|
|
|
|
|
__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: 24000 |
|
|
llm_input_size: 2048 |
|
|
llm_output_size: 2048 |
|
|
spk_embed_dim: 192 |
|
|
qwen_pretrain_path: '' |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llm: !new:model.llm.llm.RWKV7LM |
|
|
llm_input_size: !ref <llm_input_size> |
|
|
llm_output_size: !ref <llm_output_size> |
|
|
speech_token_size: 6561 |
|
|
length_normalized_loss: True |
|
|
lsm_weight: 0 |
|
|
vocab_size: 65548 |
|
|
llm: !ref <qwen_pretrain_path> |
|
|
sampling: !name:cosyvoice.utils.common.ras_sampling |
|
|
top_p: 0.8 |
|
|
top_k: 25 |
|
|
win_size: 10 |
|
|
tau_r: 0.1 |
|
|
|
|
|
flow: !new:cosyvoice.flow.flow.CausalMaskedDiffWithXvec |
|
|
input_size: 512 |
|
|
output_size: 80 |
|
|
spk_embed_dim: !ref <spk_embed_dim> |
|
|
output_type: 'mel' |
|
|
vocab_size: 6561 |
|
|
input_frame_rate: 25 |
|
|
only_mask_loss: True |
|
|
token_mel_ratio: 2 |
|
|
pre_lookahead_len: 3 |
|
|
encoder: !new:cosyvoice.transformer.upsample_encoder.UpsampleConformerEncoder |
|
|
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 |
|
|
decoder: !new:cosyvoice.flow.flow_matching.CausalConditionalCFM |
|
|
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:cosyvoice.flow.decoder.ConditionalDecoder |
|
|
in_channels: 320 |
|
|
out_channels: 80 |
|
|
causal: True |
|
|
channels: [256] |
|
|
dropout: 0.0 |
|
|
attention_head_dim: 64 |
|
|
n_blocks: 4 |
|
|
num_mid_blocks: 12 |
|
|
num_heads: 8 |
|
|
act_fn: 'gelu' |
|
|
|
|
|
hift: !new:cosyvoice.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, 5, 3] |
|
|
upsample_kernel_sizes: [16, 11, 7] |
|
|
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, 7, 11] |
|
|
source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]] |
|
|
lrelu_slope: 0.1 |
|
|
audio_limit: 0.99 |
|
|
f0_predictor: !new:cosyvoice.hifigan.f0_predictor.ConvRNNF0Predictor |
|
|
num_class: 1 |
|
|
in_channels: 80 |
|
|
cond_channels: 512 |
|
|
|
|
|
|
|
|
get_tokenizer: !name:utils.utilities.get_tokenizer |
|
|
model_dir: !ref <qwen_pretrain_path> |
|
|
allowed_special: 'all' |
|
|
feat_extractor: !name:matcha.utils.audio.mel_spectrogram |
|
|
n_fft: 1920 |
|
|
num_mels: 80 |
|
|
sampling_rate: !ref <sample_rate> |
|
|
hop_size: 480 |
|
|
win_size: 1920 |
|
|
fmin: 0 |
|
|
fmax: 8000 |
|
|
center: False |
|
|
|
