Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,271 @@
+{
+    "output_path": "voco_logs/",
+    "logger_uri": null,
+    "run_name": "voco-single",
+    "project_name": "voco-single-female",
+    "run_description": "voco-tts single female",
+    "print_step": 50,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 5000,
+    "save_n_checkpoints": 10,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 0,
+    "target_loss": null,
+    "print_eval": false,
+    "test_delay_epochs": -1,
+    "run_eval": false,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "precision": "fp16",
+    "epochs": 1500,
+    "batch_size": 16,
+    "eval_batch_size": 16,
+    "grad_clip": [
+        5.0,
+        5.0
+    ],
+    "scheduler_after_epoch": true,
+    "lr": 5e-05,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "weight_decay": 0.01
+    },
+    "lr_scheduler": "ReduceROnPlateau",
+    "lr_scheduler_params": {
+        "mode": "min",
+        "factor": 0.5,
+        "patience": 5
+    },
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 12,
+    "num_eval_loader_workers": 12,
+    "use_noise_augment": true,
+    "audio": {
+        "fft_size": 1024,
+        "sample_rate": 22050,
+        "win_length": 1024,
+        "hop_length": 256,
+        "num_mels": 80,
+        "mel_fmin": 0,
+        "mel_fmax": null
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": false,
+    "text_cleaner": "basic_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.Graphemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\u014a\u014b",
+        "punctuations": "!'(),-.:;?\" ",
+        "phonemes": null,
+        "is_unique": false,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": Infinity,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "compute_f0": false,
+    "compute_energy": false,
+    "compute_linear_spec": true,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "ljspeech",
+            "dataset_name": "",
+            "path": "ones_data/",
+            "meta_file_train": "wavs/metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "Abantu abasinga obungi tebamanyi kwogera bulungi Luganda."
+        ],
+        [
+            "Kabaka waffe yasiimye naggulawo e ddwaliro lya kookolo."
+        ],
+        [
+            "Minisita yasabye abakyala bonna okwegemesa ekirwadde."
+        ],
+        [
+            "Ennyanja yaffe egenda kusaanawo yonna singa gavumenti teteekamu maanyi."
+        ]
+    ],
+    "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,
+    "use_length_weighted_sampler": false,
+    "length_weighted_sampler_alpha": 1.0,
+    "model_args": {
+        "num_chars": 70,
+        "out_channels": 513,
+        "spec_segment_size": 32,
+        "hidden_channels": 192,
+        "hidden_channels_ffn_text_encoder": 768,
+        "num_heads_text_encoder": 2,
+        "num_layers_text_encoder": 6,
+        "kernel_size_text_encoder": 3,
+        "dropout_p_text_encoder": 0.25,
+        "dropout_p_duration_predictor": 0.5,
+        "kernel_size_posterior_encoder": 5,
+        "dilation_rate_posterior_encoder": 1,
+        "num_layers_posterior_encoder": 16,
+        "kernel_size_flow": 5,
+        "dilation_rate_flow": 1,
+        "num_layers_flow": 4,
+        "resblock_type_decoder": "1",
+        "resblock_kernel_sizes_decoder": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes_decoder": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates_decoder": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel_decoder": 512,
+        "upsample_kernel_sizes_decoder": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "periods_multi_period_discriminator": [
+            2,
+            3,
+            5,
+            7,
+            11
+        ],
+        "use_sdp": true,
+        "noise_scale": 1.0,
+        "inference_noise_scale": 0.667,
+        "length_scale": 1.0,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 1.0,
+        "max_inference_len": null,
+        "init_discriminator": true,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": false,
+        "num_speakers": 0,
+        "speakers_file": null,
+        "d_vector_file": null,
+        "speaker_embedding_channels": 256,
+        "use_d_vector_file": false,
+        "d_vector_dim": 0,
+        "detach_dp_input": true,
+        "use_language_embedding": false,
+        "embedded_language_dim": 4,
+        "num_languages": 0,
+        "language_ids_file": null,
+        "use_speaker_encoder_as_loss": false,
+        "speaker_encoder_config_path": "",
+        "speaker_encoder_model_path": "",
+        "condition_dp_on_speaker": true,
+        "freeze_encoder": false,
+        "freeze_DP": false,
+        "freeze_PE": false,
+        "freeze_flow_decoder": false,
+        "freeze_waveform_decoder": false,
+        "encoder_sample_rate": null,
+        "interpolate_z": true,
+        "reinit_DP": false,
+        "reinit_text_encoder": false
+    },
+    "lr_gen": 0.0002,
+    "lr_disc": 0.0002,
+    "lr_scheduler_gen": "ExponentialLR",
+    "lr_scheduler_gen_params": {
+        "gamma": 0.999875,
+        "last_epoch": -1
+    },
+    "lr_scheduler_disc": "ExponentialLR",
+    "lr_scheduler_disc_params": {
+        "gamma": 0.999875,
+        "last_epoch": -1
+    },
+    "kl_loss_alpha": 1.0,
+    "disc_loss_alpha": 1.0,
+    "gen_loss_alpha": 1.0,
+    "feat_loss_alpha": 1.0,
+    "mel_loss_alpha": 45.0,
+    "dur_loss_alpha": 1.0,
+    "speaker_encoder_loss_alpha": 1.0,
+    "return_wav": true,
+    "use_weighted_sampler": false,
+    "weighted_sampler_attrs": {},
+    "weighted_sampler_multipliers": {},
+    "r": 1,
+    "num_speakers": 0,
+    "use_speaker_embedding": false,
+    "speakers_file": null,
+    "speaker_embedding_channels": 256,
+    "language_ids_file": null,
+    "use_language_embedding": false,
+    "use_d_vector_file": false,
+    "d_vector_file": null,
+    "d_vector_dim": 0,
+    "restore_path": "tts_models--en--ljspeech--vits/model_file.pth",
+    "github_branch": "* dev"
+}

best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410cdfbc715818b7b6c64741f6a59fcabb551010e490f187edac41a99785811f
+size 997781046

best_model_1009721.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410cdfbc715818b7b6c64741f6a59fcabb551010e490f187edac41a99785811f
+size 997781046

checkpoint_1060000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9cb372bc48ebd315b3937cf8afce62a98f40f2ec5fc1c397d28513731eb6b69
+size 997781046

checkpoint_1065000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37e0c331b43e2510e6193109589d84026c1935d8e48b663be2ac80fe44c9f51
+size 997781046

checkpoint_1070000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f196fb32e6343f2549ab8905e95c6cd6f2e135fe858f09ec9a2bf39438f1bc1a
+size 997781046

checkpoint_1075000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbda74dac6fda9912730a95aff4c614f5cb8fbf84af8012a700fb722a2e3033f
+size 997781046

checkpoint_1080000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e44170cfab9f219a927fa3dfd4d9abb2066bf46d6a3eac7389a4ad44f29e6c6
+size 997781046

checkpoint_1085000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef7616851f064c5ac77bc99482cde3181c13a1f392b6f533c765aed797a1827
+size 997781046

checkpoint_1090000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def2deaa32970ea9e711fa4019ddf266f0067b8fba3ca1c33ad30b61a281d8cf
+size 997781046

checkpoint_1095000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51672d910e484f95362e45ed88f6e8750b8e22f33d3318ad57b392049337ef1c
+size 997781046

checkpoint_1100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4cd957ba40c994d099b84b40d5be061f58ebff358946db53e8764eb216b8516
+size 997781046

checkpoint_1105000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd250079d990695a48116c10f76dd1bb4ff7fe4d0f7a85a769a2208b2ecbc3a
+size 997781046

config.json

@@ -0,0 +1,271 @@
+{
+    "output_path": "voco_logs/",
+    "logger_uri": null,
+    "run_name": "voco-single",
+    "project_name": "voco-single-female",
+    "run_description": "voco-tts single female",
+    "print_step": 50,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 5000,
+    "save_n_checkpoints": 10,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 0,
+    "target_loss": null,
+    "print_eval": false,
+    "test_delay_epochs": -1,
+    "run_eval": false,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "precision": "fp16",
+    "epochs": 1500,
+    "batch_size": 16,
+    "eval_batch_size": 16,
+    "grad_clip": [
+        5.0,
+        5.0
+    ],
+    "scheduler_after_epoch": true,
+    "lr": 5e-05,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "weight_decay": 0.01
+    },
+    "lr_scheduler": "ReduceROnPlateau",
+    "lr_scheduler_params": {
+        "mode": "min",
+        "factor": 0.5,
+        "patience": 5
+    },
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 12,
+    "num_eval_loader_workers": 12,
+    "use_noise_augment": true,
+    "audio": {
+        "fft_size": 1024,
+        "sample_rate": 22050,
+        "win_length": 1024,
+        "hop_length": 256,
+        "num_mels": 80,
+        "mel_fmin": 0,
+        "mel_fmax": null
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": false,
+    "text_cleaner": "basic_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.Graphemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\u014a\u014b",
+        "punctuations": "!'(),-.:;?\" ",
+        "phonemes": null,
+        "is_unique": false,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": Infinity,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "compute_f0": false,
+    "compute_energy": false,
+    "compute_linear_spec": true,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "ljspeech",
+            "dataset_name": "",
+            "path": "ones_data/",
+            "meta_file_train": "wavs/metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "Abantu abasinga obungi tebamanyi kwogera bulungi Luganda."
+        ],
+        [
+            "Kabaka waffe yasiimye naggulawo e ddwaliro lya kookolo."
+        ],
+        [
+            "Minisita yasabye abakyala bonna okwegemesa ekirwadde."
+        ],
+        [
+            "Ennyanja yaffe egenda kusaanawo yonna singa gavumenti teteekamu maanyi."
+        ]
+    ],
+    "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,
+    "use_length_weighted_sampler": false,
+    "length_weighted_sampler_alpha": 1.0,
+    "model_args": {
+        "num_chars": 70,
+        "out_channels": 513,
+        "spec_segment_size": 32,
+        "hidden_channels": 192,
+        "hidden_channels_ffn_text_encoder": 768,
+        "num_heads_text_encoder": 2,
+        "num_layers_text_encoder": 6,
+        "kernel_size_text_encoder": 3,
+        "dropout_p_text_encoder": 0.25,
+        "dropout_p_duration_predictor": 0.5,
+        "kernel_size_posterior_encoder": 5,
+        "dilation_rate_posterior_encoder": 1,
+        "num_layers_posterior_encoder": 16,
+        "kernel_size_flow": 5,
+        "dilation_rate_flow": 1,
+        "num_layers_flow": 4,
+        "resblock_type_decoder": "1",
+        "resblock_kernel_sizes_decoder": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes_decoder": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates_decoder": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel_decoder": 512,
+        "upsample_kernel_sizes_decoder": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "periods_multi_period_discriminator": [
+            2,
+            3,
+            5,
+            7,
+            11
+        ],
+        "use_sdp": true,
+        "noise_scale": 1.0,
+        "inference_noise_scale": 0.667,
+        "length_scale": 1.0,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 1.0,
+        "max_inference_len": null,
+        "init_discriminator": true,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": false,
+        "num_speakers": 0,
+        "speakers_file": null,
+        "d_vector_file": null,
+        "speaker_embedding_channels": 256,
+        "use_d_vector_file": false,
+        "d_vector_dim": 0,
+        "detach_dp_input": true,
+        "use_language_embedding": false,
+        "embedded_language_dim": 4,
+        "num_languages": 0,
+        "language_ids_file": null,
+        "use_speaker_encoder_as_loss": false,
+        "speaker_encoder_config_path": "",
+        "speaker_encoder_model_path": "",
+        "condition_dp_on_speaker": true,
+        "freeze_encoder": false,
+        "freeze_DP": false,
+        "freeze_PE": false,
+        "freeze_flow_decoder": false,
+        "freeze_waveform_decoder": false,
+        "encoder_sample_rate": null,
+        "interpolate_z": true,
+        "reinit_DP": false,
+        "reinit_text_encoder": false
+    },
+    "lr_gen": 0.0002,
+    "lr_disc": 0.0002,
+    "lr_scheduler_gen": "ExponentialLR",
+    "lr_scheduler_gen_params": {
+        "gamma": 0.999875,
+        "last_epoch": -1
+    },
+    "lr_scheduler_disc": "ExponentialLR",
+    "lr_scheduler_disc_params": {
+        "gamma": 0.999875,
+        "last_epoch": -1
+    },
+    "kl_loss_alpha": 1.0,
+    "disc_loss_alpha": 1.0,
+    "gen_loss_alpha": 1.0,
+    "feat_loss_alpha": 1.0,
+    "mel_loss_alpha": 45.0,
+    "dur_loss_alpha": 1.0,
+    "speaker_encoder_loss_alpha": 1.0,
+    "return_wav": true,
+    "use_weighted_sampler": false,
+    "weighted_sampler_attrs": {},
+    "weighted_sampler_multipliers": {},
+    "r": 1,
+    "num_speakers": 0,
+    "use_speaker_embedding": false,
+    "speakers_file": null,
+    "speaker_embedding_channels": 256,
+    "language_ids_file": null,
+    "use_language_embedding": false,
+    "use_d_vector_file": false,
+    "d_vector_file": null,
+    "d_vector_dim": 0,
+    "restore_path": "tts_models--en--ljspeech--vits/model_file.pth",
+    "github_branch": "* dev"
+}

events.out.tfevents.1740471046.tts-lug.182735.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f14c0a6cdab242cb79afe41a7b7ca862d239a3d3ffa2d197ec4b5568ec3e74
+size 1427651348

train_tts.py

@@ -0,0 +1,71 @@
+import os
+from dataclasses import dataclass, field
+
+from trainer import Trainer, TrainerArgs
+
+from TTS.config import load_config, register_config
+from TTS.tts.datasets import load_tts_samples
+from TTS.tts.models import setup_model
+
+
+@dataclass
+class TrainTTSArgs(TrainerArgs):
+    config_path: str = field(default=None, metadata={"help": "Path to the config file."})
+
+
+def main():
+    """Run `tts` model training directly by a `config.json` file."""
+    # init trainer args
+    train_args = TrainTTSArgs()
+    parser = train_args.init_argparse(arg_prefix="")
+
+    # override trainer args from comman-line args
+    args, config_overrides = parser.parse_known_args()
+    train_args.parse_args(args)
+
+    # load config.json and register
+    if args.config_path or args.continue_path:
+        if args.config_path:
+            # init from a file
+            config = load_config(args.config_path)
+            if len(config_overrides) > 0:
+                config.parse_known_args(config_overrides, relaxed_parser=True)
+        elif args.continue_path:
+            # continue from a prev experiment
+            config = load_config(os.path.join(args.continue_path, "config.json"))
+            if len(config_overrides) > 0:
+                config.parse_known_args(config_overrides, relaxed_parser=True)
+        else:
+            # init from console args
+            from TTS.config.shared_configs import BaseTrainingConfig  # pylint: disable=import-outside-toplevel
+
+            config_base = BaseTrainingConfig()
+            config_base.parse_known_args(config_overrides)
+            config = register_config(config_base.model)()
+
+    # load training samples
+    train_samples, eval_samples = load_tts_samples(
+        config.datasets,
+        eval_split=True,
+        eval_split_max_size=config.eval_split_max_size,
+        eval_split_size=config.eval_split_size,
+    )
+
+    # init the model from config
+    model = setup_model(config, train_samples + eval_samples)
+
+    # init the trainer and 🚀
+    trainer = Trainer(
+        train_args,
+        model.config,
+        config.output_path,
+        model=model,
+        train_samples=train_samples,
+        eval_samples=eval_samples,
+        parse_command_line_args=False,
+    )
+    trainer.fit()
+
+
+if __name__ == "__main__":
+    main()