feat: add files

checkpoint_1260000-inference.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399e41d1e2a704056b96b82692dd7d0fa3cc351ea20d277f534f7a656522eb74
+size 345999149

config.json

@@ -0,0 +1,308 @@
+{
+    "output_path": "/workspace/TTS",
+    "logger_uri": null,
+    "run_name": "vits_indonesian_multispeaker",
+    "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": 10000,
+    "save_step": 10000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": null,
+    "print_eval": true,
+    "test_delay_epochs": -1,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 8,
+    "grad_clip": [
+        1000,
+        1000
+    ],
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "weight_decay": 0.01
+    },
+    "lr_scheduler": "",
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 4,
+    "num_eval_loader_workers": 4,
+    "use_noise_augment": false,
+    "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": "en-us",
+    "compute_input_seq_cache": true,
+    "text_cleaner": "basic_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/workspace/TTS/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.models.vits.VitsCharacters",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "abdefhijklmnoprstuwxz\u014b\u0254\u0259\u025b\u0261\u026a\u0272\u0283\u028a\u0292\u0294\u02c8",
+        "punctuations": " !,.?",
+        "phonemes": null,
+        "is_unique": true,
+        "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_linear_spec": true,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "datasets": [
+        {
+            "name": "coqui",
+            "path": "dataset",
+            "meta_file_train": "metadata-wibowo.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "name": "coqui",
+            "path": "dataset",
+            "meta_file_train": "metadata-ardi.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "name": "coqui",
+            "path": "dataset",
+            "meta_file_train": "metadata-gadis.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "name": "coqui",
+            "path": "dataset",
+            "meta_file_train": "metadata-javanese.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "name": "coqui",
+            "path": "dataset",
+            "meta_file_train": "metadata-sundanese.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "\u02c8budi \u02c8makan \u02c8tahu, \u02c8soto, dan \u02c8tempe",
+            "wibowo",
+            null,
+            null
+        ],
+        [
+            "\u02c8tadi \u02c8pa\u0261i \u02c8ali dan \u02c8\u0283afi s\u0259\u02c8dan\u0294 m\u0259n\u0294\u02c8\u0261unakan \u02c8m\u0254t\u0254r di \u02c8kantor \u02c8m\u0259r\u025bka.",
+            "ardi",
+            null,
+            null
+        ],
+        [
+            "\u02c8ardi dan \u02c8thomas \u02c8m\u0259nud\u0292u \u02c8k\u0259 \u02c8s\u0259kolah \u02c8pada \u02c8puk\u028al \u02c8s\u0259pul\u028ah \u02c8pa\u0261i.",
+            "gadis",
+            null,
+            null
+        ],
+        [
+            "\u02c8ardi dan \u02c8thomas \u02c8m\u0259nud\u0292u \u02c8k\u0259 \u02c8s\u0259kolah \u02c8pada \u02c8puk\u028al \u02c8s\u0259pul\u028ah \u02c8pa\u0261i.",
+            "JV-00264",
+            null,
+            null
+        ],
+        [
+            "\u02c8ardi dan \u02c8thomas \u02c8m\u0259nud\u0292u \u02c8k\u0259 \u02c8s\u0259kolah \u02c8pada \u02c8puk\u028al \u02c8s\u0259pul\u028ah \u02c8pa\u0261i.",
+            "SU-00060",
+            null,
+            null
+        ]
+    ],
+    "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": 40,
+        "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": 0.1,
+        "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": 0.33,
+        "length_scale": 1,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 0.33,
+        "max_inference_len": null,
+        "init_discriminator": true,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": true,
+        "num_speakers": 83,
+        "speakers_file": "speakers.pth",
+        "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": true,
+        "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,
+    "r": 1,
+    "num_speakers": 0,
+    "use_speaker_embedding": true,
+    "speakers_file": "speakers.pth",
+    "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
+}

speakers.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51f3840be3e92a96805c5ec81ee0948a44f965e77d980b0ad59fe0f661c2d17
+size 1839