+        "last_epoch": -1
+    },
+    "use_pqmf": false,
+    "diff_samples_for_G_and_D": false,
+    "discriminator_model": "hifigan_discriminator",
+    "generator_model": "hifigan_generator",
+    "generator_model_params": {
+        "upsample_factors": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "upsample_initial_channel": 512,
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "resblock_type": "1"
+    },
+    "restore_path": "/storage/output/finetuning-hifigan/checkpoint_286000.pth",
+    "github_branch": "* dev"
+}

vocoder.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e80d2eef7c5b58a174442071e779fee87b1e8a887ce9f18a1c50919afa136f7
+size 1016384188