funcineforge_zh_en/vocoder/hift_causal.hyper.yaml

# set random seed, so that you may reproduce your result.
__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]

# fixed params
sample_rate: 24000
text_encoder_input_size: 512
llm_input_size: 1024
llm_output_size: 1024
spk_embed_dim: 192

# model params
# for all class/function included in this repo, we use !<name> or !<new> for intialization, so that user may find all corresponding class/function according to one single yaml.
hift: !new:cosyvoice.models.vocoder.hift_causal.CausalHiFTGenerator
    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.models.vocoder.f0_predictor_causal.CausalConvRNNF0Predictor
        num_class: 1
        in_channels: 80
        cond_channels: 512