This model was trained by kan-bayashi using ljspeech/tts1 recipe in espnet. Python APISee https://github.com/espnet/espnet_model_zoo Evaluate in the recipegit clone https://github.com/espnet/espnet cd espnet git checkout 628b46282537ce532d613d6bafb75e826e8455de pip install -e . cd egs2/ljspeech/tts1 # Download the model file here ./run.sh --skip_data_prep false --skip_train true --download_model kan-bayashi/ljspeech_tts_train_conformer_fastspeech2_raw_phn_tacotron_espeak_ng_english_us_vits_train.loss.ave Configconfig: ./conf/tuning/train_conformer_fastspeech2.ngpu4.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/tts_train_conformer_fastspeech2.ngpu4_raw_phn_none ngpu: 1 seed: 0 num_workers: 8 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: 4 dist_rank: 0 local_rank: 0 dist_master_addr: localhost dist_master_port: 40173 dist_launcher: null multiprocessing_distributed: true unused_parameters: false sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: false collect_stats: false write_collected_feats: false max_epoch: 100 patience: null val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - loss - min - - train - loss - min keep_nbest_models: 5 grad_clip: 1.0 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: null use_tensorboard: true 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: [] ignore_init_mismatch: false freeze_param: [] num_iters_per_epoch: 1000 batch_size: 20 valid_batch_size: null batch_bins: 6000000 valid_batch_bins: null train_shape_file: - exp/tts_train_tacotron2_raw_phn_none/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/text_shape.phn - exp/tts_train_tacotron2_raw_phn_none/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/speech_shape valid_shape_file: - exp/tts_train_tacotron2_raw_phn_none/decode_use_teacher_forcingtrue_train.loss.ave/stats/valid/text_shape.phn - exp/tts_train_tacotron2_raw_phn_none/decode_use_teacher_forcingtrue_train.loss.ave/stats/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/raw/tr_no_dev_phn/text - text - text - - exp/tts_train_tacotron2_raw_phn_none/decode_use_teacher_forcingtrue_train.loss.ave/tr_no_dev_phn/durations - durations - text_int - - dump/raw/tr_no_dev_phn/wav.scp - speech - sound valid_data_path_and_name_and_type: - - dump/raw/dev_phn/text - text - text - - exp/tts_train_tacotron2_raw_phn_none/decode_use_teacher_forcingtrue_train.loss.ave/dev_phn/durations - durations - text_int - - dump/raw/dev_phn/wav.scp - speech - sound allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 valid_max_cache_size: null optim: adam optim_conf: lr: 1.0 scheduler: noamlr scheduler_conf: model_size: 384 warmup_steps: 4000 token_list: - - - - ˈ - ɪ - n - t - ː - ə - d - ɹ - s - l - ð - i - k - ɛ - z - æ - ʌ - m - ˌ - w - p - v - ʊ - a - f - ɚ - ',' - b - u - e - h - o - ʃ - ɑ - ɔ - ᵻ - ɐ - . - ŋ - ɜ - ɾ - ɡ - ʒ - j - θ - ̩ - ʔ - '?' - '!' - r - x - odim: null model_conf: {} use_preprocessor: true token_type: phn bpemodel: null non_linguistic_symbols: null cleaner: tacotron g2p: espeak_ng_english_us_vits 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: exp/tts_train_tacotron2_raw_phn_none/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/feats_stats.npz tts: fastspeech2 tts_conf: adim: 384 aheads: 2 elayers: 4 eunits: 1536 dlayers: 4 dunits: 1536 positionwise_layer_type: conv1d positionwise_conv_kernel_size: 3 duration_predictor_layers: 2 duration_predictor_chans: 256 duration_predictor_kernel_size: 3 postnet_layers: 5 postnet_filts: 5 postnet_chans: 256 use_masking: true encoder_normalize_before: true decoder_normalize_before: true reduction_factor: 1 encoder_type: conformer decoder_type: conformer conformer_pos_enc_layer_type: rel_pos conformer_self_attn_layer_type: rel_selfattn conformer_activation_type: swish use_macaron_style_in_conformer: true use_cnn_in_conformer: true conformer_enc_kernel_size: 7 conformer_dec_kernel_size: 31 init_type: xavier_uniform transformer_enc_dropout_rate: 0.2 transformer_enc_positional_dropout_rate: 0.2 transformer_enc_attn_dropout_rate: 0.2 transformer_dec_dropout_rate: 0.2 transformer_dec_positional_dropout_rate: 0.2 transformer_dec_attn_dropout_rate: 0.2 pitch_predictor_layers: 5 pitch_predictor_chans: 256 pitch_predictor_kernel_size: 5 pitch_predictor_dropout: 0.5 pitch_embed_kernel_size: 1 pitch_embed_dropout: 0.0 stop_gradient_from_pitch_predictor: true energy_predictor_layers: 2 energy_predictor_chans: 256 energy_predictor_kernel_size: 3 energy_predictor_dropout: 0.5 energy_embed_kernel_size: 1 energy_embed_dropout: 0.0 stop_gradient_from_energy_predictor: false pitch_extract: dio pitch_extract_conf: fs: 22050 n_fft: 1024 hop_length: 256 f0max: 400 f0min: 80 reduction_factor: 1 pitch_normalize: global_mvn pitch_normalize_conf: stats_file: exp/tts_train_tacotron2_raw_phn_none/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/pitch_stats.npz energy_extract: energy energy_extract_conf: fs: 22050 n_fft: 1024 hop_length: 256 win_length: null reduction_factor: 1 energy_normalize: global_mvn energy_normalize_conf: stats_file: exp/tts_train_tacotron2_raw_phn_none/decode_use_teacher_forcingtrue_train.loss.ave/stats/train/energy_stats.npz required: - output_dir - token_list version: 0.10.3a2 distributed: true