Upload folder using huggingface_hub

best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535a0d521d981183d98cb66eb3d127a8428655dd38e472fd8dfe9b22884a56a2
+size 997753925

best_model_56351.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535a0d521d981183d98cb66eb3d127a8428655dd38e472fd8dfe9b22884a56a2
+size 997753925

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
+}

train_vits.py

@@ -0,0 +1,108 @@
+import os
+
+from trainer import Trainer, TrainerArgs
+
+from TTS.tts.configs.shared_configs import BaseDatasetConfig , CharactersConfig
+from TTS.config.shared_configs import BaseAudioConfig
+from TTS.tts.configs.vits_config import VitsConfig
+from TTS.tts.datasets import load_tts_samples
+from TTS.tts.models.vits import Vits, VitsAudioConfig
+from TTS.tts.utils.text.tokenizer import TTSTokenizer
+from TTS.utils.audio import AudioProcessor
+from TTS.utils.downloaders import download_thorsten_de
+
+output_path = os.path.dirname(os.path.abspath(__file__))
+dataset_config = BaseDatasetConfig(
+    formatter="mozilla", meta_file_train="metadata.csv", path="dataset/"
+)
+
+
+
+audio_config = BaseAudioConfig(
+    sample_rate=24000,
+    do_trim_silence=True,
+    resample=False,
+    mel_fmin=0,
+    mel_fmax=None
+)
+character_config=CharactersConfig(
+  characters='abnhikorstабвгдежзийклмнопрстуфхцчшщъыьэюяӏ',
+  punctuations='!"(),-.:?«»– ',
+  phonemes='',
+  pad="<PAD>",
+  eos="<EOS>",
+  bos="<BOS>",
+  blank="<BLNK>",
+)
+config = VitsConfig(
+    dashboard_logger='wandb',
+    audio=audio_config,
+    run_name="vits_kbd_female",
+    batch_size=24,
+    eval_batch_size=16,
+    batch_group_size=5,
+    num_loader_workers=0,
+    num_eval_loader_workers=2,
+    run_eval=True,
+    test_delay_epochs=-1,
+    epochs=1000,
+    save_step=1000,
+    text_cleaner="basic_cleaners",
+    use_phonemes=False,
+    #phoneme_language="fa",
+    characters=character_config,
+    phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
+    compute_input_seq_cache=True,
+    print_step=25,
+    print_eval=True,
+    mixed_precision=False,
+    test_sentences=[
+        ["умыпӏащӏэу къедаӏуи псори къэпщӏэнщ"],
+        ["щиху тхьэмпэ цӏыкӏухэм загъэсысу абы сэлам ирахыж щхьэкӏэ псыгъуэ лантӏэхэм загъэшауэ щхьэщэ хуащӏыж"],
+        ["уэрамыбгъум къытеува цӏыху ӏувым я нэр тодие кхъэм яхьым"],
+        ["дэнэ фхьа си лъагъуныгъэр"],
+        ["а махуэм ежьащ цӏыху гъащӏэр зытекӏуэда лъагъуныгъэр"],
+        ["езыхэри лэжьыгъэфӏкӏэ зи цӏэ къаӏэт къуажэ щӏалэгъуалэм ящыщт"],
+        ["дауэ хъуами фенэ къуажэм яфӏэӏеякъым къэзыша унагъуэрти — я нэ-я псэт"],
+        ["хъыджэбзри щтэжри екъужауэ жаӏэ ауэ хухэчыжакъым"],
+        ["ауэ абыи куэд ихьакъым"]
+    ],
+    output_path=output_path,
+    datasets=[dataset_config],
+)
+
+# INITIALIZE THE AUDIO PROCESSOR
+# Audio processor is used for feature extraction and audio I/O.
+# It mainly serves to the dataloader and the training loggers.
+ap = AudioProcessor.init_from_config(config)
+
+# INITIALIZE THE TOKENIZER
+# Tokenizer is used to convert text to sequences of token IDs.
+# config is updated with the default characters if not defined in the config.
+tokenizer, config = TTSTokenizer.init_from_config(config)
+
+# LOAD DATA SAMPLES
+# Each sample is a list of ```[text, audio_file_path, speaker_name]```
+# You can define your custom sample loader returning the list of samples.
+# Or define your custom formatter and pass it to the `load_tts_samples`.
+# Check `TTS.tts.datasets.load_tts_samples` for more details.
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
+
+# init model
+model = Vits(config, ap, tokenizer, speaker_manager=None)
+
+# init the trainer and 🚀
+trainer = Trainer(
+    TrainerArgs(),
+    config,
+    output_path,
+    model=model,
+    train_samples=train_samples,
+    eval_samples=eval_samples,
+)
+trainer.fit()