| { | |
| "output_path": "output_indic_fastpitch/mni", | |
| "logger_uri": null, | |
| "run_name": "mni_fastpitch_indictts_all_align_off", | |
| "project_name": "indic-fastpitch-stage2", | |
| "run_description": "align_off", | |
| "print_step": 100, | |
| "plot_step": 100, | |
| "model_param_stats": false, | |
| "wandb_entity": "indic-asr", | |
| "dashboard_logger": "wandb", | |
| "log_model_step": 10000, | |
| "save_step": 10000, | |
| "save_n_checkpoints": 1, | |
| "save_checkpoints": true, | |
| "save_all_best": false, | |
| "save_best_after": 10000, | |
| "target_loss": null, | |
| "print_eval": false, | |
| "test_delay_epochs": 0, | |
| "run_eval": true, | |
| "distributed_backend": "nccl", | |
| "distributed_url": "tcp://localhost:54321", | |
| "mixed_precision": true, | |
| "epochs": 1000, | |
| "batch_size": 32, | |
| "eval_batch_size": 32, | |
| "grad_clip": 5.0, | |
| "scheduler_after_epoch": true, | |
| "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 | |
| }, | |
| "lr_scheduler_aligner": "NoamLR", | |
| "lr_scheduler_aligner_params": { | |
| "warmup_steps": 4000 | |
| }, | |
| "use_grad_scaler": false, | |
| "cudnn_enable": true, | |
| "cudnn_deterministic": false, | |
| "cudnn_benchmark": false, | |
| "training_seed": 54321, | |
| "model": "fast_pitch", | |
| "num_loader_workers": 0, | |
| "num_eval_loader_workers": 0, | |
| "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": 60.0, | |
| "do_rms_norm": false, | |
| "db_level": null, | |
| "power": 1.5, | |
| "griffin_lim_iters": 60, | |
| "num_mels": 80, | |
| "mel_fmin": 0.0, | |
| "mel_fmax": 8000, | |
| "spec_gain": 1.0, | |
| "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": false, | |
| "phonemizer": null, | |
| "phoneme_language": "en-us", | |
| "compute_input_seq_cache": false, | |
| "text_cleaner": "multilingual_cleaners", | |
| "enable_eos_bos_chars": false, | |
| "test_sentences_file": "", | |
| "phoneme_cache_path": "output_indic_fastpitch/mni/phoneme_cache", | |
| "characters": { | |
| "characters_class": "TTS.tts.models.vits.VitsCharacters", | |
| "vocab_dict": null, | |
| "pad": "<PAD>", | |
| "eos": "<EOS>", | |
| "bos": "<BOS>", | |
| "blank": "<BLNK>", | |
| "characters": " ,-./0123456789acefghkmnoprvw\u0981\u0982\u0985\u0986\u0987\u0988\u0989\u098a\u098f\u0990\u0993\u0994\u0995\u0996\u0997\u0998\u0999\u099a\u099b\u099c\u099d\u099e\u099f\u09a0\u09a1\u09a3\u09a4\u09a5\u09a6\u09a7\u09a8\u09aa\u09ab\u09ac\u09ad\u09ae\u09af\u09b0\u09b2\u09b6\u09b7\u09b8\u09b9\u09bc\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd\u09ce\u09df\u09e6\u09e7\u09e8\u09e9\u09ea\u09eb\u09ec\u09ed\u09ee\u09ef\u09f0\u09f1\u09f7", | |
| "punctuations": "!\u00a1'(),-.:;\u00bf? ", | |
| "phonemes": null, | |
| "is_unique": true, | |
| "is_sorted": true | |
| }, | |
| "add_blank": false, | |
| "batch_group_size": 0, | |
| "loss_masking": null, | |
| "sort_by_audio_len": true, | |
| "min_audio_len": 1, | |
| "max_audio_len": 441000, | |
| "min_text_len": 1, | |
| "max_text_len": 400, | |
| "compute_f0": true, | |
| "compute_linear_spec": false, | |
| "precompute_num_workers": 0, | |
| "start_by_longest": false, | |
| "datasets": [ | |
| { | |
| "name": "indictts", | |
| "path": "/home/ttsteam/datasets/indictts/mni", | |
| "meta_file_train": "metadata_train.csv", | |
| "ignored_speakers": null, | |
| "language": "mni", | |
| "meta_file_val": "metadata_test.csv", | |
| "meta_file_attn_mask": "" | |
| } | |
| ], | |
| "test_sentences": [ | |
| "\u09ae\u09a5\u0982 \u09ae\u09a5\u0982, \u0985\u09b8\u09c1\u09ae \u0995\u09be\u0996\u09bf\u09ac\u09a8\u09be.", | |
| "\u09a5\u09c7\u09ac\u09a8\u09be \u0999\u09be\u09b6\u09bf\u0982\u09a6\u09c1 \u0985\u09ae\u09ae\u09ae\u09cd\u09a4\u09be \u0987\u09b2\u09cd\u09b2\u09c7." | |
| ], | |
| "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": 114, | |
| "out_channels": 80, | |
| "hidden_channels": 512, | |
| "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, | |
| "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": 2, | |
| "use_speaker_embedding": true, | |
| "speakers_file": "mni_fastpitch_speakers.pth", | |
| "use_d_vector_file": false, | |
| "d_vector_dim": 512, | |
| "d_vector_file": null, | |
| "use_speaker_encoder_as_loss": false, | |
| "speaker_encoder_config_path": "", | |
| "speaker_encoder_model_path": "", | |
| "vocoder_path": null, | |
| "vocoder_config_path": null, | |
| "use_separate_optimizers": false | |
| }, | |
| "return_wav": false, | |
| "num_speakers": 2, | |
| "speakers_file": "mni_fastpitch_speakers.pth", | |
| "use_speaker_embedding": true, | |
| "use_d_vector_file": false, | |
| "d_vector_file": "", | |
| "d_vector_dim": 512, | |
| "spec_loss_type": "mse", | |
| "duration_loss_type": "mse", | |
| "use_ssim_loss": false, | |
| "ssim_loss_alpha": 1.0, | |
| "spec_loss_alpha": 1.0, | |
| "aligner_loss_alpha": 1.0, | |
| "pitch_loss_alpha": 0.1, | |
| "dur_loss_alpha": 0.1, | |
| "binary_align_loss_alpha": 0.1, | |
| "spk_encoder_loss_alpha": 0.1, | |
| "binary_loss_warmup_epochs": 150, | |
| "aligner_epochs": 0, | |
| "min_seq_len": 13, | |
| "max_seq_len": 500000, | |
| "r": 1, | |
| "f0_cache_path": "output_indic_fastpitch/mni/f0_cache" | |
| } |