Upload 24 files

local_coqui_tts_models/tts_models--ca--custom--vits/._model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbc7856dd427df6aeb4b7900dc629272704cdd8dea679a151ea15122fccc77b
+size 1548

local_coqui_tts_models/tts_models--ca--custom--vits/._speaker_ids.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6642567185879c93920f9e8ded216aac964f512dcdeb52b534dfbe1547cd01e2
+size 1542

local_coqui_tts_models/tts_models--ca--custom--vits/__MACOSX/tts_models--ca--custom--vits/._model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbc7856dd427df6aeb4b7900dc629272704cdd8dea679a151ea15122fccc77b
+size 1548

local_coqui_tts_models/tts_models--ca--custom--vits/__MACOSX/tts_models--ca--custom--vits/._speaker_ids.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6642567185879c93920f9e8ded216aac964f512dcdeb52b534dfbe1547cd01e2
+size 1542

local_coqui_tts_models/tts_models--ca--custom--vits/config.json

@@ -0,0 +1,269 @@
+{
+    "output_path": "/gpfs/projects/bsc88/speech/tts/TTS_v0.8.0/recipes/multispeaker/experiments_from_previous",
+    "logger_uri": null,
+    "run_name": "multispeaker_vits_ca_1e4_1e4_32",
+    "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": 1000,
+    "save_step": 1000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": true,
+    "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,
+    "precision": "fp16",
+    "epochs": 1000,
+    "batch_size": 16,
+    "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": "",
+    "lr_scheduler_params": null,
+    "use_grad_scaler": false,
+    "allow_tf32": 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": true,
+    "phonemizer": "espeak",
+    "phoneme_language": "ca",
+    "compute_input_seq_cache": true,
+    "text_cleaner": "multilingual_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/gpfs/projects/bsc88/speech/tts/TTS_v0.8.0/recipes/multispeaker/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.IPAPhonemes",
+        "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\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": 5,
+    "loss_masking": null,
+    "min_audio_len": 1,
+    "max_audio_len": Infinity,
+    "min_text_len": 1,
+    "max_text_len": 325,
+    "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": "vctk_old",
+            "dataset_name": "vctk_old",
+            "path": "/gpfs/scratch/bsc88/bsc88474/data/multispeaker_ca",
+            "meta_file_train": "",
+            "ignored_speakers": [
+                "uri",
+                "09796",
+                "05450"
+            ],
+            "language": "ca",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "Per exemple, dels nostres bancs que inverteixen en armament de les nostres empreses."
+        ],
+        [
+            "Preguntin-se si aix\u00f2 era necessari."
+        ],
+        [
+            "La suposada ocultaci\u00f3 dels informes que advertien de risc s\u00edsmic."
+        ],
+        [
+            "\u00c9s de 633 milions d'euros quan es far\u00e0 la publicaci\u00f3 detallada."
+        ]
+    ],
+    "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": 131,
+        "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": 0.667,
+        "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": 257,
+        "speakers_file": "/Users/drew/Library/Application Support/tts/tts_models--ca--custom--vits/speaker_ids.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": false,
+        "reinit_text_encoder": false
+    },
+    "lr_gen": 0.0001,
+    "lr_disc": 0.0001,
+    "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": null,
+    "weighted_sampler_multipliers": null,
+    "r": 1,
+    "num_speakers": 257,
+    "use_speaker_embedding": true,
+    "speakers_file": "/Users/drew/Library/Application Support/tts/tts_models--ca--custom--vits/speaker_ids.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
+}

local_coqui_tts_models/tts_models--ca--custom--vits/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15fa7d2052bada1cf421e49d2d03b00e95b49fcd0e42b7af1d92da2880cdecc
+size 1038659133

local_coqui_tts_models/tts_models--ca--custom--vits/speaker_ids.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dacda0b8dd3e111c5072f8f33c08b4a29b92ac79aaf22ceca912d01e7deb905
+size 30191

local_coqui_tts_models/tts_models--en--vctk--fast_pitch/config.json

@@ -0,0 +1,218 @@
+{
+    "output_path": "/home/ubuntu/TTS/recipes/vctk/fast_pitch",
+    "logger_uri": null,
+    "run_name": "fast_pitch_ljspeech",
+    "project_name": null,
+    "run_description": "",
+    "print_step": 50,
+    "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": 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": false,
+    "precision": "fp16",
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": 5.0,
+    "scheduler_after_epoch": false,
+    "lr": 0.0001,
+    "optimizer": "Adam",
+    "optimizer_params": {
+        "betas": [
+            0.9,
+            0.998
+        ],
+        "weight_decay": 1e-06
+    },
+    "lr_scheduler": "NoamLR",
+    "lr_scheduler_params": {
+        "warmup_steps": 4000
+    },
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": true,
+    "training_seed": 54321,
+    "model": "fast_pitch",
+    "num_loader_workers": 8,
+    "num_eval_loader_workers": 4,
+    "use_noise_augment": false,
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 22050,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log",
+        "do_trim_silence": true,
+        "trim_db": 23,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": 8000.0,
+        "spec_gain": 1,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 0.0,
+        "signal_norm": false,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": true,
+    "phonemizer": "gruut",
+    "phoneme_language": "en-us",
+    "compute_input_seq_cache": true,
+    "text_cleaner": "english_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/home/ubuntu/TTS/recipes/vctk/fast_pitch/phoneme_cache",
+    "characters": {
+        "characters_class": null,
+        "vocab_dict": null,
+        "pad": "_",
+        "eos": "~",
+        "bos": "^",
+        "blank": null,
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz!'(),-.:;? ",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": "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\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u02b2\u025a\u02de\u026b",
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": false,
+    "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": true,
+    "compute_energy": false,
+    "compute_linear_spec": false,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "/home/ubuntu/TTS/VCTK-Corpus-removed-silence",
+            "meta_file_train": "",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
+        "Be a voice, not an echo.",
+        "I'm sorry Dave. I'm afraid I can't do that.",
+        "This cake is great. It's so delicious and moist.",
+        "Prior to November 22, 1963."
+    ],
+    "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,
+    "base_model": "forward_tts",
+    "model_args": {
+        "num_chars": 130,
+        "out_channels": 80,
+        "hidden_channels": 384,
+        "use_aligner": true,
+        "use_pitch": true,
+        "pitch_predictor_hidden_channels": 256,
+        "pitch_predictor_kernel_size": 3,
+        "pitch_predictor_dropout_p": 0.1,
+        "pitch_embedding_kernel_size": 3,
+        "use_energy": false,
+        "energy_predictor_hidden_channels": 256,
+        "energy_predictor_kernel_size": 3,
+        "energy_predictor_dropout_p": 0.1,
+        "energy_embedding_kernel_size": 3,
+        "duration_predictor_hidden_channels": 256,
+        "duration_predictor_kernel_size": 3,
+        "duration_predictor_dropout_p": 0.1,
+        "positional_encoding": true,
+        "poisitonal_encoding_use_scale": true,
+        "length_scale": 1,
+        "encoder_type": "fftransformer",
+        "encoder_params": {
+            "hidden_channels_ffn": 1024,
+            "num_heads": 1,
+            "num_layers": 6,
+            "dropout_p": 0.1
+        },
+        "decoder_type": "fftransformer",
+        "decoder_params": {
+            "hidden_channels_ffn": 1024,
+            "num_heads": 1,
+            "num_layers": 6,
+            "dropout_p": 0.1
+        },
+        "detach_duration_predictor": false,
+        "max_duration": 75,
+        "num_speakers": 108,
+        "use_speaker_embedding": true,
+        "speakers_file": "/Users/drew/Library/Application Support/tts/tts_models--en--vctk--fast_pitch/speaker_ids.json",
+        "use_d_vector_file": false,
+        "d_vector_dim": 0,
+        "d_vector_file": null
+    },
+    "num_speakers": 0,
+    "speakers_file": "/Users/drew/Library/Application Support/tts/tts_models--en--vctk--fast_pitch/speaker_ids.json",
+    "use_speaker_embedding": true,
+    "use_d_vector_file": false,
+    "d_vector_file": false,
+    "d_vector_dim": 0,
+    "spec_loss_type": "mse",
+    "duration_loss_type": "mse",
+    "use_ssim_loss": true,
+    "ssim_loss_alpha": 1.0,
+    "spec_loss_alpha": 1.0,
+    "aligner_loss_alpha": 1.0,
+    "pitch_loss_alpha": 1.0,
+    "dur_loss_alpha": 1.0,
+    "binary_align_loss_alpha": 1.0,
+    "binary_loss_warmup_epochs": 150,
+    "min_seq_len": 13,
+    "max_seq_len": 500000,
+    "r": 1,
+    "f0_cache_path": "/home/ubuntu/TTS/recipes/vctk/fast_pitch/f0_cache"
+}

local_coqui_tts_models/tts_models--en--vctk--fast_pitch/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5bd8f0b2bb7222be9859f308e0ec22223f875194ec17f70358a598d4c9a20f6
+size 458564167

local_coqui_tts_models/tts_models--en--vctk--fast_pitch/speaker_ids.json

@@ -0,0 +1,110 @@
+{
+    "VCTK_p225": 0,
+    "VCTK_p226": 1,
+    "VCTK_p227": 2,
+    "VCTK_p228": 3,
+    "VCTK_p229": 4,
+    "VCTK_p230": 5,
+    "VCTK_p231": 6,
+    "VCTK_p232": 7,
+    "VCTK_p233": 8,
+    "VCTK_p234": 9,
+    "VCTK_p236": 10,
+    "VCTK_p237": 11,
+    "VCTK_p238": 12,
+    "VCTK_p239": 13,
+    "VCTK_p240": 14,
+    "VCTK_p241": 15,
+    "VCTK_p243": 16,
+    "VCTK_p244": 17,
+    "VCTK_p245": 18,
+    "VCTK_p246": 19,
+    "VCTK_p247": 20,
+    "VCTK_p248": 21,
+    "VCTK_p249": 22,
+    "VCTK_p250": 23,
+    "VCTK_p251": 24,
+    "VCTK_p252": 25,
+    "VCTK_p253": 26,
+    "VCTK_p254": 27,
+    "VCTK_p255": 28,
+    "VCTK_p256": 29,
+    "VCTK_p257": 30,
+    "VCTK_p258": 31,
+    "VCTK_p259": 32,
+    "VCTK_p260": 33,
+    "VCTK_p261": 34,
+    "VCTK_p262": 35,
+    "VCTK_p263": 36,
+    "VCTK_p264": 37,
+    "VCTK_p265": 38,
+    "VCTK_p266": 39,
+    "VCTK_p267": 40,
+    "VCTK_p268": 41,
+    "VCTK_p269": 42,
+    "VCTK_p270": 43,
+    "VCTK_p271": 44,
+    "VCTK_p272": 45,
+    "VCTK_p273": 46,
+    "VCTK_p274": 47,
+    "VCTK_p275": 48,
+    "VCTK_p276": 49,
+    "VCTK_p277": 50,
+    "VCTK_p278": 51,
+    "VCTK_p279": 52,
+    "VCTK_p280": 53,
+    "VCTK_p281": 54,
+    "VCTK_p282": 55,
+    "VCTK_p283": 56,
+    "VCTK_p284": 57,
+    "VCTK_p285": 58,
+    "VCTK_p286": 59,
+    "VCTK_p287": 60,
+    "VCTK_p288": 61,
+    "VCTK_p292": 62,
+    "VCTK_p293": 63,
+    "VCTK_p294": 64,
+    "VCTK_p295": 65,
+    "VCTK_p297": 66,
+    "VCTK_p298": 67,
+    "VCTK_p299": 68,
+    "VCTK_p300": 69,
+    "VCTK_p301": 70,
+    "VCTK_p302": 71,
+    "VCTK_p303": 72,
+    "VCTK_p304": 73,
+    "VCTK_p305": 74,
+    "VCTK_p306": 75,
+    "VCTK_p307": 76,
+    "VCTK_p308": 77,
+    "VCTK_p310": 78,
+    "VCTK_p311": 79,
+    "VCTK_p312": 80,
+    "VCTK_p313": 81,
+    "VCTK_p314": 82,
+    "VCTK_p316": 83,
+    "VCTK_p317": 84,
+    "VCTK_p318": 85,
+    "VCTK_p323": 86,
+    "VCTK_p326": 87,
+    "VCTK_p329": 88,
+    "VCTK_p330": 89,
+    "VCTK_p333": 90,
+    "VCTK_p334": 91,
+    "VCTK_p335": 92,
+    "VCTK_p336": 93,
+    "VCTK_p339": 94,
+    "VCTK_p340": 95,
+    "VCTK_p341": 96,
+    "VCTK_p343": 97,
+    "VCTK_p345": 98,
+    "VCTK_p347": 99,
+    "VCTK_p351": 100,
+    "VCTK_p360": 101,
+    "VCTK_p361": 102,
+    "VCTK_p362": 103,
+    "VCTK_p363": 104,
+    "VCTK_p364": 105,
+    "VCTK_p374": 106,
+    "VCTK_p376": 107
+}

local_coqui_tts_models/tts_models--en--vctk--vits/config.json

@@ -0,0 +1,504 @@
+{
+    "output_path": null,
+    "logger_uri": null,
+    "run_name": "",
+    "project_name": null,
+    "run_description": "",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 10000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": null,
+    "print_eval": false,
+    "test_delay_epochs": 0,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "precision": "fp16",
+    "epochs": 10000,
+    "batch_size": null,
+    "eval_batch_size": null,
+    "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": "",
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": true,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": null,
+    "num_eval_loader_workers": 0,
+    "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": true,
+    "phonemizer": "espeak",
+    "phoneme_language": "en",
+    "compute_input_seq_cache": false,
+    "text_cleaner": "phoneme_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": "_",
+        "eos": "",
+        "bos": "",
+        "blank": null,
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",
+        "punctuations": ";:,.!?\u00a1\u00bf\u2014\u2026\"\u00ab\u00bb\u201c\u201d ",
+        "phonemes": "\u0251\u0250\u0252\u00e6\u0253\u0299\u03b2\u0254\u0255\u00e7\u0257\u0256\u00f0\u02a4\u0259\u0258\u025a\u025b\u025c\u025d\u025e\u025f\u0284\u0261\u0260\u0262\u029b\u0266\u0267\u0127\u0265\u029c\u0268\u026a\u029d\u026d\u026c\u026b\u026e\u029f\u0271\u026f\u0270\u014b\u0273\u0272\u0274\u00f8\u0275\u0278\u03b8\u0153\u0276\u0298\u0279\u027a\u027e\u027b\u0280\u0281\u027d\u0282\u0283\u0288\u02a7\u0289\u028a\u028b\u2c71\u028c\u0263\u0264\u028d\u03c7\u028e\u028f\u0291\u0290\u0292\u0294\u02a1\u0295\u02a2\u01c0\u01c1\u01c2\u01c3\u02c8\u02cc\u02d0\u02d1\u02bc\u02b4\u02b0\u02b1\u02b2\u02b7\u02e0\u02e4\u02de\u2193\u2191\u2192\u2197\u2198'\u0329'\u1d7b",
+        "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_energy": false,
+    "compute_linear_spec": true,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "",
+            "meta_file_train": "",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "I",
+            "t",
+            " ",
+            "t",
+            "o",
+            "o",
+            "k",
+            " ",
+            "m",
+            "e",
+            " ",
+            "q",
+            "u",
+            "i",
+            "t",
+            "e",
+            " ",
+            "a",
+            " ",
+            "l",
+            "o",
+            "n",
+            "g",
+            " ",
+            "t",
+            "i",
+            "m",
+            "e",
+            " ",
+            "t",
+            "o",
+            " ",
+            "d",
+            "e",
+            "v",
+            "e",
+            "l",
+            "o",
+            "p",
+            " ",
+            "a",
+            " ",
+            "v",
+            "o",
+            "i",
+            "c",
+            "e",
+            ",",
+            " ",
+            "a",
+            "n",
+            "d",
+            " ",
+            "n",
+            "o",
+            "w",
+            " ",
+            "t",
+            "h",
+            "a",
+            "t",
+            " ",
+            "I",
+            " ",
+            "h",
+            "a",
+            "v",
+            "e",
+            " ",
+            "i",
+            "t",
+            " ",
+            "I",
+            "'",
+            "m",
+            " ",
+            "n",
+            "o",
+            "t",
+            " ",
+            "g",
+            "o",
+            "i",
+            "n",
+            "g",
+            " ",
+            "t",
+            "o",
+            " ",
+            "b",
+            "e",
+            " ",
+            "s",
+            "i",
+            "l",
+            "e",
+            "n",
+            "t",
+            "."
+        ],
+        [
+            "B",
+            "e",
+            " ",
+            "a",
+            " ",
+            "v",
+            "o",
+            "i",
+            "c",
+            "e",
+            ",",
+            " ",
+            "n",
+            "o",
+            "t",
+            " ",
+            "a",
+            "n",
+            " ",
+            "e",
+            "c",
+            "h",
+            "o",
+            "."
+        ],
+        [
+            "I",
+            "'",
+            "m",
+            " ",
+            "s",
+            "o",
+            "r",
+            "r",
+            "y",
+            " ",
+            "D",
+            "a",
+            "v",
+            "e",
+            ".",
+            " ",
+            "I",
+            "'",
+            "m",
+            " ",
+            "a",
+            "f",
+            "r",
+            "a",
+            "i",
+            "d",
+            " ",
+            "I",
+            " ",
+            "c",
+            "a",
+            "n",
+            "'",
+            "t",
+            " ",
+            "d",
+            "o",
+            " ",
+            "t",
+            "h",
+            "a",
+            "t",
+            "."
+        ],
+        [
+            "T",
+            "h",
+            "i",
+            "s",
+            " ",
+            "c",
+            "a",
+            "k",
+            "e",
+            " ",
+            "i",
+            "s",
+            " ",
+            "g",
+            "r",
+            "e",
+            "a",
+            "t",
+            ".",
+            " ",
+            "I",
+            "t",
+            "'",
+            "s",
+            " ",
+            "s",
+            "o",
+            " ",
+            "d",
+            "e",
+            "l",
+            "i",
+            "c",
+            "i",
+            "o",
+            "u",
+            "s",
+            " ",
+            "a",
+            "n",
+            "d",
+            " ",
+            "m",
+            "o",
+            "i",
+            "s",
+            "t",
+            "."
+        ],
+        [
+            "P",
+            "r",
+            "i",
+            "o",
+            "r",
+            " ",
+            "t",
+            "o",
+            " ",
+            "N",
+            "o",
+            "v",
+            "e",
+            "m",
+            "b",
+            "e",
+            "r",
+            " ",
+            "2",
+            "2",
+            ",",
+            " ",
+            "1",
+            "9",
+            "6",
+            "3",
+            "."
+        ]
+    ],
+    "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": 179,
+        "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": 0.667,
+        "length_scale": 1.0,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 0.8,
+        "max_inference_len": null,
+        "init_discriminator": false,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": true,
+        "num_speakers": 109,
+        "speakers_file": "/Users/drew/Library/Application Support/tts/tts_models--en--vctk--vits/speaker_ids.json",
+        "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": "/Users/drew/Library/Application Support/tts/tts_models--en--vctk--vits/speaker_ids.json",
+    "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
+}

local_coqui_tts_models/tts_models--en--vctk--vits/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbec6b420abcc677fe4a357994ee68f8f3b6fa84502e7accad42b11a79f6ad0d
+size 159111821

local_coqui_tts_models/tts_models--en--vctk--vits/speaker_ids.json

@@ -0,0 +1,111 @@
+{
+    "ED\n": 0,
+    "p225": 1,
+    "p226": 2,
+    "p227": 3,
+    "p228": 4,
+    "p229": 5,
+    "p230": 6,
+    "p231": 7,
+    "p232": 8,
+    "p233": 9,
+    "p234": 10,
+    "p236": 11,
+    "p237": 12,
+    "p238": 13,
+    "p239": 14,
+    "p240": 15,
+    "p241": 16,
+    "p243": 17,
+    "p244": 18,
+    "p245": 19,
+    "p246": 20,
+    "p247": 21,
+    "p248": 22,
+    "p249": 23,
+    "p250": 24,
+    "p251": 25,
+    "p252": 26,
+    "p253": 27,
+    "p254": 28,
+    "p255": 29,
+    "p256": 30,
+    "p257": 31,
+    "p258": 32,
+    "p259": 33,
+    "p260": 34,
+    "p261": 35,
+    "p262": 36,
+    "p263": 37,
+    "p264": 38,
+    "p265": 39,
+    "p266": 40,
+    "p267": 41,
+    "p268": 42,
+    "p269": 43,
+    "p270": 44,
+    "p271": 45,
+    "p272": 46,
+    "p273": 47,
+    "p274": 48,
+    "p275": 49,
+    "p276": 50,
+    "p277": 51,
+    "p278": 52,
+    "p279": 53,
+    "p280": 54,
+    "p281": 55,
+    "p282": 56,
+    "p283": 57,
+    "p284": 58,
+    "p285": 59,
+    "p286": 60,
+    "p287": 61,
+    "p288": 62,
+    "p292": 63,
+    "p293": 64,
+    "p294": 65,
+    "p295": 66,
+    "p297": 67,
+    "p298": 68,
+    "p299": 69,
+    "p300": 70,
+    "p301": 71,
+    "p302": 72,
+    "p303": 73,
+    "p304": 74,
+    "p305": 75,
+    "p306": 76,
+    "p307": 77,
+    "p308": 78,
+    "p310": 79,
+    "p311": 80,
+    "p312": 81,
+    "p313": 82,
+    "p314": 83,
+    "p316": 84,
+    "p317": 85,
+    "p318": 86,
+    "p323": 87,
+    "p326": 88,
+    "p329": 89,
+    "p330": 90,
+    "p333": 91,
+    "p334": 92,
+    "p335": 93,
+    "p336": 94,
+    "p339": 95,
+    "p340": 96,
+    "p341": 97,
+    "p343": 98,
+    "p345": 99,
+    "p347": 100,
+    "p351": 101,
+    "p360": 102,
+    "p361": 103,
+    "p362": 104,
+    "p363": 105,
+    "p364": 106,
+    "p374": 107,
+    "p376": 108
+}

local_coqui_tts_models/tts_models--multilingual--multi-dataset--xtts_v2/config.json

@@ -0,0 +1,159 @@
+{
+    "output_path": "output",
+    "logger_uri": null,
+    "run_name": "run",
+    "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": null,
+    "save_step": 10000,
+    "save_n_checkpoints": 5,
+    "save_checkpoints": true,
+    "save_all_best": false,
+    "save_best_after": 10000,
+    "target_loss": null,
+    "print_eval": false,
+    "test_delay_epochs": 0,
+    "run_eval": true,
+    "run_eval_steps": null,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": false,
+    "precision": "fp16",
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": 0.0,
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "radam",
+    "optimizer_params": null,
+    "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": "xtts",
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "audio": {
+        "sample_rate": 22050,
+        "output_sample_rate": 24000
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": false,
+    "text_cleaner": null,
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": null,
+    "add_blank": false,
+    "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": false,
+    "precompute_num_workers": 0,
+    "start_by_longest": false,
+    "shuffle": false,
+    "drop_last": false,
+    "datasets": [
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "",
+            "meta_file_train": "",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [],
+    "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": {
+        "gpt_batch_size": 1,
+        "enable_redaction": false,
+        "kv_cache": true,
+        "gpt_checkpoint": null,
+        "clvp_checkpoint": null,
+        "decoder_checkpoint": null,
+        "num_chars": 255,
+        "tokenizer_file": "",
+        "gpt_max_audio_tokens": 605,
+        "gpt_max_text_tokens": 402,
+        "gpt_max_prompt_tokens": 70,
+        "gpt_layers": 30,
+        "gpt_n_model_channels": 1024,
+        "gpt_n_heads": 16,
+        "gpt_number_text_tokens": 6681,
+        "gpt_start_text_token": null,
+        "gpt_stop_text_token": null,
+        "gpt_num_audio_tokens": 1026,
+        "gpt_start_audio_token": 1024,
+        "gpt_stop_audio_token": 1025,
+        "gpt_code_stride_len": 1024,
+        "gpt_use_masking_gt_prompt_approach": true,
+        "gpt_use_perceiver_resampler": true,
+        "input_sample_rate": 22050,
+        "output_sample_rate": 24000,
+        "output_hop_length": 256,
+        "decoder_input_dim": 1024,
+        "d_vector_dim": 512,
+        "cond_d_vector_in_each_upsampling_layer": true,
+        "duration_const": 102400
+    },
+    "model_dir": null,
+    "languages": [
+        "en",
+        "es",
+        "fr",
+        "de",
+        "it",
+        "pt",
+        "pl",
+        "tr",
+        "ru",
+        "nl",
+        "cs",
+        "ar",
+        "zh-cn",
+        "hu",
+        "ko",
+        "ja",
+        "hi"
+    ],
+    "temperature": 0.75,
+    "length_penalty": 1.0,
+    "repetition_penalty": 5.0,
+    "top_k": 50,
+    "top_p": 0.85,
+    "num_gpt_outputs": 1,
+    "gpt_cond_len": 30,
+    "gpt_cond_chunk_len": 4,
+    "max_ref_len": 30,
+    "sound_norm_refs": false
+}

local_coqui_tts_models/tts_models--multilingual--multi-dataset--xtts_v2/hash.md5

@@ -0,0 +1 @@
+10f92b55c512af7a8d39d650547a15a7

local_coqui_tts_models/tts_models--multilingual--multi-dataset--xtts_v2/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ea20001c6a0a841c77e252d8409f6a74fb423e79b3206a0771ba5989776187
+size 1867929118