Upload 16 files

models/tts_models--en--ljspeech--tacotron2-DDC/config.json

@@ -0,0 +1,173 @@
+{
+    "model": "Tacotron2",
+    "run_name": "ljspeech-ddc",
+    "run_description": "Tacotron2 with DDC. It uses only characters and the 2nd decoder is prunned for efficient inference.",
+    // AUDIO PARAMETERS
+    "audio":{
+        // stft parameters
+        "fft_size": 1024,         // number of stft frequency levels. Size of the linear spectogram frame.
+        "win_length": 1024,      // stft window length in ms.
+        "hop_length": 256,       // stft window hop-lengh in ms.
+        "frame_length_ms": null, // stft window length in ms.If null, 'win_length' is used.
+        "frame_shift_ms": null,  // stft window hop-lengh in ms. If null, 'hop_length' is used.
+
+        // Audio processing parameters
+        "sample_rate": 22050,   // DATASET-RELATED: wav sample-rate.
+        "preemphasis": 0.0,     // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
+        "ref_level_db": 20,     // reference level db, theoretically 20db is the sound of air.
+        "log_func": "np.log",
+
+        // Silence trimming
+        "do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (true), TWEB (false), Nancy (true)
+        "trim_db": 60,          // threshold for timming silence. Set this according to your dataset.
+
+        // Griffin-Lim
+        "power": 1.5,           // value to sharpen wav signals after GL algorithm.
+        "griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
+
+        // MelSpectrogram parameters
+        "num_mels": 80,         // size of the mel spec frame.
+        "mel_fmin": 0.0,        // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
+        "mel_fmax": 8000.0,     // maximum freq level for mel-spec. Tune for dataset!!
+        "spec_gain": 1,
+
+        // Normalization parameters
+        "signal_norm": false,    // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params.
+        "min_level_db": -100,   // lower bound for normalization
+        "symmetric_norm": true, // move normalization to range [-1, 1]
+        "max_norm": 4.0,        // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
+        "clip_norm": true,      // clip normalized values into the range.
+        "stats_path": null    // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
+    },
+
+    // VOCABULARY PARAMETERS
+    "characters":{
+        "pad": "",
+        "eos": "",
+        "bos": "",
+        "characters": "_-!'(),.:;? ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",
+        "punctuations":"",
+        "phonemes":""
+    },
+
+    // DISTRIBUTED TRAINING
+    "distributed":{
+        "backend": "nccl",
+        "url": "tcp:\/\/localhost:54321"
+    },
+
+    "reinit_layers": [],    // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers.
+
+    // TRAINING
+    "batch_size": 32,       // Batch size for training. Lower values than 32 might cause hard to learn attention. It is overwritten by 'gradual_training'.
+    "eval_batch_size":16,
+    "r": 1,                 // Number of decoder frames to predict per iteration. Set the initial values if gradual training is enabled.
+    "gradual_training": null, //set gradual training steps [first_step, r, batch_size]. If it is null, gradual training is disabled. For Tacotron, you might need to reduce the 'batch_size' as you proceeed.
+    "mixed_precision": false,     // level of optimization with NVIDIA's apex feature for automatic mixed FP16/FP32 precision (AMP), NOTE: currently only O1 is supported, and use "O1" to activate.
+
+    // LOSS SETTINGS
+    "loss_masking": true,       // enable / disable loss masking against the sequence padding.
+    "decoder_loss_alpha": 1,  // original decoder loss weight. If > 0, it is enabled
+    "postnet_loss_alpha": 1, // original postnet loss weight. If > 0, it is enabled
+    "postnet_diff_spec_alpha": 0,     // differential spectral loss weight. If > 0, it is enabled
+    "decoder_diff_spec_alpha": 0,     // differential spectral loss weight. If > 0, it is enabled
+    "decoder_ssim_alpha": 0,     // decoder ssim loss weight. If > 0, it is enabled
+    "postnet_ssim_alpha": 0,     // postnet ssim loss weight. If > 0, it is enabled
+    "ga_alpha": 5.0,           // weight for guided attention loss. If > 0, guided attention is enabled.
+    "stopnet_pos_weight": 15.0, // pos class weight for stopnet loss since there are way more negative samples than positive samples.
+
+
+    // VALIDATION
+    "run_eval": true,
+    "test_delay_epochs": 10,  //Until attention is aligned, testing only wastes computation time.
+    "test_sentences_file": null,  // set a file to load sentences to be used for testing. If it is null then we use default english sentences.
+
+    // OPTIMIZER
+    "noam_schedule": false,        // use noam warmup and lr schedule.
+    "grad_clip": 1.0,              // upper limit for gradients for clipping.
+    "epochs": 1000,                // total number of epochs to train.
+    "lr": 0.00001,                  // Initial learning rate. If Noam decay is active, maximum learning rate.
+    "wd": 0.000001,                // Weight decay weight.
+    "warmup_steps": 4000,          // Noam decay steps to increase the learning rate from 0 to "lr"
+    "seq_len_norm": false,         // Normalize eash sample loss with its length to alleviate imbalanced datasets. Use it if your dataset is small or has skewed distribution of sequence lengths.
+
+    // TACOTRON PRENET
+    "memory_size": -1,             // ONLY TACOTRON - size of the memory queue used fro storing last decoder predictions for auto-regression. If < 0, memory queue is disabled and decoder only uses the last prediction frame.
+    "prenet_type": "original",     // "original" or "bn".
+    "prenet_dropout": true,       // enable/disable dropout at prenet.
+    "prenet_dropout_at_inference": true,
+
+    // TACOTRON ATTENTION
+    "attention_type": "original",  // 'original' , 'graves', 'dynamic_convolution'
+    "attention_heads": 4,          // number of attention heads (only for 'graves')
+    "attention_norm": "softmax",   // softmax or sigmoid.
+    "windowing": false,            // Enables attention windowing. Used only in eval mode.
+    "use_forward_attn": false,     // if it uses forward attention. In general, it aligns faster.
+    "forward_attn_mask": false,    // Additional masking forcing monotonicity only in eval mode.
+    "transition_agent": false,     // enable/disable transition agent of forward attention.
+    "location_attn": true,         // enable_disable location sensitive attention. It is enabled for TACOTRON by default.
+    "bidirectional_decoder": false,  // use https://arxiv.org/abs/1907.09006. Use it, if attention does not work well with your dataset.
+    "double_decoder_consistency": false,  // use DDC explained here https://erogol.com/solving-attention-problems-of-tts-models-with-double-decoder-consistency-draft/
+    "ddc_r": 7,                           // reduction rate for coarse decoder.
+
+    // STOPNET
+    "stopnet": true,               // Train stopnet predicting the end of synthesis.
+    "separate_stopnet": false,      // Train stopnet seperately if 'stopnet==true'. It prevents stopnet loss to influence the rest of the model. It causes a better model, but it trains SLOWER.
+
+    // TENSORBOARD and LOGGING
+    "print_step": 25,       // Number of steps to log training on console.
+    "tb_plot_step": 100,    // Number of steps to plot TB training figures.
+    "print_eval": false,     // If True, it prints intermediate loss values in evalulation.
+    "save_step": 1000,      // Number of training steps expected to save traninpg stats and checkpoints.
+    "checkpoint": true,     // If true, it saves checkpoints per "save_step"
+    "keep_all_best": false,  // If true, keeps all best_models after keep_after steps
+    "keep_after": 10000,    // Global step after which to keep best models if keep_all_best is true
+    "tb_model_param_stats": false,     // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.
+
+    // DATA LOADING
+    "text_cleaner": "english_cleaners",
+    "enable_eos_bos_chars": false, // enable/disable beginning of sentence and end of sentence chars.
+    "num_loader_workers": 4,        // number of training data loader processes. Don't set it too big. 4-8 are good values.
+    "num_val_loader_workers": 4,    // number of evaluation data loader processes.
+    "batch_group_size": 4,  //Number of batches to shuffle after bucketing.
+    "min_seq_len": 6,       // DATASET-RELATED: minimum text length to use in training
+    "max_seq_len": 153,     // DATASET-RELATED: maximum text length
+    "compute_input_seq_cache": false,  // if true, text sequences are computed before starting training. If phonemes are enabled, they are also computed at this stage.
+    "use_noise_augment": false,
+
+    // PATHS
+    "output_path": "/content/gdrive/MyDrive/Trainings/LJSpeech/",
+
+    // PHONEMES
+    "phoneme_cache_path": "/home/erogol/Models/phoneme_cache/",  // phoneme computation is slow, therefore, it caches results in the given folder.
+    "use_phonemes": false,           // use phonemes instead of raw characters. It is suggested for better pronounciation.
+    "phoneme_language": "en-us",     // depending on your target language, pick one from  https://github.com/bootphon/phonemizer#languages
+
+    // MULTI-SPEAKER and GST
+    "use_speaker_embedding": false,      // use speaker embedding to enable multi-speaker learning.
+    "use_gst": false,       			    // use global style tokens
+    "use_external_speaker_embedding_file": false, // if true, forces the model to use external embedding per sample instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558
+    "external_speaker_embedding_file": "../../speakers-vctk-en.json", // if not null and use_external_speaker_embedding_file is true, it is used to load a specific embedding file and thus uses these embeddings instead of nn.embeddings, that is, it supports external embeddings such as those used at: https://arxiv.org/abs /1806.04558
+    "gst":	{			                // gst parameter if gst is enabled
+        "gst_style_input": null,        // Condition the style input either on a
+                                        // -> wave file [path to wave] or
+                                        // -> dictionary using the style tokens {'token1': 'value', 'token2': 'value'} example {"0": 0.15, "1": 0.15, "5": -0.15}
+                                        // with the dictionary being len(dict) <= len(gst_style_tokens).
+        "gst_embedding_dim": 512,
+        "gst_num_heads": 4,
+        "gst_style_tokens": 10,
+        "gst_use_speaker_embedding": false
+	},
+
+    // DATASETS
+    "datasets":   // List of datasets. They all merged and they get different speaker_ids.
+        [
+            {
+                "name": "ljspeech",
+                "path": "/content/LJSpeech-1.1/",
+                "meta_file_train": "metadata.csv", // for vtck if list, ignore speakers id in list for train, its useful for test cloning with new speakers
+                "meta_file_val": null
+            }
+        ]
+}
+

models/tts_models--en--ljspeech--tacotron2-DDC/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d121d9068896e5e1427ffc6dd069f1785baf1ed0d63d5a3d6855c47aed340ad
+size 112672337

models/tts_models--multilingual--multi-dataset--your_tts/config.json

@@ -0,0 +1,401 @@
+{
+    "output_path": "../checkpoints/VITS-multilingual/VITS_fixes/new/new-SE/use_noise_aument_false/xlarge-ZS-PT-VCTK/pt-en+LibriTTS-fr/speaker_encoder_as_loss_9_alpha/mixed-p-false-bug-SDP-fixed/",
+    "logger_uri": null,
+    "run_name": "vits_tts-portuguese",
+    "project_name": null,
+    "run_description": "",
+    "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": 52,
+    "eval_batch_size": 52,
+    "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": null,
+    "use_grad_scaler": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": true,
+    "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": "pt-br",
+    "compute_input_seq_cache": false,
+    "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": "_",
+        "eos": "&",
+        "bos": "*",
+        "blank": null,
+        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\u00af\u00b7\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f9\u00fa\u00fb\u00fc\u00ff\u0101\u0105\u0107\u0113\u0119\u011b\u012b\u0131\u0142\u0144\u014d\u0151\u0153\u015b\u016b\u0171\u017a\u017c\u01ce\u01d0\u01d2\u01d4\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\u2013!'(),-.:;? ",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": "",
+        "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": "../../datasets/VCTK-Corpus-removed-silence_16Khz/",
+            "meta_file_train": null,
+            "ignored_speakers": null,
+            "language": "en",
+            "phonemizer": "",
+            "meta_file_val": null,
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "../../datasets/LibriTTS/LibriTTS/dataset-preprocessed-clean-100-and-360/dataset-22k/",
+            "meta_file_train": "metadata_all.csv",
+            "ignored_speakers": null,
+            "language": "en",
+            "phonemizer": "",
+            "meta_file_val": "dev-clean_500.csv",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "../../datasets/TTS-Portuguese-Corpus_16khz/",
+            "meta_file_train": "train_TTS-Portuguese_Corpus_metadata.csv",
+            "ignored_speakers": null,
+            "language": "pt-br",
+            "phonemizer": "",
+            "meta_file_val": "eval_TTS-Portuguese_Corpus_metadata.csv",
+            "meta_file_attn_mask": ""
+        },
+        {
+            "formatter": "",
+            "dataset_name": "",
+            "path": "../../datasets/M-AILABS/fr_FR",
+            "meta_file_train": "",
+            "ignored_speakers": null,
+            "language": "fr-fr",
+            "phonemizer": "",
+            "meta_file_val": null,
+            "meta_file_attn_mask": null
+        }
+    ],
+    "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.",
+            "VCTK_p225",
+            null,
+            "en"
+        ],
+        [
+            "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
+            "ED",
+            null,
+            "en"
+        ],
+        [
+            "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
+            "bernard",
+            null,
+            "en"
+        ],
+        [
+            "This cake is great. It's so delicious and moist.",
+            "VCTK_p234",
+            null,
+            "en"
+        ],
+        [
+            "This cake is great. It's so delicious and moist.",
+            "ED",
+            null,
+            "en"
+        ],
+        [
+            "This cake is great. It's so delicious and moist.",
+            "ezwa",
+            null,
+            "en"
+        ],
+        [
+            "Hoje \u00e9 fundamental encontrar a raz\u00e3o da exist\u00eancia humana.",
+            "ED",
+            null,
+            "pt-br"
+        ],
+        [
+            "Hoje \u00e9 fundamental encontrar a raz\u00e3o da exist\u00eancia humana.",
+            "VCTK_p238",
+            null,
+            "pt-br"
+        ],
+        [
+            "Hoje \u00e9 fundamental encontrar a raz\u00e3o da exist\u00eancia humana.",
+            "gilles_g_le_blanc",
+            null,
+            "pt-br"
+        ],
+        [
+            "Em muitas cidades a popula\u00e7\u00e3o est\u00e1 diminuindo.",
+            "ED",
+            null,
+            "pt-br"
+        ],
+        [
+            "Em muitas cidades a popula\u00e7\u00e3o est\u00e1 diminuindo.",
+            "VCTK_p245",
+            null,
+            "pt-br"
+        ],
+        [
+            "Em muitas cidades a popula\u00e7\u00e3o est\u00e1 diminuindo.",
+            "nadine_eckert_boulet",
+            null,
+            "pt-br"
+        ],
+        [
+            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
+            "VCTK_p245",
+            null,
+            "fr-fr"
+        ],
+        [
+            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
+            "ED",
+            null,
+            "fr-fr"
+        ],
+        [
+            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
+            "ezwa",
+            null,
+            "fr-fr"
+        ],
+        [
+            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
+            "bernard",
+            null,
+            "fr-fr"
+        ],
+        [
+            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
+            "gilles_g_le_blanc",
+            null,
+            "fr-fr"
+        ],
+        [
+            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
+            "nadine_eckert_boulet",
+            null,
+            "fr-fr"
+        ],
+        [
+            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
+            "zeckou",
+            null,
+            "fr-fr"
+        ]
+    ],
+    "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": 165,
+        "out_channels": 513,
+        "spec_segment_size": 62,
+        "hidden_channels": 192,
+        "hidden_channels_ffn_text_encoder": 768,
+        "num_heads_text_encoder": 2,
+        "num_layers_text_encoder": 10,
+        "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": 0.3,
+        "length_scale": 1.5,
+        "noise_scale_dp": 0.6,
+        "inference_noise_scale_dp": 0.3,
+        "max_inference_len": null,
+        "init_discriminator": true,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": false,
+        "num_speakers": 1244,
+        "speakers_file": null,
+        "d_vector_file": [
+            "C:/Users/Torch/AppData/Local\\tts\\tts_models--multilingual--multi-dataset--your_tts\\speakers.json"
+        ],
+        "speaker_embedding_channels": 512,
+        "use_d_vector_file": true,
+        "d_vector_dim": 512,
+        "detach_dp_input": true,
+        "use_language_embedding": true,
+        "embedded_language_dim": 4,
+        "num_languages": 3,
+        "language_ids_file": null,
+        "use_speaker_encoder_as_loss": true,
+        "speaker_encoder_config_path": "C:/Users/Torch/AppData/Local\\tts\\tts_models--multilingual--multi-dataset--your_tts\\config_se.json",
+        "speaker_encoder_model_path": "C:/Users/Torch/AppData/Local\\tts\\tts_models--multilingual--multi-dataset--your_tts\\model_se.pth",
+        "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": null,
+    "speaker_embedding_channels": 256,
+    "language_ids_file": null,
+    "use_language_embedding": false,
+    "use_d_vector_file": true,
+    "d_vector_file": [
+        "C:/Users/Torch/AppData/Local\\tts\\tts_models--multilingual--multi-dataset--your_tts\\speakers.json"
+    ],
+    "d_vector_dim": 512
+}

models/tts_models--multilingual--multi-dataset--your_tts/config_se.json

@@ -0,0 +1,121 @@
+{
+    "model": "speaker_encoder",
+    "run_name": "speaker_encoder",
+    "run_description": "resnet speaker encoder trained with commonvoice all languages dev and train, Voxceleb 1 dev and Voxceleb 2 dev",
+    "epochs": 100000,
+    "batch_size": null,
+    "eval_batch_size": null,
+    "mixed_precision": false,
+    "run_eval": true,
+    "test_delay_epochs": 0,
+    "print_eval": false,
+    "print_step": 50,
+    "tb_plot_step": 100,
+    "tb_model_param_stats": false,
+    "save_step": 1000,
+    "checkpoint": true,
+    "keep_all_best": false,
+    "keep_after": 10000,
+    "num_loader_workers": 8,
+    "num_val_loader_workers": 0,
+    "use_noise_augment": false,
+    "output_path": "../checkpoints/speaker_encoder/language_balanced/normalized/angleproto-4-samples-by-speakers/",
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "audio": {
+        "fft_size": 512,
+        "win_length": 400,
+        "hop_length": 160,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 16000,
+        "resample": false,
+        "preemphasis": 0.97,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "do_trim_silence": false,
+        "trim_db": 60,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 64,
+        "mel_fmin": 0.0,
+        "mel_fmax": 8000.0,
+        "spec_gain": 20,
+        "signal_norm": false,
+        "min_level_db": -100,
+        "symmetric_norm": false,
+        "max_norm": 4.0,
+        "clip_norm": false,
+        "stats_path": null,
+        "do_rms_norm": true,
+        "db_level": -27.0
+    },
+    "datasets": [
+        {
+            "name": "voxceleb2",
+            "path": "/workspace/scratch/ecasanova/datasets/VoxCeleb/vox2_dev_aac/",
+            "meta_file_train": null,
+            "ununsed_speakers": null,
+            "meta_file_val": null,
+            "meta_file_attn_mask": "",
+            "language": "voxceleb"
+        }
+    ],
+    "model_params": {
+        "model_name": "resnet",
+        "input_dim": 64,
+        "use_torch_spec": true,
+        "log_input": true,
+        "proj_dim": 512
+    },
+    "audio_augmentation": {
+        "p": 0.5,
+        "rir": {
+            "rir_path": "/workspace/store/ecasanova/ComParE/RIRS_NOISES/simulated_rirs/",
+            "conv_mode": "full"
+        },
+        "additive": {
+            "sounds_path": "/workspace/store/ecasanova/ComParE/musan/",
+            "speech": {
+                "min_snr_in_db": 13,
+                "max_snr_in_db": 20,
+                "min_num_noises": 1,
+                "max_num_noises": 1
+            },
+            "noise": {
+                "min_snr_in_db": 0,
+                "max_snr_in_db": 15,
+                "min_num_noises": 1,
+                "max_num_noises": 1
+            },
+            "music": {
+                "min_snr_in_db": 5,
+                "max_snr_in_db": 15,
+                "min_num_noises": 1,
+                "max_num_noises": 1
+            }
+        },
+        "gaussian": {
+            "p": 0.0,
+            "min_amplitude": 0.0,
+            "max_amplitude": 1e-05
+        }
+    },
+    "storage": {
+        "sample_from_storage_p": 0.5,
+        "storage_size": 40
+    },
+    "max_train_step": 1000000,
+    "loss": "angleproto",
+    "grad_clip": 3.0,
+    "lr": 0.0001,
+    "lr_decay": false,
+    "warmup_steps": 4000,
+    "wd": 1e-06,
+    "steps_plot_stats": 100,
+    "num_speakers_in_batch": 100,
+    "num_utters_per_speaker": 4,
+    "skip_speakers": true,
+    "voice_len": 2.0
+}

models/tts_models--multilingual--multi-dataset--your_tts/language_ids.json

@@ -0,0 +1,5 @@
+{
+    "en": 0,
+    "fr-fr": 1,
+    "pt-br": 2
+}

models/tts_models--multilingual--multi-dataset--your_tts/model_file.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017bfd8907c80bb5857d65d0223f0e4e4b9d699ef52e2a853d9cc7eb7e308cf0
+size 379957289

models/tts_models--multilingual--multi-dataset--your_tts/model_se.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f96efb20cbeeefd81fd8336d7f0155bf8902f82f9474e58ccb19d9e12345172
+size 44610930

models/voice_conversion_models--multilingual--vctk--freevc24/._model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa468ed77a9726751b4d321242e069c77dbcd8ecb2e30a212dc0f38f69b852a
+size 230

models/voice_conversion_models--multilingual--vctk--freevc24/__MACOSX/voice_conversion_models--multilingual--vctk--freevc24/._model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa468ed77a9726751b4d321242e069c77dbcd8ecb2e30a212dc0f38f69b852a
+size 230

models/voice_conversion_models--multilingual--vctk--freevc24/config.json

@@ -0,0 +1,204 @@
+{
+    "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",
+    "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,
+    "epochs": 1000,
+    "batch_size": 32,
+    "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": "freevc",
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 0,
+    "use_noise_augment": false,
+    "audio": {
+        "max_wav_value": 32768.0,
+        "input_sample_rate": 16000,
+        "output_sample_rate": 24000,
+        "filter_length": 1280,
+        "hop_length": 320,
+        "win_length": 1280,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null
+    },
+    "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": [
+        [
+            "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,
+    "model_args": {
+        "spec_channels": 641,
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            10,
+            6,
+            4,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false,
+        "gin_channels": 256,
+        "ssl_dim": 1024,
+        "use_spk": true,
+        "num_spks": 0,
+        "segment_size": 8960
+    },
+    "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,
+    "add_blank": true,
+    "num_speakers": 0,
+    "use_speaker_embedding": false,
+    "speakers_file": null,
+    "speaker_embedding_channels": 256,
+    "language_ids_file": null,
+    "use_language_embedding": false,
+    "use_d_vector_file": false,
+    "d_vector_file": null,
+    "d_vector_dim": null
+}

models/voice_conversion_models--multilingual--vctk--freevc24/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d4ce44e7c803d675be1984b174e0f7bf05ce937419f19a818877e83f197007
+size 1425242419