init

2025/04/10 15:55:52

kokoro/__init__.py

+__version__ = '0.9.4'
+
+from loguru import logger
+import sys
+
+# Remove default handler
+logger.remove()
+
+# Add custom handler with clean format including module and line number
+logger.add(
+    sys.stderr,
+    format="<green>{time:HH:mm:ss}</green> | <cyan>{module:>16}:{line}</cyan> | <level>{level: >8}</level> | <level>{message}</level>",
+    colorize=True,
+    level="INFO" # "DEBUG" to enable logger.debug("message") and up prints 
+                 # "ERROR" to enable only logger.error("message") prints
+                 # etc
+)
+
+# Disable before release or as needed
+logger.disable("kokoro")
+
+from .model import KModel
+from .pipeline import KPipeline

kokoro/__main__.py

+"""Kokoro TTS CLI
+Example usage:
+python3 -m kokoro --text "The sky above the port was the color of television, tuned to a dead channel." -o file.wav --debug
+
+echo "Bom dia mundo, como vão vocês" > text.txt
+python3 -m kokoro -i text.txt -l p --voice pm_alex > audio.wav
+
+Common issues:
+pip not installed: `uv pip install pip`
+(Temporary workaround while https://github.com/explosion/spaCy/issues/13747 is not fixed)
+
+espeak not installed: `apt-get install espeak-ng`
+"""
+
+import argparse
+import wave
+from pathlib import Path
+from typing import Generator, TYPE_CHECKING
+
+import numpy as np
+from loguru import logger
+
+languages = [
+    "a",  # American English
+    "b",  # British English
+    "h",  # Hindi
+    "e",  # Spanish
+    "f",  # French
+    "i",  # Italian
+    "p",  # Brazilian Portuguese
+    "j",  # Japanese
+    "z",  # Mandarin Chinese
+]
+
+if TYPE_CHECKING:
+    from kokoro import KPipeline
+
+
+def generate_audio(
+    text: str, kokoro_language: str, voice: str, speed=1
+) -> Generator["KPipeline.Result", None, None]:
+    from kokoro import KPipeline
+
+    if not voice.startswith(kokoro_language):
+        logger.warning(f"Voice {voice} is not made for language {kokoro_language}")
+    pipeline = KPipeline(lang_code=kokoro_language)
+    yield from pipeline(text, voice=voice, speed=speed, split_pattern=r"\n+")
+
+
+def generate_and_save_audio(
+    output_file: Path, text: str, kokoro_language: str, voice: str, speed=1
+) -> None:
+    with wave.open(str(output_file.resolve()), "wb") as wav_file:
+        wav_file.setnchannels(1)  # Mono audio
+        wav_file.setsampwidth(2)  # 2 bytes per sample (16-bit audio)
+        wav_file.setframerate(24000)  # Sample rate
+
+        for result in generate_audio(
+            text, kokoro_language=kokoro_language, voice=voice, speed=speed
+        ):
+            logger.debug(result.phonemes)
+            if result.audio is None:
+                continue
+            audio_bytes = (result.audio.numpy() * 32767).astype(np.int16).tobytes()
+            wav_file.writeframes(audio_bytes)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-m",
+        "--voice",
+        default="af_heart",
+        help="Voice to use",
+    )
+    parser.add_argument(
+        "-l",
+        "--language",
+        help="Language to use (defaults to the one corresponding to the voice)",
+        choices=languages,
+    )
+    parser.add_argument(
+        "-o",
+        "--output-file",
+        "--output_file",
+        type=Path,
+        help="Path to output WAV file",
+        required=True,
+    )
+    parser.add_argument(
+        "-i",
+        "--input-file",
+        "--input_file",
+        type=Path,
+        help="Path to input text file (default: stdin)",
+    )
+    parser.add_argument(
+        "-t",
+        "--text",
+        help="Text to use instead of reading from stdin",
+    )
+    parser.add_argument(
+        "-s",
+        "--speed",
+        type=float,
+        default=1.0,
+        help="Speech speed",
+    )
+    parser.add_argument(
+        "--debug",
+        action="store_true",
+        help="Print DEBUG messages to console",
+    )
+    args = parser.parse_args()
+    if args.debug:
+        logger.level("DEBUG")
+    logger.debug(args)
+
+    lang = args.language or args.voice[0]
+
+    if args.text is not None and args.input_file is not None:
+        raise Exception("You cannot specify both 'text' and 'input_file'")
+    elif args.text:
+        text = args.text
+    elif args.input_file:
+        file: Path = args.input_file
+        text = file.read_text()
+    else:
+        import sys
+        print("Press Ctrl+D to stop reading input and start generating", flush=True)
+        text = '\n'.join(sys.stdin)
+
+    logger.debug(f"Input text: {text!r}")
+
+    out_file: Path = args.output_file
+    if not out_file.suffix == ".wav":
+        logger.warning("The output file name should end with .wav")
+    generate_and_save_audio(
+        output_file=out_file,
+        text=text,
+        kokoro_language=lang,
+        voice=args.voice,
+        speed=args.speed,
+    )
+
+
+if __name__ == "__main__":
+    main()

kokoro/custom_stft.py

+from attr import attr
+import numpy as np
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+class CustomSTFT(nn.Module):
+    """
+    STFT/iSTFT without unfold/complex ops, using conv1d and conv_transpose1d.
+
+    - forward STFT => Real-part conv1d + Imag-part conv1d
+    - inverse STFT => Real-part conv_transpose1d + Imag-part conv_transpose1d + sum
+    - avoids F.unfold, so easier to export to ONNX
+    - uses replicate or constant padding for 'center=True' to approximate 'reflect' 
+      (reflect is not supported for dynamic shapes in ONNX)
+    """
+
+    def __init__(
+        self,
+        filter_length=800,
+        hop_length=200,
+        win_length=800,
+        window="hann",
+        center=True,
+        pad_mode="replicate",  # or 'constant'
+    ):
+        super().__init__()
+        self.filter_length = filter_length
+        self.hop_length = hop_length
+        self.win_length = win_length
+        self.n_fft = filter_length
+        self.center = center
+        self.pad_mode = pad_mode
+
+        # Number of frequency bins for real-valued STFT with onesided=True
+        self.freq_bins = self.n_fft // 2 + 1
+
+        # Build window
+        assert window == 'hann', window
+        window_tensor = torch.hann_window(win_length, periodic=True, dtype=torch.float32)
+        if self.win_length < self.n_fft:
+            # Zero-pad up to n_fft
+            extra = self.n_fft - self.win_length
+            window_tensor = F.pad(window_tensor, (0, extra))
+        elif self.win_length > self.n_fft:
+            window_tensor = window_tensor[: self.n_fft]
+        self.register_buffer("window", window_tensor)
+
+        # Precompute forward DFT (real, imag)
+        # PyTorch stft uses e^{-j 2 pi k n / N} => real=cos(...), imag=-sin(...)
+        n = np.arange(self.n_fft)
+        k = np.arange(self.freq_bins)
+        angle = 2 * np.pi * np.outer(k, n) / self.n_fft  # shape (freq_bins, n_fft)
+        dft_real = np.cos(angle)
+        dft_imag = -np.sin(angle)  # note negative sign
+
+        # Combine window and dft => shape (freq_bins, filter_length)
+        # We'll make 2 conv weight tensors of shape (freq_bins, 1, filter_length).
+        forward_window = window_tensor.numpy()  # shape (n_fft,)
+        forward_real = dft_real * forward_window  # (freq_bins, n_fft)
+        forward_imag = dft_imag * forward_window
+
+        # Convert to PyTorch
+        forward_real_torch = torch.from_numpy(forward_real).float()
+        forward_imag_torch = torch.from_numpy(forward_imag).float()
+
+        # Register as Conv1d weight => (out_channels, in_channels, kernel_size)
+        # out_channels = freq_bins, in_channels=1, kernel_size=n_fft
+        self.register_buffer(
+            "weight_forward_real", forward_real_torch.unsqueeze(1)
+        )
+        self.register_buffer(
+            "weight_forward_imag", forward_imag_torch.unsqueeze(1)
+        )
+
+        # Precompute inverse DFT
+        # Real iFFT formula => scale = 1/n_fft, doubling for bins 1..freq_bins-2 if n_fft even, etc.
+        # For simplicity, we won't do the "DC/nyquist not doubled" approach here. 
+        # If you want perfect real iSTFT, you can add that logic. 
+        # This version just yields good approximate reconstruction with Hann + typical overlap.
+        inv_scale = 1.0 / self.n_fft
+        n = np.arange(self.n_fft)
+        angle_t = 2 * np.pi * np.outer(n, k) / self.n_fft  # shape (n_fft, freq_bins)
+        idft_cos = np.cos(angle_t).T  # => (freq_bins, n_fft)
+        idft_sin = np.sin(angle_t).T  # => (freq_bins, n_fft)
+
+        # Multiply by window again for typical overlap-add
+        # We also incorporate the scale factor 1/n_fft
+        inv_window = window_tensor.numpy() * inv_scale
+        backward_real = idft_cos * inv_window  # (freq_bins, n_fft)
+        backward_imag = idft_sin * inv_window
+
+        # We'll implement iSTFT as real+imag conv_transpose with stride=hop.
+        self.register_buffer(
+            "weight_backward_real", torch.from_numpy(backward_real).float().unsqueeze(1)
+        )
+        self.register_buffer(
+            "weight_backward_imag", torch.from_numpy(backward_imag).float().unsqueeze(1)
+        )
+        
+
+
+    def transform(self, waveform: torch.Tensor):
+        """
+        Forward STFT => returns magnitude, phase
+        Output shape => (batch, freq_bins, frames)
+        """
+        # waveform shape => (B, T).  conv1d expects (B, 1, T).
+        # Optional center pad
+        if self.center:
+            pad_len = self.n_fft // 2
+            waveform = F.pad(waveform, (pad_len, pad_len), mode=self.pad_mode)
+
+        x = waveform.unsqueeze(1)  # => (B, 1, T)
+        # Convolution to get real part => shape (B, freq_bins, frames)
+        real_out = F.conv1d(
+            x,
+            self.weight_forward_real,
+            bias=None,
+            stride=self.hop_length,
+            padding=0,
+        )
+        # Imag part
+        imag_out = F.conv1d(
+            x,
+            self.weight_forward_imag,
+            bias=None,
+            stride=self.hop_length,
+            padding=0,
+        )
+
+        # magnitude, phase
+        magnitude = torch.sqrt(real_out**2 + imag_out**2 + 1e-14)
+        phase = torch.atan2(imag_out, real_out)
+        # Handle the case where imag_out is 0 and real_out is negative to correct ONNX atan2 to match PyTorch
+        # In this case, PyTorch returns pi, ONNX returns -pi
+        correction_mask = (imag_out == 0) & (real_out < 0)
+        phase[correction_mask] = torch.pi
+        return magnitude, phase
+
+
+    def inverse(self, magnitude: torch.Tensor, phase: torch.Tensor, length=None):
+        """
+        Inverse STFT => returns waveform shape (B, T).
+        """
+        # magnitude, phase => (B, freq_bins, frames)
+        # Re-create real/imag => shape (B, freq_bins, frames)
+        real_part = magnitude * torch.cos(phase)
+        imag_part = magnitude * torch.sin(phase)
+
+        # conv_transpose wants shape (B, freq_bins, frames). We'll treat "frames" as time dimension
+        # so we do (B, freq_bins, frames) => (B, freq_bins, frames)
+        # But PyTorch conv_transpose1d expects (B, in_channels, input_length)
+        real_part = real_part  # (B, freq_bins, frames)
+        imag_part = imag_part
+
+        # real iSTFT => convolve with "backward_real", "backward_imag", and sum
+        # We'll do 2 conv_transpose calls, each giving (B, 1, time),
+        # then add them => (B, 1, time).
+        real_rec = F.conv_transpose1d(
+            real_part,
+            self.weight_backward_real,  # shape (freq_bins, 1, filter_length)
+            bias=None,
+            stride=self.hop_length,
+            padding=0,
+        )
+        imag_rec = F.conv_transpose1d(
+            imag_part,
+            self.weight_backward_imag,
+            bias=None,
+            stride=self.hop_length,
+            padding=0,
+        )
+        # sum => (B, 1, time)
+        waveform = real_rec - imag_rec  # typical real iFFT has minus for imaginary part
+
+        # If we used "center=True" in forward, we should remove pad
+        if self.center:
+            pad_len = self.n_fft // 2
+            # Because of transposed convolution, total length might have extra samples
+            # We remove `pad_len` from start & end if possible
+            waveform = waveform[..., pad_len:-pad_len]
+
+        # If a specific length is desired, clamp
+        if length is not None:
+            waveform = waveform[..., :length]
+
+        # shape => (B, T)
+        return waveform
+
+    def forward(self, x: torch.Tensor):
+        """
+        Full STFT -> iSTFT pass: returns time-domain reconstruction.
+        Same interface as your original code.
+        """
+        mag, phase = self.transform(x)
+        return self.inverse(mag, phase, length=x.shape[-1])

kokoro/istftnet.py

+# ADAPTED from https://github.com/yl4579/StyleTTS2/blob/main/Modules/istftnet.py
+from kokoro.custom_stft import CustomSTFT
+from torch.nn.utils import weight_norm
+import math
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+# https://github.com/yl4579/StyleTTS2/blob/main/Modules/utils.py
+def init_weights(m, mean=0.0, std=0.01):
+    classname = m.__class__.__name__
+    if classname.find("Conv") != -1:
+        m.weight.data.normal_(mean, std)
+
+def get_padding(kernel_size, dilation=1):
+    return int((kernel_size*dilation - dilation)/2)
+
+
+class AdaIN1d(nn.Module):
+    def __init__(self, style_dim, num_features):
+        super().__init__()
+        # affine should be False, however there's a bug in the old torch.onnx.export (not newer dynamo) that causes the channel dimension to be lost if affine=False. When affine is true, there's additional learnably parameters. This shouldn't really matter setting it to True, since we're in inference mode
+        self.norm = nn.InstanceNorm1d(num_features, affine=True)
+        self.fc = nn.Linear(style_dim, num_features*2)
+
+    def forward(self, x, s):
+        h = self.fc(s)
+        h = h.view(h.size(0), h.size(1), 1)
+        gamma, beta = torch.chunk(h, chunks=2, dim=1)
+        return (1 + gamma) * self.norm(x) + beta
+
+
+class AdaINResBlock1(nn.Module):
+    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5), style_dim=64):
+        super(AdaINResBlock1, self).__init__()
+        self.convs1 = nn.ModuleList([
+            weight_norm(nn.Conv1d(channels, channels, kernel_size, 1, dilation=dilation[0],
+                                  padding=get_padding(kernel_size, dilation[0]))),
+            weight_norm(nn.Conv1d(channels, channels, kernel_size, 1, dilation=dilation[1],
+                                  padding=get_padding(kernel_size, dilation[1]))),
+            weight_norm(nn.Conv1d(channels, channels, kernel_size, 1, dilation=dilation[2],
+                                  padding=get_padding(kernel_size, dilation[2])))
+        ])
+        self.convs1.apply(init_weights)
+        self.convs2 = nn.ModuleList([
+            weight_norm(nn.Conv1d(channels, channels, kernel_size, 1, dilation=1,
+                                  padding=get_padding(kernel_size, 1))),
+            weight_norm(nn.Conv1d(channels, channels, kernel_size, 1, dilation=1,
+                                  padding=get_padding(kernel_size, 1))),
+            weight_norm(nn.Conv1d(channels, channels, kernel_size, 1, dilation=1,
+                                  padding=get_padding(kernel_size, 1)))
+        ])
+        self.convs2.apply(init_weights)
+        self.adain1 = nn.ModuleList([
+            AdaIN1d(style_dim, channels),
+            AdaIN1d(style_dim, channels),
+            AdaIN1d(style_dim, channels),
+        ])
+        self.adain2 = nn.ModuleList([
+            AdaIN1d(style_dim, channels),
+            AdaIN1d(style_dim, channels),
+            AdaIN1d(style_dim, channels),
+        ])
+        self.alpha1 = nn.ParameterList([nn.Parameter(torch.ones(1, channels, 1)) for i in range(len(self.convs1))])
+        self.alpha2 = nn.ParameterList([nn.Parameter(torch.ones(1, channels, 1)) for i in range(len(self.convs2))])
+
+    def forward(self, x, s):
+        for c1, c2, n1, n2, a1, a2 in zip(self.convs1, self.convs2, self.adain1, self.adain2, self.alpha1, self.alpha2):
+            xt = n1(x, s)
+            xt = xt + (1 / a1) * (torch.sin(a1 * xt) ** 2)  # Snake1D
+            xt = c1(xt)
+            xt = n2(xt, s)
+            xt = xt + (1 / a2) * (torch.sin(a2 * xt) ** 2)  # Snake1D
+            xt = c2(xt)
+            x = xt + x
+        return x
+
+
+class TorchSTFT(nn.Module):
+    def __init__(self, filter_length=800, hop_length=200, win_length=800, window='hann'):
+        super().__init__()
+        self.filter_length = filter_length
+        self.hop_length = hop_length
+        self.win_length = win_length
+        assert window == 'hann', window
+        self.window = torch.hann_window(win_length, periodic=True, dtype=torch.float32)
+
+    def transform(self, input_data):
+        forward_transform = torch.stft(
+            input_data,
+            self.filter_length, self.hop_length, self.win_length, window=self.window.to(input_data.device),
+            return_complex=True)
+        return torch.abs(forward_transform), torch.angle(forward_transform)
+
+    def inverse(self, magnitude, phase):
+        inverse_transform = torch.istft(
+            magnitude * torch.exp(phase * 1j),
+            self.filter_length, self.hop_length, self.win_length, window=self.window.to(magnitude.device))
+        return inverse_transform.unsqueeze(-2)  # unsqueeze to stay consistent with conv_transpose1d implementation
+
+    def forward(self, input_data):
+        self.magnitude, self.phase = self.transform(input_data)
+        reconstruction = self.inverse(self.magnitude, self.phase)
+        return reconstruction
+
+
+class SineGen(nn.Module):
+    """ Definition of sine generator
+    SineGen(samp_rate, harmonic_num = 0,
+            sine_amp = 0.1, noise_std = 0.003,
+            voiced_threshold = 0,
+            flag_for_pulse=False)
+    samp_rate: sampling rate in Hz
+    harmonic_num: number of harmonic overtones (default 0)
+    sine_amp: amplitude of sine-wavefrom (default 0.1)
+    noise_std: std of Gaussian noise (default 0.003)
+    voiced_thoreshold: F0 threshold for U/V classification (default 0)
+    flag_for_pulse: this SinGen is used inside PulseGen (default False)
+    Note: when flag_for_pulse is True, the first time step of a voiced
+        segment is always sin(torch.pi) or cos(0)
+    """
+    def __init__(self, samp_rate, upsample_scale, harmonic_num=0,
+                 sine_amp=0.1, noise_std=0.003,
+                 voiced_threshold=0,
+                 flag_for_pulse=False):
+        super(SineGen, self).__init__()
+        self.sine_amp = sine_amp
+        self.noise_std = noise_std
+        self.harmonic_num = harmonic_num
+        self.dim = self.harmonic_num + 1
+        self.sampling_rate = samp_rate
+        self.voiced_threshold = voiced_threshold
+        self.flag_for_pulse = flag_for_pulse
+        self.upsample_scale = upsample_scale
+
+    def _f02uv(self, f0):
+        # generate uv signal
+        uv = (f0 > self.voiced_threshold).type(torch.float32)
+        return uv
+
+    def _f02sine(self, f0_values):
+        """ f0_values: (batchsize, length, dim)
+            where dim indicates fundamental tone and overtones
+        """
+        # convert to F0 in rad. The interger part n can be ignored
+        # because 2 * torch.pi * n doesn't affect phase
+        rad_values = (f0_values / self.sampling_rate) % 1
+        # initial phase noise (no noise for fundamental component)
+        rand_ini = torch.rand(f0_values.shape[0], f0_values.shape[2], device=f0_values.device)
+        rand_ini[:, 0] = 0
+        rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini
+        # instantanouse phase sine[t] = sin(2*pi \sum_i=1 ^{t} rad)
+        if not self.flag_for_pulse:
+            rad_values = F.interpolate(rad_values.transpose(1, 2), scale_factor=1/self.upsample_scale, mode="linear").transpose(1, 2)
+            phase = torch.cumsum(rad_values, dim=1) * 2 * torch.pi
+            phase = F.interpolate(phase.transpose(1, 2) * self.upsample_scale, scale_factor=self.upsample_scale, mode="linear").transpose(1, 2)
+            sines = torch.sin(phase)
+        else:
+            # If necessary, make sure that the first time step of every
+            # voiced segments is sin(pi) or cos(0)
+            # This is used for pulse-train generation
+            # identify the last time step in unvoiced segments
+            uv = self._f02uv(f0_values)
+            uv_1 = torch.roll(uv, shifts=-1, dims=1)
+            uv_1[:, -1, :] = 1
+            u_loc = (uv < 1) * (uv_1 > 0)
+            # get the instantanouse phase
+            tmp_cumsum = torch.cumsum(rad_values, dim=1)
+            # different batch needs to be processed differently
+            for idx in range(f0_values.shape[0]):
+                temp_sum = tmp_cumsum[idx, u_loc[idx, :, 0], :]
+                temp_sum[1:, :] = temp_sum[1:, :] - temp_sum[0:-1, :]
+                # stores the accumulation of i.phase within
+                # each voiced segments
+                tmp_cumsum[idx, :, :] = 0
+                tmp_cumsum[idx, u_loc[idx, :, 0], :] = temp_sum
+            # rad_values - tmp_cumsum: remove the accumulation of i.phase
+            # within the previous voiced segment.
+            i_phase = torch.cumsum(rad_values - tmp_cumsum, dim=1)
+            # get the sines
+            sines = torch.cos(i_phase * 2 * torch.pi)
+        return sines
+
+    def forward(self, f0):
+        """ sine_tensor, uv = forward(f0)
+        input F0: tensor(batchsize=1, length, dim=1)
+                  f0 for unvoiced steps should be 0
+        output sine_tensor: tensor(batchsize=1, length, dim)
+        output uv: tensor(batchsize=1, length, 1)
+        """
+        f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim, device=f0.device)
+        # fundamental component
+        fn = torch.multiply(f0, torch.FloatTensor([[range(1, self.harmonic_num + 2)]]).to(f0.device))
+        # generate sine waveforms
+        sine_waves = self._f02sine(fn) * self.sine_amp
+        # generate uv signal
+        # uv = torch.ones(f0.shape)
+        # uv = uv * (f0 > self.voiced_threshold)
+        uv = self._f02uv(f0)
+        # noise: for unvoiced should be similar to sine_amp
+        #        std = self.sine_amp/3 -> max value ~ self.sine_amp
+        #        for voiced regions is self.noise_std
+        noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3
+        noise = noise_amp * torch.randn_like(sine_waves)
+        # first: set the unvoiced part to 0 by uv
+        # then: additive noise
+        sine_waves = sine_waves * uv + noise
+        return sine_waves, uv, noise
+
+
+class SourceModuleHnNSF(nn.Module):
+    """ SourceModule for hn-nsf
+    SourceModule(sampling_rate, harmonic_num=0, sine_amp=0.1,
+                 add_noise_std=0.003, voiced_threshod=0)
+    sampling_rate: sampling_rate in Hz
+    harmonic_num: number of harmonic above F0 (default: 0)
+    sine_amp: amplitude of sine source signal (default: 0.1)
+    add_noise_std: std of additive Gaussian noise (default: 0.003)
+        note that amplitude of noise in unvoiced is decided
+        by sine_amp
+    voiced_threshold: threhold to set U/V given F0 (default: 0)
+    Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
+    F0_sampled (batchsize, length, 1)
+    Sine_source (batchsize, length, 1)
+    noise_source (batchsize, length 1)
+    uv (batchsize, length, 1)
+    """
+    def __init__(self, sampling_rate, upsample_scale, harmonic_num=0, sine_amp=0.1,
+                 add_noise_std=0.003, voiced_threshod=0):
+        super(SourceModuleHnNSF, self).__init__()
+        self.sine_amp = sine_amp
+        self.noise_std = add_noise_std
+        # to produce sine waveforms
+        self.l_sin_gen = SineGen(sampling_rate, upsample_scale, harmonic_num,
+                                 sine_amp, add_noise_std, voiced_threshod)
+        # to merge source harmonics into a single excitation
+        self.l_linear = nn.Linear(harmonic_num + 1, 1)
+        self.l_tanh = nn.Tanh()
+
+    def forward(self, x):
+        """
+        Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
+        F0_sampled (batchsize, length, 1)
+        Sine_source (batchsize, length, 1)
+        noise_source (batchsize, length 1)
+        """
+        # source for harmonic branch
+        with torch.no_grad():
+            sine_wavs, uv, _ = self.l_sin_gen(x)
+        sine_merge = self.l_tanh(self.l_linear(sine_wavs))
+        # source for noise branch, in the same shape as uv
+        noise = torch.randn_like(uv) * self.sine_amp / 3
+        return sine_merge, noise, uv
+
+
+class Generator(nn.Module):
+    def __init__(self, style_dim, resblock_kernel_sizes, upsample_rates, upsample_initial_channel, resblock_dilation_sizes, upsample_kernel_sizes, gen_istft_n_fft, gen_istft_hop_size, disable_complex=False):
+        super(Generator, self).__init__()
+        self.num_kernels = len(resblock_kernel_sizes)
+        self.num_upsamples = len(upsample_rates)
+        self.m_source = SourceModuleHnNSF(
+                    sampling_rate=24000,
+                    upsample_scale=math.prod(upsample_rates) * gen_istft_hop_size,
+                    harmonic_num=8, voiced_threshod=10)
+        self.f0_upsamp = nn.Upsample(scale_factor=math.prod(upsample_rates) * gen_istft_hop_size)
+        self.noise_convs = nn.ModuleList()
+        self.noise_res = nn.ModuleList()
+        self.ups = nn.ModuleList()
+        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+            self.ups.append(weight_norm(
+                nn.ConvTranspose1d(upsample_initial_channel//(2**i), upsample_initial_channel//(2**(i+1)),
+                                   k, u, padding=(k-u)//2)))
+        self.resblocks = nn.ModuleList()
+        for i in range(len(self.ups)):
+            ch = upsample_initial_channel//(2**(i+1))
+            for j, (k, d) in enumerate(zip(resblock_kernel_sizes,resblock_dilation_sizes)):
+                self.resblocks.append(AdaINResBlock1(ch, k, d, style_dim))
+            c_cur = upsample_initial_channel // (2 ** (i + 1))
+            if i + 1 < len(upsample_rates):
+                stride_f0 = math.prod(upsample_rates[i + 1:])
+                self.noise_convs.append(nn.Conv1d(
+                    gen_istft_n_fft + 2, c_cur, kernel_size=stride_f0 * 2, stride=stride_f0, padding=(stride_f0+1) // 2))
+                self.noise_res.append(AdaINResBlock1(c_cur, 7, [1,3,5], style_dim))
+            else:
+                self.noise_convs.append(nn.Conv1d(gen_istft_n_fft + 2, c_cur, kernel_size=1))
+                self.noise_res.append(AdaINResBlock1(c_cur, 11, [1,3,5], style_dim))
+        self.post_n_fft = gen_istft_n_fft
+        self.conv_post = weight_norm(nn.Conv1d(ch, self.post_n_fft + 2, 7, 1, padding=3))
+        self.ups.apply(init_weights)
+        self.conv_post.apply(init_weights)
+        self.reflection_pad = nn.ReflectionPad1d((1, 0))
+        self.stft = (
+            CustomSTFT(filter_length=gen_istft_n_fft, hop_length=gen_istft_hop_size, win_length=gen_istft_n_fft)
+            if disable_complex
+            else TorchSTFT(filter_length=gen_istft_n_fft, hop_length=gen_istft_hop_size, win_length=gen_istft_n_fft)
+        )
+
+    def forward(self, x, s, f0):
+        with torch.no_grad():
+            f0 = self.f0_upsamp(f0[:, None]).transpose(1, 2)  # bs,n,t
+            har_source, noi_source, uv = self.m_source(f0)
+            har_source = har_source.transpose(1, 2).squeeze(1)
+            har_spec, har_phase = self.stft.transform(har_source)
+            har = torch.cat([har_spec, har_phase], dim=1)
+        for i in range(self.num_upsamples):
+            x = F.leaky_relu(x, negative_slope=0.1) 
+            x_source = self.noise_convs[i](har)
+            x_source = self.noise_res[i](x_source, s)
+            x = self.ups[i](x)
+            if i == self.num_upsamples - 1:
+                x = self.reflection_pad(x)
+            x = x + x_source
+            xs = None
+            for j in range(self.num_kernels):
+                if xs is None:
+                    xs = self.resblocks[i*self.num_kernels+j](x, s)
+                else:
+                    xs += self.resblocks[i*self.num_kernels+j](x, s)
+            x = xs / self.num_kernels
+        x = F.leaky_relu(x)
+        x = self.conv_post(x)
+        spec = torch.exp(x[:,:self.post_n_fft // 2 + 1, :])
+        phase = torch.sin(x[:, self.post_n_fft // 2 + 1:, :])
+        return self.stft.inverse(spec, phase)
+
+
+class UpSample1d(nn.Module):
+    def __init__(self, layer_type):
+        super().__init__()
+        self.layer_type = layer_type
+
+    def forward(self, x):
+        if self.layer_type == 'none':
+            return x
+        else:
+            return F.interpolate(x, scale_factor=2, mode='nearest')
+
+
+class AdainResBlk1d(nn.Module):
+    def __init__(self, dim_in, dim_out, style_dim=64, actv=nn.LeakyReLU(0.2), upsample='none', dropout_p=0.0):
+        super().__init__()
+        self.actv = actv
+        self.upsample_type = upsample
+        self.upsample = UpSample1d(upsample)
+        self.learned_sc = dim_in != dim_out
+        self._build_weights(dim_in, dim_out, style_dim)
+        self.dropout = nn.Dropout(dropout_p)
+        if upsample == 'none':
+            self.pool = nn.Identity()
+        else:
+            self.pool = weight_norm(nn.ConvTranspose1d(dim_in, dim_in, kernel_size=3, stride=2, groups=dim_in, padding=1, output_padding=1))
+
+    def _build_weights(self, dim_in, dim_out, style_dim):
+        self.conv1 = weight_norm(nn.Conv1d(dim_in, dim_out, 3, 1, 1))
+        self.conv2 = weight_norm(nn.Conv1d(dim_out, dim_out, 3, 1, 1))
+        self.norm1 = AdaIN1d(style_dim, dim_in)
+        self.norm2 = AdaIN1d(style_dim, dim_out)
+        if self.learned_sc:
+            self.conv1x1 = weight_norm(nn.Conv1d(dim_in, dim_out, 1, 1, 0, bias=False))
+
+    def _shortcut(self, x):
+        x = self.upsample(x)
+        if self.learned_sc:
+            x = self.conv1x1(x)
+        return x
+
+    def _residual(self, x, s):
+        x = self.norm1(x, s)
+        x = self.actv(x)
+        x = self.pool(x)
+        x = self.conv1(self.dropout(x))
+        x = self.norm2(x, s)
+        x = self.actv(x)
+        x = self.conv2(self.dropout(x))
+        return x
+
+    def forward(self, x, s):
+        out = self._residual(x, s)
+        out = (out + self._shortcut(x)) * torch.rsqrt(torch.tensor(2))
+        return out
+
+
+class Decoder(nn.Module):
+    def __init__(self, dim_in, style_dim, dim_out, 
+                 resblock_kernel_sizes,
+                 upsample_rates,
+                 upsample_initial_channel,
+                 resblock_dilation_sizes,
+                 upsample_kernel_sizes,
+                 gen_istft_n_fft, gen_istft_hop_size,
+                 disable_complex=False):
+        super().__init__()
+        self.encode = AdainResBlk1d(dim_in + 2, 1024, style_dim)
+        self.decode = nn.ModuleList()
+        self.decode.append(AdainResBlk1d(1024 + 2 + 64, 1024, style_dim))
+        self.decode.append(AdainResBlk1d(1024 + 2 + 64, 1024, style_dim))
+        self.decode.append(AdainResBlk1d(1024 + 2 + 64, 1024, style_dim))
+        self.decode.append(AdainResBlk1d(1024 + 2 + 64, 512, style_dim, upsample=True))
+        self.F0_conv = weight_norm(nn.Conv1d(1, 1, kernel_size=3, stride=2, groups=1, padding=1))
+        self.N_conv = weight_norm(nn.Conv1d(1, 1, kernel_size=3, stride=2, groups=1, padding=1))
+        self.asr_res = nn.Sequential(weight_norm(nn.Conv1d(512, 64, kernel_size=1)))
+        self.generator = Generator(style_dim, resblock_kernel_sizes, upsample_rates, 
+                                   upsample_initial_channel, resblock_dilation_sizes, 
+                                   upsample_kernel_sizes, gen_istft_n_fft, gen_istft_hop_size, disable_complex=disable_complex)
+
+    def forward(self, asr, F0_curve, N, s):
+        F0 = self.F0_conv(F0_curve.unsqueeze(1))
+        N = self.N_conv(N.unsqueeze(1))
+        x = torch.cat([asr, F0, N], axis=1)
+        x = self.encode(x, s)
+        asr_res = self.asr_res(asr)
+        res = True
+        for block in self.decode:
+            if res:
+                x = torch.cat([x, asr_res, F0, N], axis=1)
+            x = block(x, s)
+            if block.upsample_type != "none":
+                res = False
+        x = self.generator(x, s, F0_curve)
+        return x