| __set_seed1: !apply:random.seed [1986] | |
| __set_seed2: !apply:numpy.random.seed [1986] | |
| __set_seed3: !apply:torch.manual_seed [1986] | |
| __set_seed4: !apply:torch.cuda.manual_seed_all [1986] | |
| sample_rate: 22050 | |
| text_encoder_input_size: 512 | |
| llm_input_size: 1024 | |
| llm_output_size: 1024 | |
| spk_embed_dim: 192 | |
| llm: !new:VietTTS.llm.llm.TransformerLM | |
| text_encoder_input_size: !ref <text_encoder_input_size> | |
| llm_input_size: !ref <llm_input_size> | |
| llm_output_size: !ref <llm_output_size> | |
| text_token_size: 60515 | |
| speech_token_size: 4096 | |
| length_normalized_loss: True | |
| lsm_weight: 0 | |
| spk_embed_dim: !ref <spk_embed_dim> | |
| text_encoder: !new:VietTTS.transformer.encoder.ConformerEncoder | |
| input_size: !ref <text_encoder_input_size> | |
| output_size: 1024 | |
| attention_heads: 16 | |
| linear_units: 4096 | |
| num_blocks: 6 | |
| dropout_rate: 0.1 | |
| positional_dropout_rate: 0.1 | |
| attention_dropout_rate: 0.0 | |
| normalize_before: True | |
| input_layer: 'linear' | |
| pos_enc_layer_type: 'rel_pos_espnet' | |
| selfattention_layer_type: 'rel_selfattn' | |
| use_cnn_module: False | |
| macaron_style: False | |
| use_dynamic_chunk: False | |
| use_dynamic_left_chunk: False | |
| static_chunk_size: 1 | |
| llm: !new:VietTTS.transformer.encoder.TransformerEncoder | |
| input_size: !ref <llm_input_size> | |
| output_size: !ref <llm_output_size> | |
| attention_heads: 16 | |
| linear_units: 4096 | |
| num_blocks: 14 | |
| dropout_rate: 0.1 | |
| positional_dropout_rate: 0.1 | |
| attention_dropout_rate: 0.0 | |
| input_layer: 'linear_legacy' | |
| pos_enc_layer_type: 'rel_pos_espnet' | |
| selfattention_layer_type: 'rel_selfattn' | |
| static_chunk_size: 1 | |
| sampling: !name:VietTTS.utils.common.ras_sampling | |
| top_p: 0.8 | |
| top_k: 25 | |
| win_size: 10 | |
| tau_r: 0.1 | |
| flow: !new:VietTTS.flow.flow.MaskedDiffWithXvec | |
| input_size: 512 | |
| output_size: 80 | |
| spk_embed_dim: !ref <spk_embed_dim> | |
| output_type: 'mel' | |
| vocab_size: 4096 | |
| input_frame_rate: 25 | |
| only_mask_loss: True | |
| encoder: !new:VietTTS.transformer.encoder.ConformerEncoder | |
| output_size: 512 | |
| attention_heads: 8 | |
| linear_units: 2048 | |
| num_blocks: 6 | |
| dropout_rate: 0.1 | |
| positional_dropout_rate: 0.1 | |
| attention_dropout_rate: 0.1 | |
| normalize_before: True | |
| input_layer: 'linear' | |
| pos_enc_layer_type: 'rel_pos_espnet' | |
| selfattention_layer_type: 'rel_selfattn' | |
| input_size: 512 | |
| use_cnn_module: False | |
| macaron_style: False | |
| length_regulator: !new:VietTTS.flow.length_regulator.InterpolateRegulator | |
| channels: 80 | |
| sampling_ratios: [1, 1, 1, 1] | |
| decoder: !new:VietTTS.flow.flow_matching.ConditionalCFM | |
| in_channels: 240 | |
| n_spks: 1 | |
| spk_emb_dim: 80 | |
| cfm_params: !new:omegaconf.DictConfig | |
| content: | |
| sigma_min: 1e-06 | |
| solver: 'euler' | |
| t_scheduler: 'cosine' | |
| training_cfg_rate: 0.2 | |
| inference_cfg_rate: 0.7 | |
| reg_loss_type: 'l1' | |
| estimator: !new:VietTTS.flow.decoder.ConditionalDecoder | |
| in_channels: 320 | |
| out_channels: 80 | |
| channels: [256, 256] | |
| dropout: 0.0 | |
| attention_head_dim: 64 | |
| n_blocks: 4 | |
| num_mid_blocks: 12 | |
| num_heads: 8 | |
| act_fn: 'gelu' | |
| hift: !new:VietTTS.hifigan.generator.HiFTGenerator | |
| in_channels: 80 | |
| base_channels: 512 | |
| nb_harmonics: 8 | |
| sampling_rate: !ref <sample_rate> | |
| nsf_alpha: 0.1 | |
| nsf_sigma: 0.003 | |
| nsf_voiced_threshold: 10 | |
| upsample_rates: [8, 8] | |
| upsample_kernel_sizes: [16, 16] | |
| istft_params: | |
| n_fft: 16 | |
| hop_len: 4 | |
| resblock_kernel_sizes: [3, 7, 11] | |
| resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]] | |
| source_resblock_kernel_sizes: [7, 11] | |
| source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5]] | |
| lrelu_slope: 0.1 | |
| audio_limit: 0.99 | |
| f0_predictor: !new:VietTTS.hifigan.f0_predictor.ConvRNNF0Predictor | |
| num_class: 1 | |
| in_channels: 80 | |
| cond_channels: 512 | |