Spaces:
Running
Running
| config: ./conf/tuning/finetune_joint_tacotron2_hifigan.yaml | |
| print_config: false | |
| log_level: INFO | |
| dry_run: false | |
| iterator_type: sequence | |
| output_dir: exp/22k/tts_finetune_joint_tacotron2_hifigan_raw_char | |
| ngpu: 1 | |
| seed: 777 | |
| num_workers: 4 | |
| num_att_plot: 3 | |
| dist_backend: nccl | |
| dist_init_method: env:// | |
| dist_world_size: null | |
| dist_rank: null | |
| local_rank: 0 | |
| dist_master_addr: null | |
| dist_master_port: null | |
| dist_launcher: null | |
| multiprocessing_distributed: false | |
| unused_parameters: true | |
| sharded_ddp: false | |
| cudnn_enabled: true | |
| cudnn_benchmark: false | |
| cudnn_deterministic: false | |
| collect_stats: false | |
| write_collected_feats: false | |
| max_epoch: 140 | |
| patience: null | |
| val_scheduler_criterion: | |
| - valid | |
| - loss | |
| early_stopping_criterion: | |
| - valid | |
| - loss | |
| - min | |
| best_model_criterion: | |
| - - valid | |
| - text2mel_loss | |
| - min | |
| - - train | |
| - text2mel_loss | |
| - min | |
| - - train | |
| - total_count | |
| - max | |
| keep_nbest_models: 5 | |
| nbest_averaging_interval: 0 | |
| grad_clip: -1 | |
| grad_clip_type: 2.0 | |
| grad_noise: false | |
| accum_grad: 1 | |
| no_forward_run: false | |
| resume: true | |
| train_dtype: float32 | |
| use_amp: false | |
| log_interval: 50 | |
| use_matplotlib: true | |
| use_tensorboard: true | |
| create_graph_in_tensorboard: false | |
| use_wandb: false | |
| wandb_project: null | |
| wandb_id: null | |
| wandb_entity: null | |
| wandb_name: null | |
| wandb_model_log_interval: -1 | |
| detect_anomaly: false | |
| pretrain_path: null | |
| init_param: | |
| - exp/22k/tts_train_tacotron2_raw_char/train.loss.ave_5best.pth:tts:tts.generator.text2mel | |
| - exp/22k/ljspeech_hifigan.v1/generator.pth::tts.generator.vocoder | |
| - exp/22k/ljspeech_hifigan.v1/discriminator.pth::tts.discriminator | |
| ignore_init_mismatch: false | |
| freeze_param: [] | |
| num_iters_per_epoch: null | |
| batch_size: 20 | |
| valid_batch_size: null | |
| batch_bins: 1600000 | |
| valid_batch_bins: null | |
| train_shape_file: | |
| - exp/22k/tts_stats_raw_char/train/text_shape.char | |
| - exp/22k/tts_stats_raw_char/train/speech_shape | |
| valid_shape_file: | |
| - exp/22k/tts_stats_raw_char/valid/text_shape.char | |
| - exp/22k/tts_stats_raw_char/valid/speech_shape | |
| batch_type: numel | |
| valid_batch_type: null | |
| fold_length: | |
| - 150 | |
| - 204800 | |
| sort_in_batch: descending | |
| sort_batch: descending | |
| multiple_iterator: false | |
| chunk_length: 500 | |
| chunk_shift_ratio: 0.5 | |
| num_cache_chunks: 1024 | |
| train_data_path_and_name_and_type: | |
| - - dump/22k/raw/tr_no_dev/text | |
| - text | |
| - text | |
| - - dump/22k/raw/tr_no_dev/wav.scp | |
| - speech | |
| - sound | |
| - - dump/22k/xvector/tr_no_dev/xvector.scp | |
| - spembs | |
| - kaldi_ark | |
| valid_data_path_and_name_and_type: | |
| - - dump/22k/raw/dev/text | |
| - text | |
| - text | |
| - - dump/22k/raw/dev/wav.scp | |
| - speech | |
| - sound | |
| - - dump/22k/xvector/dev/xvector.scp | |
| - spembs | |
| - kaldi_ark | |
| allow_variable_data_keys: false | |
| max_cache_size: 0.0 | |
| max_cache_fd: 32 | |
| valid_max_cache_size: null | |
| exclude_weight_decay: false | |
| exclude_weight_decay_conf: {} | |
| optim: adam | |
| optim_conf: | |
| lr: 1.25e-05 | |
| betas: | |
| - 0.5 | |
| - 0.9 | |
| weight_decay: 0.0 | |
| scheduler: exponentiallr | |
| scheduler_conf: | |
| gamma: 0.999875 | |
| optim2: adam | |
| optim2_conf: | |
| lr: 1.25e-05 | |
| betas: | |
| - 0.5 | |
| - 0.9 | |
| weight_decay: 0.0 | |
| scheduler2: exponentiallr | |
| scheduler2_conf: | |
| gamma: 0.999875 | |
| generator_first: true | |
| token_list: | |
| - <blank> | |
| - <unk> | |
| - + | |
| - <space> | |
| - о | |
| - а | |
| - и | |
| - н | |
| - в | |
| - е | |
| - т | |
| - і | |
| - с | |
| - р | |
| - д | |
| - л | |
| - у | |
| - к | |
| - м | |
| - п | |
| - я | |
| - з | |
| - ',' | |
| - б | |
| - ь | |
| - г | |
| - ч | |
| - й | |
| - ж | |
| - х | |
| - ш | |
| - ю | |
| - ц | |
| - щ | |
| - '?' | |
| - '-' | |
| - ї | |
| - є | |
| - '!' | |
| - '''' | |
| - ф | |
| - . | |
| - '"' | |
| - ґ | |
| - ':' | |
| - / | |
| - „ | |
| - <sos/eos> | |
| odim: null | |
| model_conf: {} | |
| use_preprocessor: true | |
| token_type: char | |
| bpemodel: null | |
| non_linguistic_symbols: null | |
| cleaner: null | |
| g2p: g2p_en | |
| feats_extract: fbank | |
| feats_extract_conf: | |
| n_fft: 1024 | |
| hop_length: 256 | |
| win_length: null | |
| fs: 22050 | |
| fmin: 80 | |
| fmax: 7600 | |
| n_mels: 80 | |
| normalize: global_mvn | |
| normalize_conf: | |
| stats_file: feats_stats.npz | |
| tts: joint_text2wav | |
| tts_conf: | |
| text2mel_type: tacotron2 | |
| text2mel_params: | |
| embed_dim: 512 | |
| elayers: 1 | |
| eunits: 512 | |
| econv_layers: 3 | |
| econv_chans: 512 | |
| econv_filts: 5 | |
| atype: location | |
| adim: 512 | |
| aconv_chans: 32 | |
| aconv_filts: 15 | |
| cumulate_att_w: true | |
| dlayers: 2 | |
| dunits: 1024 | |
| prenet_layers: 2 | |
| prenet_units: 256 | |
| postnet_layers: 5 | |
| postnet_chans: 512 | |
| postnet_filts: 5 | |
| output_activation: null | |
| use_batch_norm: true | |
| use_concate: true | |
| use_residual: false | |
| spk_embed_dim: 192 | |
| spk_embed_integration_type: add | |
| dropout_rate: 0.5 | |
| zoneout_rate: 0.1 | |
| reduction_factor: 1 | |
| use_masking: true | |
| bce_pos_weight: 10.0 | |
| use_guided_attn_loss: true | |
| guided_attn_loss_sigma: 0.4 | |
| guided_attn_loss_lambda: 1.0 | |
| idim: 48 | |
| odim: 80 | |
| vocoder_type: hifigan_generator | |
| vocoder_params: | |
| bias: true | |
| channels: 512 | |
| in_channels: 80 | |
| kernel_size: 7 | |
| nonlinear_activation: LeakyReLU | |
| nonlinear_activation_params: | |
| negative_slope: 0.1 | |
| out_channels: 1 | |
| resblock_dilations: | |
| - - 1 | |
| - 3 | |
| - 5 | |
| - - 1 | |
| - 3 | |
| - 5 | |
| - - 1 | |
| - 3 | |
| - 5 | |
| resblock_kernel_sizes: | |
| - 3 | |
| - 7 | |
| - 11 | |
| upsample_kernel_sizes: | |
| - 16 | |
| - 16 | |
| - 4 | |
| - 4 | |
| upsample_scales: | |
| - 8 | |
| - 8 | |
| - 2 | |
| - 2 | |
| use_additional_convs: true | |
| use_weight_norm: true | |
| discriminator_type: hifigan_multi_scale_multi_period_discriminator | |
| discriminator_params: | |
| follow_official_norm: true | |
| period_discriminator_params: | |
| bias: true | |
| channels: 32 | |
| downsample_scales: | |
| - 3 | |
| - 3 | |
| - 3 | |
| - 3 | |
| - 1 | |
| in_channels: 1 | |
| kernel_sizes: | |
| - 5 | |
| - 3 | |
| max_downsample_channels: 1024 | |
| nonlinear_activation: LeakyReLU | |
| nonlinear_activation_params: | |
| negative_slope: 0.1 | |
| out_channels: 1 | |
| use_spectral_norm: false | |
| use_weight_norm: true | |
| periods: | |
| - 2 | |
| - 3 | |
| - 5 | |
| - 7 | |
| - 11 | |
| scale_discriminator_params: | |
| bias: true | |
| channels: 128 | |
| downsample_scales: | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 4 | |
| - 1 | |
| in_channels: 1 | |
| kernel_sizes: | |
| - 15 | |
| - 41 | |
| - 5 | |
| - 3 | |
| max_downsample_channels: 1024 | |
| max_groups: 16 | |
| nonlinear_activation: LeakyReLU | |
| nonlinear_activation_params: | |
| negative_slope: 0.1 | |
| out_channels: 1 | |
| scale_downsample_pooling: AvgPool1d | |
| scale_downsample_pooling_params: | |
| kernel_size: 4 | |
| padding: 2 | |
| stride: 2 | |
| scales: 3 | |
| generator_adv_loss_params: | |
| average_by_discriminators: false | |
| loss_type: mse | |
| discriminator_adv_loss_params: | |
| average_by_discriminators: false | |
| loss_type: mse | |
| use_feat_match_loss: true | |
| feat_match_loss_params: | |
| average_by_discriminators: false | |
| average_by_layers: false | |
| include_final_outputs: true | |
| use_mel_loss: true | |
| mel_loss_params: | |
| fs: 22050 | |
| n_fft: 1024 | |
| hop_length: 256 | |
| win_length: null | |
| window: hann | |
| n_mels: 80 | |
| fmin: 0 | |
| fmax: null | |
| log_base: null | |
| lambda_text2mel: 1.0 | |
| lambda_adv: 1.0 | |
| lambda_mel: 45.0 | |
| lambda_feat_match: 2.0 | |
| sampling_rate: 22050 | |
| segment_size: 32 | |
| cache_generator_outputs: true | |
| pitch_extract: null | |
| pitch_extract_conf: {} | |
| pitch_normalize: null | |
| pitch_normalize_conf: {} | |
| energy_extract: null | |
| energy_extract_conf: {} | |
| energy_normalize: null | |
| energy_normalize_conf: {} | |
| required: | |
| - output_dir | |
| - token_list | |
| version: '202301' | |
| distributed: false | |