Upload 3 files

config.json

@@ -0,0 +1,405 @@
+{
+    "output_path": "D:\\MULTI-LOD\\output\\",
+    "logger_uri": null,
+    "run_name": "vits_multilingual-lod",
+    "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",
+    "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": 0,
+    "target_loss": null,
+    "print_eval": false,
+    "test_delay_epochs": -1,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "precision": "fp16",
+    "epochs": 1000,
+    "batch_size": 8,
+    "eval_batch_size": 8,
+    "grad_clip": [
+        1000.0,
+        1000.0
+    ],
+    "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": 1,
+    "num_eval_loader_workers": 1,
+    "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": "multilingual_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "D:\\MULTI-LOD\\output\\phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.models.vits.VitsCharacters",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "abcdefghijklmnopqrstuvwxyz\u00b5\u00df\u00e0\u00e1\u00e2\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f1\u00f2\u00f3\u00f4\u00f6\u00f9\u00fa\u00fb\u00fc\u0105\u0107\u0119\u0142\u0144\u0153\u015b\u015f\u017a\u017c\u0192\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f\u0451\u0454\u0456\u0457\u0491\u04e7\u00ab\u00b0\u00b1\u00b5\u00bb$%&\u2018\u2019\u201a\u201c`\u201d\u201e\u00f5\u00e3\u0131",
+        "punctuations": "!\u00a1'(),-.:;\u00bf? ",
+        "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": 600000,
+    "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": "mailabs",
+            "dataset_name": "",
+            "path": "D:\\MULTI-LOD\\mailabs\\en",
+            "meta_file_train": null,
+            "ignored_speakers": null,
+            "language": "D:\\MULTI-LOD\\mailabs\\en",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "mailabs",
+            "dataset_name": "",
+            "path": "D:\\MULTI-LOD\\mailabs\\x-de",
+            "meta_file_train": null,
+            "ignored_speakers": null,
+            "language": "D:\\MULTI-LOD\\mailabs\\x-de",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "mailabs",
+            "dataset_name": "",
+            "path": "D:\\MULTI-LOD\\mailabs\\x-lb",
+            "meta_file_train": null,
+            "ignored_speakers": null,
+            "language": "D:\\MULTI-LOD\\mailabs\\x-lb",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "mailabs",
+            "dataset_name": "",
+            "path": "D:\\MULTI-LOD\\mailabs\\fr-fr",
+            "meta_file_train": null,
+            "ignored_speakers": null,
+            "language": "D:\\MULTI-LOD\\mailabs\\fr-fr",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "mailabs",
+            "dataset_name": "",
+            "path": "D:\\MULTI-LOD\\mailabs\\pt-br",
+            "meta_file_train": null,
+            "ignored_speakers": null,
+            "language": "D:\\MULTI-LOD\\mailabs\\pt-br",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "An der Z\u00e4it hunn sech den Nordwand an d\u2019Sonn gestridden, wie vun hinnen zwee wuel m\u00e9i staark wier, w\u00e9i e Wanderer, deen an ee waarme Mantel agepak war, iwwert de Wee koum.",
+            "Mod",
+            null,
+            "x-lb"
+        ],
+        [
+            "Si goufen sech eens, datt deej\u00e9inege fir dee St\u00e4erkste g\u00eblle sollt, deen de Wanderer forc\u00e9iere g\u00e9if, s\u00e4i Mantel auszedoen.",
+            "Mod",
+            null,
+            "x-lb"
+        ],
+        [
+            "Dunn huet d\u2019Sonn d\u2019Loft mat hire fr\u00ebndleche Strale gewiermt, a schonn no kuerzer Z\u00e4it huet de Wanderer s\u00e4i Mantel ausgedoen.",
+            "Max",
+            null,
+            "x-lb"
+        ],
+        [
+            "Do huet den Nordwand missen zouginn, datt d\u2019Sonn vun hinnen zwee dee St\u00e4erkste wier.",
+            "Max",
+            null,
+            "x-lb"
+        ],
+        [
+            "The North Wind and the Sun were disputing which was the stronger, when a traveler came along wrapped in a warm cloak.",
+            "Linda",
+            null,
+            "en"
+        ],
+        [
+            "They agreed that the one who first succeeded in making the traveler take his cloak off should be considered stronger than the other.",
+            "Linda",
+            null,
+            "en"
+        ],
+        [
+            "Then the North Wind blew as hard as he could, but the more he blew the more closely did the traveler fold his cloak around him; and at last the North Wind gave up the attempt.",
+            "Linda",
+            null,
+            "en"
+        ],
+        [
+            "Then the Sun shined out warmly, and immediately the traveler took off his cloak.",
+            "Linda",
+            null,
+            "en"
+        ],
+        [
+            "To vento norte e o sol discutiam quem era o mais forte, quando surgiu um viajante envolvido em uma capa.",
+            "Ed",
+            null,
+            "pt-br"
+        ],
+        [
+            "Eles concordam em que o primeiro que fizesse o viajante tirar a capa seria considerado o mais forte.",
+            "Ed",
+            null,
+            "pt-br"
+        ],
+        [
+            "Alors, la bise s'est mise \u00e0 souffler de toute sa force mais plus elle soufflait, plus le voyageur serrait son manteau autour de lui et \u00e0 la fin, la bise a renonc\u00e9 \u00e0 le lui faire \u00f4ter.",
+            "Nadine",
+            null,
+            "fr-fr"
+        ],
+        [
+            "La bise et le soleil se disputaient, chacun assurant qu'il \u00e9tait le plus fort, quand ils ont vu un voyageur qui s'avan\u00e7ait, envelopp\u00e9 dans son manteau.",
+            "Nadine",
+            null,
+            "fr-fr"
+        ],
+        [
+            "Ils sont tomb\u00e9s d'accord que celui qui arriverait le premier \u00e0 faire \u00f4ter son manteau au voyageur serait regard\u00e9 comme le plus fort.",
+            "Nadine",
+            null,
+            "fr-fr"
+        ],
+        [
+            "Alors le soleil a commenc\u00e9 \u00e0 briller et au bout d'un moment, le voyageur, r\u00e9chauff\u00e9, a \u00f4t\u00e9 son manteau.",
+            "Nadine",
+            null,
+            "fr-fr"
+        ],
+        [
+            "Einst stritten sich Nordwind und Sonne, wer von ihnen beiden wohl der St\u00e4rkere w\u00e4re, als ein Wanderer, der in einen warmen Mantel geh\u00fcllt war, des Weges daherkam.",
+            "Thorsten",
+            null,
+            "x-de"
+        ],
+        [
+            "Sie wurden einig, da\u00df derjenige f\u00fcr den St\u00e4rkeren gelten sollte, der den Wanderer zwingen w\u00fcrde, seinen Mantel abzunehmen.",
+            "Thorsten",
+            null,
+            "x-de"
+        ],
+        [
+            "Der Nordwind blies mit aller Macht, aber je mehr er blies, desto fester h\u00fcllte sich der Wanderer in seinen Mantel ein. Endlich gab der Nordwind den Kampf auf.",
+            "Thorsten",
+            null,
+            "x-de"
+        ],
+        [
+            "Nun erw\u00e4rmte die Sonne die Luft mit ihren freundlichen Strahlen, und schon nach wenigen Augenblicken zog der Wanderer seinen Mantel aus.",
+            "Thorsten",
+            null,
+            "x-de"
+        ]
+    ],
+    "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": true,
+    "language_weighted_sampler_alpha": 1.0,
+    "use_length_weighted_sampler": false,
+    "length_weighted_sampler_alpha": 1.0,
+    "model_args": {
+        "num_chars": 134,
+        "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": false,
+        "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": true,
+        "num_speakers": 6,
+        "speakers_file": "D:\\MULTI-LOD\\output\\vits_multilingual-lod-July-08-2024_12+24PM-dbf1a08a\\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": true,
+        "embedded_language_dim": 4,
+        "num_languages": 5,
+        "language_ids_file": "D:\\MULTI-LOD\\output\\vits_multilingual-lod-July-08-2024_12+24PM-dbf1a08a\\language_ids.json",
+        "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": true,
+    "speakers_file": "D:\\MULTI-LOD\\output\\vits_multilingual-lod-July-08-2024_12+24PM-dbf1a08a\\speakers.pth",
+    "speaker_embedding_channels": 256,
+    "language_ids_file": "D:\\MULTI-LOD\\output\\vits_multilingual-lod-July-08-2024_12+24PM-dbf1a08a\\language_ids.json",
+    "use_language_embedding": true,
+    "use_d_vector_file": false,
+    "d_vector_file": null,
+    "d_vector_dim": 0
+}

language_ids.json

@@ -0,0 +1,7 @@
+{
+    "D:\\MULTI-LOD\\mailabs\\en": 0,
+    "D:\\MULTI-LOD\\mailabs\\fr-fr": 1,
+    "D:\\MULTI-LOD\\mailabs\\pt-br": 2,
+    "D:\\MULTI-LOD\\mailabs\\x-de": 3,
+    "D:\\MULTI-LOD\\mailabs\\x-lb": 4
+}

speakers.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8454531413e0b86926fa0ff65ba47a32d0ac66fa8a35d5d23fee0ee34a197a2c
+size 928