migrate coqui_community.json: +4

hf_community__anzorq__kbd-vits-tts-female/config.json

@@ -0,0 +1,305 @@
+{
+    "output_path": "/aaa/train_output",
+    "logger_uri": null,
+    "run_name": "vits_kbd_female",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 25,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "wandb",
+    "save_on_interrupt": true,
+    "log_model_step": null,
+    "save_step": 1000,
+    "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,
+    "precision": "fp16",
+    "epochs": 1000,
+    "batch_size": 24,
+    "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,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 2,
+    "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": 24000,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log10",
+        "do_trim_silence": true,
+        "trim_db": 45,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0,
+        "mel_fmax": null,
+        "spec_gain": 20,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 1.0,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": true,
+    "text_cleaner": "basic_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/aaa/train_output/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.Graphemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "abnhikorst\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\u04cf",
+        "punctuations": "!\"(),-.:?\u00ab\u00bb\u2013 ",
+        "phonemes": "",
+        "is_unique": true,
+        "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": 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": "mozilla",
+            "dataset_name": "",
+            "path": "dataset/",
+            "meta_file_train": "metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "\u0443\u043c\u044b\u043f\u04cf\u0430\u0449\u04cf\u044d\u0443 \u043a\u044a\u0435\u0434\u0430\u04cf\u0443\u0438 \u043f\u0441\u043e\u0440\u0438 \u043a\u044a\u044d\u043f\u0449\u04cf\u044d\u043d\u0449"
+        ],
+        [
+            "\u0449\u0438\u0445\u0443 \u0442\u0445\u044c\u044d\u043c\u043f\u044d \u0446\u04cf\u044b\u043a\u04cf\u0443\u0445\u044d\u043c \u0437\u0430\u0433\u044a\u044d\u0441\u044b\u0441\u0443 \u0430\u0431\u044b \u0441\u044d\u043b\u0430\u043c \u0438\u0440\u0430\u0445\u044b\u0436 \u0449\u0445\u044c\u044d\u043a\u04cf\u044d \u043f\u0441\u044b\u0433\u044a\u0443\u044d \u043b\u0430\u043d\u0442\u04cf\u044d\u0445\u044d\u043c \u0437\u0430\u0433\u044a\u044d\u0448\u0430\u0443\u044d \u0449\u0445\u044c\u044d\u0449\u044d \u0445\u0443\u0430\u0449\u04cf\u044b\u0436"
+        ],
+        [
+            "\u0443\u044d\u0440\u0430\u043c\u044b\u0431\u0433\u044a\u0443\u043c \u043a\u044a\u044b\u0442\u0435\u0443\u0432\u0430 \u0446\u04cf\u044b\u0445\u0443 \u04cf\u0443\u0432\u044b\u043c \u044f \u043d\u044d\u0440 \u0442\u043e\u0434\u0438\u0435 \u043a\u0445\u044a\u044d\u043c \u044f\u0445\u044c\u044b\u043c"
+        ],
+        [
+            "\u0434\u044d\u043d\u044d \u0444\u0445\u044c\u0430 \u0441\u0438 \u043b\u044a\u0430\u0433\u044a\u0443\u043d\u044b\u0433\u044a\u044d\u0440"
+        ],
+        [
+            "\u0430 \u043c\u0430\u0445\u0443\u044d\u043c \u0435\u0436\u044c\u0430\u0449 \u0446\u04cf\u044b\u0445\u0443 \u0433\u044a\u0430\u0449\u04cf\u044d\u0440 \u0437\u044b\u0442\u0435\u043a\u04cf\u0443\u044d\u0434\u0430 \u043b\u044a\u0430\u0433\u044a\u0443\u043d\u044b\u0433\u044a\u044d\u0440"
+        ],
+        [
+            "\u0435\u0437\u044b\u0445\u044d\u0440\u0438 \u043b\u044d\u0436\u044c\u044b\u0433\u044a\u044d\u0444\u04cf\u043a\u04cf\u044d \u0437\u0438 \u0446\u04cf\u044d \u043a\u044a\u0430\u04cf\u044d\u0442 \u043a\u044a\u0443\u0430\u0436\u044d \u0449\u04cf\u0430\u043b\u044d\u0433\u044a\u0443\u0430\u043b\u044d\u043c \u044f\u0449\u044b\u0449\u0442"
+        ],
+        [
+            "\u0434\u0430\u0443\u044d \u0445\u044a\u0443\u0430\u043c\u0438 \u0444\u0435\u043d\u044d \u043a\u044a\u0443\u0430\u0436\u044d\u043c \u044f\u0444\u04cf\u044d\u04cf\u0435\u044f\u043a\u044a\u044b\u043c \u043a\u044a\u044d\u0437\u044b\u0448\u0430 \u0443\u043d\u0430\u0433\u044a\u0443\u044d\u0440\u0442\u0438 \u2014 \u044f \u043d\u044d-\u044f \u043f\u0441\u044d\u0442"
+        ],
+        [
+            "\u0445\u044a\u044b\u0434\u0436\u044d\u0431\u0437\u0440\u0438 \u0449\u0442\u044d\u0436\u0440\u0438 \u0435\u043a\u044a\u0443\u0436\u0430\u0443\u044d \u0436\u0430\u04cf\u044d \u0430\u0443\u044d \u0445\u0443\u0445\u044d\u0447\u044b\u0436\u0430\u043a\u044a\u044b\u043c"
+        ],
+        [
+            "\u0430\u0443\u044d \u0430\u0431\u044b\u0438 \u043a\u0443\u044d\u0434 \u0438\u0445\u044c\u0430\u043a\u044a\u044b\u043c"
+        ]
+    ],
+    "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": 60,
+        "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,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 1.0,
+        "max_inference_len": null,
+        "init_discriminator": true,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": false,
+        "num_speakers": 0,
+        "speakers_file": null,
+        "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": 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": 0
+}

hf_community__anzorq__kbd-vits-tts-female/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed9459c5c0b478269742731266173f5d27a8ea450cfa4c949170fff7684873e
+size 138843405

hf_community__anzorq__kbd-vits-tts-male/config.json

@@ -0,0 +1,297 @@
+{
+    "output_path": "/kaggle/working/train_output",
+    "logger_uri": null,
+    "run_name": "vits_kbd_male",
+    "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": 1000,
+    "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,
+    "precision": "fp16",
+    "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,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 0,
+    "num_eval_loader_workers": 2,
+    "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": 24000,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log10",
+        "do_trim_silence": true,
+        "trim_db": 45,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0,
+        "mel_fmax": null,
+        "spec_gain": 20,
+        "do_amp_to_db_linear": true,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 1.0,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": true,
+    "text_cleaner": "basic_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/kaggle/working/train_output/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.Graphemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "abhikorst\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\u044f\u04cf",
+        "punctuations": "!\"(),-.:?\u00ab\u00bb\u2013 ",
+        "phonemes": "",
+        "is_unique": true,
+        "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": 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": "mozilla",
+            "dataset_name": "",
+            "path": "/kaggle/input/circassian-kbd-tts-male",
+            "meta_file_train": "metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "\u0423\u0438 \u043f\u0449\u044b\u0445\u044c\u044d\u0449\u0445\u044c\u044d \u0444\u04cf\u044b\u0443\u044d"
+        ],
+        [
+            "\u0411\u0437\u044d \u043a\u044a\u044d\u0441 \u0435\u0437\u044b\u043c \u0438 \u0445\u0430\u0431\u0437\u044d \u0438\u04cf\u044d\u0436\u0449."
+        ],
+        [
+            "\u0411\u0433\u044a\u0430\u0449\u0445\u044a\u0443\u044d \u0449\u044b\u043b\u044a\u0445\u0443\u0445\u044d\u0440"
+        ],
+        [
+            "\u0425\u044c\u044d\u0442\u0438\u044f\u043a\u04cf\u0443\u044d\u0445\u044d\u043c \u0437\u044d\u04cf\u044d\u043f\u0430\u0445\u0440\u044d \u0437\u044d\u0445\u0443\u0430\u0434\u0437\u044b\u0436\u0443 \u0430\u0434\u044b\u0433\u044d\u0431\u0437\u044d\u0440 \u044f\u0433\u044a\u044d\u0434\u0436\u044d\u0433\u0443\u0440\u0442"
+        ],
+        [
+            "\u0423\u0437\u044d\u0440\u044b\u0449\u04cf\u044d\u043c\u044d \u0443\u0437\u044d\u0434\u043e\u0449\u04cf\u044d, \u0443\u0437\u044d\u0434\u044d\u0449\u04cf\u044d\u043c\u044d \u0437\u044b \u0443\u043e\u0445\u044a\u0443!"
+        ],
+        [
+            "\u0414\u0438 \u0431\u0437\u044b\u043b\u044a\u0445\u0443\u0433\u044a\u044d\u0445\u044d\u0440 \u043a\u0443\u044d\u0434\u0440\u044d \u043c\u044d\u0443\u043f\u0449\u04cf\u044d: \u00ab\u0430\u0434\u044b\u0433\u044d \u0446\u04cf\u044b\u0445\u0443\u0431\u0437\u044b\u043c \"\u0444\u04cf\u044d\u0445\u044a\u0443\u0441 \u0430\u043f\u0449\u0438\u0439\" \u0436\u0438\u04cf\u044d \u0445\u044a\u0443\u043d\u0443?\u00bb \u0436\u0430\u0440\u0438"
+        ]
+    ],
+    "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": 58,
+        "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,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 1.0,
+        "max_inference_len": null,
+        "init_discriminator": true,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": false,
+        "num_speakers": 0,
+        "speakers_file": null,
+        "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": 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": 0,
+    "github_branch": "inside_docker"
+}

hf_community__anzorq__kbd-vits-tts-male/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1973e65e7f55826ab491119b77a6ed7c3edc573e4e3759363a2d4f2c7ce2f5
+size 138843405

hf_community__denZLS__luxembourgish-male-vits-tts/config.json

@@ -0,0 +1,260 @@
+{
+    "output_path": "D:\\NEWTTS\\TTS\\dataset\\",
+    "logger_uri": null,
+    "run_name": "lod-male-vits-lb",
+    "project_name": null,
+    "run_description": "\ud83d\udc38Coqui trainer run.",
+    "print_step": 30,
+    "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": 0,
+    "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": true,
+    "precision": "fp16",
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 16,
+    "grad_clip": [
+        1000.0,
+        1000.0
+    ],
+    "scheduler_after_epoch": true,
+    "lr": 0.001,
+    "optimizer": "AdamW",
+    "optimizer_params": {
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "weight_decay": 0.01
+    },
+    "lr_scheduler": null,
+    "lr_scheduler_params": {},
+    "use_grad_scaler": false,
+    "allow_tf32": false,
+    "cudnn_enable": true,
+    "cudnn_deterministic": false,
+    "cudnn_benchmark": false,
+    "training_seed": 54321,
+    "model": "vits",
+    "num_loader_workers": 0,
+    "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": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": true,
+    "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": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "abcdefghijklmnopqrstuvwxyz\u00b5\u00df\u00e0\u00e1\u00e2\u00e4\u00e5\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f1\u00f2\u00f3\u00f4\u00f6\u00f9\u00fa\u00fb\u00fc\u0105\u0107\u0119\u0142\u0144\u0153\u015b\u015f\u017a\u017c\u0192\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f\u0451\u0454\u0456\u0457\u0491\u04e7\u00ab\u00b0\u00b1\u00b5\u00bb$%&\u2018\u2019\u201a\u201c`\u201d\u201e\u00f5\u00e3\u0131",
+        "punctuations": "!\u00a1'(),-.:;\u00bf? ",
+        "phonemes": null,
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 5,
+    "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": "luxembourgish",
+            "dataset_name": "",
+            "path": "D:\\NEWTTS\\TTS\\dataset\\lod-male-vits-lb/",
+            "meta_file_train": "metadata.csv",
+            "ignored_speakers": null,
+            "language": "",
+            "phonemizer": "",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        "an der z\u00e4it hunn sech den nordwand an d\u2019sonn gestridden, wie vun hinnen zwee wuel m\u00e9i staark wier,",
+        "w\u00e9i e wanderer, deen an ee waarme mantel agepak war, iwwert de wee koum.",
+        "si goufen sech eens, datt deej\u00e9inege fir dee st\u00e4erkste g\u00eblle sollt, deen de wanderer forc\u00e9iere g\u00e9if, s\u00e4i mantel auszedoen.",
+        "dunn huet d\u2019sonn d\u2019loft mat hire fr\u00ebndleche strale gewiermt, a schonn no kuerzer z\u00e4it huet de wanderer s\u00e4i mantel ausgedoen.",
+        "do huet den rdwand missen zouginn, datt d\u2019sonn vun hinnen zwee dee st\u00e4erkste wier."
+    ],
+    "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": 134,
+        "out_channels": 513,
+        "spec_segment_size": 32,
+        "hidden_channels": 192,
+        "hidden_channels_ffn_text_encoder": 768,
+        "num_heads_text_encoder": 2,
+        "num_layers_text_encoder": 6,
+        "kernel_size_text_encoder": 3,
+        "dropout_p_text_encoder": 0.1,
+        "dropout_p_duration_predictor": 0.5,
+        "kernel_size_posterior_encoder": 5,
+        "dilation_rate_posterior_encoder": 1,
+        "num_layers_posterior_encoder": 16,
+        "kernel_size_flow": 5,
+        "dilation_rate_flow": 1,
+        "num_layers_flow": 4,
+        "resblock_type_decoder": "1",
+        "resblock_kernel_sizes_decoder": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes_decoder": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates_decoder": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel_decoder": 512,
+        "upsample_kernel_sizes_decoder": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "periods_multi_period_discriminator": [
+            2,
+            3,
+            5,
+            7,
+            11
+        ],
+        "use_sdp": 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": false,
+        "num_speakers": 0,
+        "speakers_file": null,
+        "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": 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": 0,
+    "restore_path": "D:/NEWTTS/TTS/dataset/lod-male-vits-lb-June-28-2024_03+19PM-dbf1a08a/checkpoint_50000.pth",
+    "github_branch": "* dev"
+}

hf_community__denZLS__luxembourgish-male-vits-tts/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38169da6ee4b80b508cae1ed8bec51e21678bf47fedf995064819013dc808997
+size 132588146

hf_community__projecte-aina__tts-ca-coqui-vits-multispeaker/config.json

@@ -0,0 +1,268 @@
+{
+    "output_path": "/mnt/netapp1/Proxecto_NOS/bsc/tts/training_outputs/0.14.3",
+    "logger_uri": null,
+    "run_name": "finetune_newdata_no_cv_denoised_from_1M_model_1e-4",
+    "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": 1000,
+    "save_step": 1000,
+    "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,
+    "precision": "fp16",
+    "epochs": 1000,
+    "batch_size": 64,
+    "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": 16000,
+        "win_length": 1024,
+        "hop_length": 256,
+        "num_mels": 80,
+        "mel_fmin": 60,
+        "mel_fmax": null
+    },
+    "use_phonemes": true,
+    "phonemizer": "espeak",
+    "phoneme_language": "ca",
+    "compute_input_seq_cache": false,
+    "text_cleaner": "basic_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": "/mnt/netapp1/Proxecto_NOS/bsc/tts/training_outputs/catalan_phoneme_cache_21_09_2023",
+    "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": 4000,
+    "max_audio_len": 200000,
+    "min_text_len": 3,
+    "max_text_len": 115,
+    "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_denoised",
+            "path": "/mnt/netapp1/Proxecto_NOS/bsc/speech_data/fest_google_vctk_denoised_16khz",
+            "meta_file_train": "",
+            "ignored_speakers": null,
+            "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.",
+            "caf_09598"
+        ],
+        [
+            "Preguntin-se si aix\u00f2 era necessari.",
+            "ona"
+        ],
+        [
+            "La suposada ocultaci\u00f3 dels informes que advertien de risc s\u00edsmic.",
+            "pau"
+        ],
+        [
+            "\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": 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": 0.8333333333333334,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 0.8,
+        "max_inference_len": null,
+        "init_discriminator": true,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": true,
+        "num_speakers": 840,
+        "speakers_file": "/home/jgiraldo/projects/coqui-TTS/coqui-ai-TTS/vits_ca/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": 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": 0.85,
+        "last_epoch": -1
+    },
+    "lr_scheduler_disc": "ExponentialLR",
+    "lr_scheduler_disc_params": {
+        "gamma": 0.85,
+        "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": 840,
+    "use_speaker_embedding": false,
+    "speakers_file": "speakers.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
+}

hf_community__projecte-aina__tts-ca-coqui-vits-multispeaker/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a226b188fe5767eff98c20bdd36cd1f3d69efd6cda00268ccfa74ce28856f1
+size 139101671