feat: add model files

config.json

@@ -0,0 +1,330 @@
+{
+    "output_path": "/home/wayne/TTS/recipes/formosan/vits/results",
+    "logger_uri": null,
+    "run_name": "yourtts_formosan",
+    "project_name": "yourtts_formosan",
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 100,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "wandb",
+    "save_on_interrupt": true,
+    "log_model_step": 10000,
+    "save_step": 10000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 50,
+    "target_loss": "loss_1",
+    "print_eval": true,
+    "test_delay_epochs": -1,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "precision": "fp16",
+    "epochs": 500,
+    "batch_size": 54,
+    "eval_batch_size": 128,
+    "grad_clip": [
+        5.0,
+        5.0
+    ],
+    "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": null,
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 16,
+    "num_eval_loader_workers": 16,
+    "use_noise_augment": false,
+    "audio": {
+        "fft_size": 1024,
+        "sample_rate": 24000,
+        "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": true,
+    "text_cleaner": null,
+    "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": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u0361\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u02b2\u025a\u02de\u026b",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": null,
+        "is_unique": false,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 2,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": 720000,
+    "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": "formosan",
+            "dataset_name": "formosan_dict_ami_train",
+            "path": "/home/wayne/Corpora/formosan_clean_train",
+            "meta_file_train": "formosan_dict_ami.json",
+            "ignored_speakers": null,
+            "language": "ami",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "formosan",
+            "dataset_name": "formosan_dict_sdq_train",
+            "path": "/home/wayne/Corpora/formosan_clean_train",
+            "meta_file_train": "formosan_dict_sdq.json",
+            "ignored_speakers": null,
+            "language": "sdq",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "formosan",
+            "dataset_name": "formosan_dict_trv_train",
+            "path": "/home/wayne/Corpora/formosan_clean_train",
+            "meta_file_train": "formosan_dict_trv.json",
+            "ignored_speakers": null,
+            "language": "trv",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "formosan",
+            "dataset_name": "klokah_ami_train",
+            "path": "/home/wayne/Corpora/formosan_clean_train",
+            "meta_file_train": "klokah_ami.json",
+            "ignored_speakers": null,
+            "language": "ami",
+            "phonemizer": "",
+            "meta_file_val": "../formosan_clean_eval/klokah_eval_ami.json",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "formosan",
+            "dataset_name": "klokah_sdq_train",
+            "path": "/home/wayne/Corpora/formosan_clean_train",
+            "meta_file_train": "klokah_sdq.json",
+            "ignored_speakers": null,
+            "language": "sdq",
+            "phonemizer": "",
+            "meta_file_val": "../formosan_clean_eval/klokah_eval_sdq.json",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "formosan",
+            "dataset_name": "klokah_trv_train",
+            "path": "/home/wayne/Corpora/formosan_clean_train",
+            "meta_file_train": "klokah_trv.json",
+            "ignored_speakers": null,
+            "language": "trv",
+            "phonemizer": "",
+            "meta_file_val": "../formosan_clean_eval/klokah_eval_trv.json",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "u pajnijaru\u02a1",
+            null,
+            null,
+            "ami"
+        ],
+        [
+            "nu pan\u0261t\u0361sa\u0127 i matija",
+            null,
+            null,
+            "ami"
+        ],
+        [
+            "u ina \u0127aw ku",
+            null,
+            null,
+            "ami"
+        ]
+    ],
+    "eval_split_max_size": null,
+    "eval_split_size": 0.01429,
+    "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": 132,
+        "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": 8,
+        "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": "2",
+        "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,
+        "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": "speakers.pth",
+        "d_vector_file": [
+            "speaker_embs.pth"
+        ],
+        "speaker_embedding_channels": 256,
+        "use_d_vector_file": true,
+        "d_vector_dim": 512,
+        "detach_dp_input": true,
+        "use_language_embedding": true,
+        "embedded_language_dim": 4,
+        "num_languages": 0,
+        "language_ids_file": "language_ids.json",
+        "use_speaker_encoder_as_loss": false,
+        "speaker_encoder_config_path": "https://github.com/coqui-ai/TTS/releases/download/speaker_encoder_model/config_se.json",
+        "speaker_encoder_model_path": "https://github.com/coqui-ai/TTS/releases/download/speaker_encoder_model/model_se.pth.tar",
+        "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": 9.0,
+    "return_wav": true,
+    "use_weighted_sampler": false,
+    "weighted_sampler_attrs": {},
+    "weighted_sampler_multipliers": {},
+    "r": 1,
+    "num_speakers": 0,
+    "use_speaker_embedding": false,
+    "speakers_file": "speakers.pth",
+    "speaker_embedding_channels": 256,
+    "language_ids_file": "language_ids.json",
+    "use_language_embedding": true,
+    "use_d_vector_file": true,
+    "d_vector_file": [
+        "speaker_embs.pth"
+    ],
+    "d_vector_dim": 512
+}

language_ids.json

@@ -0,0 +1,5 @@
+{
+    "ami": 0,
+    "sdq": 1,
+    "trv": 2
+}

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02420f4c74c504dc23f7f2ee128cec1d2b61df39cb0b8fff29af6a53ca35fe6c
+size 1017382542

speaker_embs.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23325948ad9e3e7e38c621d5e31ae942c1b4bc40450b3fc89bbffd31077b85b
+size 1101114164

speakers.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63c8ac3866ecea5f10aec17a880e1c2b8c913478bf835f05d4e7bc8b6db989a
+size 15346784