Upload 4 files

config.json

@@ -0,0 +1,558 @@
+{
+    "output_path": "./models/11-ZA_multilingual",
+    "logger_uri": null,
+    "run_name": "11_ZA",
+    "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": 5000,
+    "save_step": 5000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "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": true,
+    "epochs": 1000,
+    "batch_size": 16,
+    "eval_batch_size": 16,
+    "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": null,
+    "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": 16000,
+        "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": "multilingual_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": {
+        "characters_class": "TTS.tts.models.vits.VitsCharacters",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "\u014b\u0266\u0254ma\u02d0spfut\u031dkr\u026ad\u025b!\u00a1'(),\u2014-.:;\u00bf?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",
+        "punctuations": "!\u00a1'(),-.:;\u00bf? ",
+        "phonemes": "\u014b\u0266\u0254ma\u02d0spfut\u031dkr\u026ad\u025baa\u02d0a\u0303\u02d0bcdefii\u02d0jklmnoprstuu\u02d0vwxyy\u02d0\u00e6\u02d0\u00f8\u014b\u0153\u0153\u02d0\u0254\u0254\u02d0\u0254\u0303\u02d0\u0258\u025b\u025b\u02d0\u025b\u0303\u02d0\u0261\u0266\u026a\u031d",
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": false,
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "min_audio_len": 32768,
+    "max_audio_len": 160000,
+    "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": "nchlt",
+            "dataset_name": "tts_eng",
+            "path": "",
+            "meta_file_train": "eng_metadata.txt",
+            "ignored_speakers": null,
+            "language": "eng",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_afr",
+            "path": "",
+            "meta_file_train": "afr_metadata.txt",
+            "ignored_speakers": null,
+            "language": "afr",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_zul",
+            "path": "",
+            "meta_file_train": "zul_metadata.txt",
+            "ignored_speakers": null,
+            "language": "zul",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_zho",
+            "path": "",
+            "meta_file_train": "xho_metadata.txt",
+            "ignored_speakers": null,
+            "language": "xho",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_ven",
+            "path": "",
+            "meta_file_train": "ven_metadata.txt",
+            "ignored_speakers": null,
+            "language": "ven",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_tso",
+            "path": "",
+            "meta_file_train": "tso_metadata.txt",
+            "ignored_speakers": null,
+            "language": "tso",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_tsn",
+            "path": "",
+            "meta_file_train": "tsn_metadata.txt",
+            "ignored_speakers": null,
+            "language": "tsn",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_sot",
+            "path": "",
+            "meta_file_train": "sot_metadata.txt",
+            "ignored_speakers": null,
+            "language": "sot",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_ssw",
+            "path": "",
+            "meta_file_train": "ssw_metadata.txt",
+            "ignored_speakers": null,
+            "language": "ssw",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_nbl",
+            "path": "",
+            "meta_file_train": "nbl_metadata.txt",
+            "ignored_speakers": null,
+            "language": "nbl",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "nchlt",
+            "dataset_name": "tts_nso",
+            "path": "",
+            "meta_file_train": "nso_metadata.txt",
+            "ignored_speakers": null,
+            "language": "nso",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "Something has to be put in place.",
+            "p244",
+            null,
+            "eng"
+        ],
+        [
+            "The gaseous matters (carbon dioxide, oxygen, nitrogen) enter the plant mainly by diffusion from the atmosphere,",
+            "lq_eng_f",
+            null,
+            "eng"
+        ],
+        [
+            "Anyone who was familiar with that area of Dallas would have known that the motorcade would probably pass the Texas School Book Depository to get from Main Street",
+            "Leah",
+            null,
+            "eng"
+        ],
+        [
+            "verbruik gedurende dieselfde",
+            "lq_afr_f",
+            null,
+            "afr"
+        ],
+        [
+            "In ons howe wil ons 'n regering van wette h\u00ea en nie van mans nie.",
+            "Willem",
+            null,
+            "afr"
+        ],
+        [
+            "persvrystellings aanbiedings tentoon",
+            "adri",
+            null,
+            "afr"
+        ],
+        [
+            "siphunyuke olakeni lukamama",
+            "lq_zul_f",
+            null,
+            "zul"
+        ],
+        [
+            "Abampofu bezwe elizungezile bahlala izigodlo zalo ezihlakazekile.",
+            "thando",
+            null,
+            "zul"
+        ],
+        [
+            "Futhi eyodwa enikeze izaba zokuphikisana nephakheji elinobuningi ekuseni ngakusasa ekuseni.",
+            "Themba",
+            null,
+            "zul"
+        ],
+        [
+            "le tjhabile le monatjana ho",
+            "lq_sot_f",
+            null,
+            "sot"
+        ],
+        [
+            "ha o ne o mpolella",
+            "lq_sot_f",
+            null,
+            "sot"
+        ],
+        [
+            "Ho sheba eufrate e kholo e koahelang phuleng ka tlase.",
+            "lq_sot_f",
+            null,
+            "sot"
+        ],
+        [
+            "pheji leyi ku fanele ku",
+            "lq_tso_f",
+            null,
+            "tso"
+        ],
+        [
+            "kota ku hlayela no langutisela",
+            "lq_tso_f",
+            null,
+            "tso"
+        ],
+        [
+            "vanwa milenge va kotaku tsutsuma",
+            "lq_tso_f",
+            null,
+            "tso"
+        ],
+        [
+            "motsu o o mo letshwaong",
+            "lq_tsn_f",
+            null,
+            "tsn"
+        ],
+        [
+            "itshokodisetsa eng tota ausi thando",
+            "lq_tsn_f",
+            null,
+            "tsn"
+        ],
+        [
+            "la kwa bogodimong jwa bolaodi",
+            "lq_tsn_f",
+            null,
+            "tsn"
+        ],
+        [
+            "kesinye nesinye isikhathi",
+            "lq_nbl_m",
+            null,
+            "nbl"
+        ],
+        [
+            "kibo boke abatlolisiweko",
+            "lq_nbl_m",
+            null,
+            "nbl"
+        ],
+        [
+            "kwamalungelo wabantu kanye",
+            "lq_nbl_m",
+            null,
+            "nbl"
+        ],
+        [
+            "nga thusa vhathu kana vhafarisi",
+            "lq_ven_m",
+            null,
+            "ven"
+        ],
+        [
+            "shumiselwaho vhutali i do tavhanyisa",
+            "lq_ven_m",
+            null,
+            "ven"
+        ],
+        [
+            "badela mushumi we a lova",
+            "lq_ven_m",
+            null,
+            "ven"
+        ],
+        [
+            "nanobe kuneluhlelo kwakhiwe",
+            "lq_ssw_f",
+            null,
+            "ssw"
+        ],
+        [
+            "umcimbi wekugidza umnandzi",
+            "lq_ssw_f",
+            null,
+            "ssw"
+        ],
+        [
+            "lomunye sitijabulisa ngawo",
+            "lq_ssw_f",
+            null,
+            "ssw"
+        ],
+        [
+            "ga setso se se itsego",
+            "lq_nso_m",
+            null,
+            "nso"
+        ],
+        [
+            "motho a ka ba a",
+            "lq_nso_m",
+            null,
+            "nso"
+        ],
+        [
+            "O ile a bolela gape gore o tla diri\u0161a sethunya ge e ba sebaka se ka t\u0161welela.",
+            "lq_nso_m",
+            null,
+            "nso"
+        ],
+        [
+            "ezigqibeleleyo zezemidlalo nezokuziphumza",
+            "lq_xho_m",
+            null,
+            "xho"
+        ],
+        [
+            "Ngeendlela zokufumana impilo ngokunyaniseka ukuba ilahlekile.",
+            "lq_xho_m",
+            null,
+            "xho"
+        ],
+        [
+            "nemeko yokuqesha yahlukene",
+            "lq_xho_f",
+            null,
+            "xho"
+        ]
+    ],
+    "eval_split_max_size": null,
+    "eval_split_size": 0.01,
+    "use_speaker_weighted_sampler": true,
+    "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": 236,
+        "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,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 1.0,
+        "max_inference_len": null,
+        "init_discriminator": false,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": true,
+        "num_speakers": 130,
+        "speakers_file": "./models/11-ZA_multilingual/11_ZA-May-16-2023_12+09PM-0000000/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": 12,
+        "num_languages": 11,
+        "language_ids_file": "./models/11-ZA_multilingual/11_ZA-May-16-2023_12+09PM-0000000/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": "./models/11-ZA_multilingual/11_ZA-May-16-2023_12+09PM-0000000/speakers.pth",
+    "speaker_embedding_channels": 256,
+    "language_ids_file": "./models/11-ZA_multilingual/11_ZA-May-16-2023_12+09PM-0000000/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 +1,13 @@
+{
+    "afr": 0,
+    "eng": 1,
+    "nbl": 2,
+    "nso": 3,
+    "sot": 4,
+    "ssw": 5,
+    "tsn": 6,
+    "tso": 7,
+    "ven": 8,
+    "xho": 9,
+    "zul": 10
+}

model_speakers.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f769b5fa40838d291024d57363d0abac06cae651f9bdc4da16a853435f7731
+size 2941

vits_11_ZA_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49bf95b0e87742db43b77b1c16ce9e9266dd6731ab7c30c7b9bf3129747bd96
+size 157017425