|
|
|
|
|
__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 |
|
|
|
|
|
flow: !new:.audio_detokenizer.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: 50 |
|
|
only_mask_loss: True |
|
|
encoder: !new:.audio_detokenizer.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:.audio_detokenizer.flow.length_regulator.InterpolateRegulator |
|
|
channels: 80 |
|
|
sampling_ratios: [1, 1, 1, 1] |
|
|
decoder: !new:.audio_detokenizer.flow.flow_matching.ConditionalCFM |
|
|
in_channels: 240 |
|
|
n_spks: 1 |
|
|
spk_emb_dim: 80 |
|
|
tensorrt_model_path: 'bin/ckpt_300M/estimator_fp16.plan' |
|
|
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:.audio_detokenizer.flow.decoder.ConditionalDecoder |
|
|
in_channels: 320 |
|
|
out_channels: 80 |
|
|
channels: [256, 256] |
|
|
dropout: 0 |
|
|
attention_head_dim: 64 |
|
|
n_blocks: 4 |
|
|
num_mid_blocks: 12 |
|
|
num_heads: 8 |
|
|
act_fn: 'gelu' |
|
|
|
|
|
hift: !new:.audio_detokenizer.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:.audio_detokenizer.hifigan.f0_predictor.ConvRNNF0Predictor |
|
|
num_class: 1 |
|
|
in_channels: 80 |
|
|
cond_channels: 512 |
|
|
|
|
|
|
