initial upload attempt

initial upload attempt

system/tts_engines/rvc/lib/infer_pack/attentions.py

@@ -0,0 +1,398 @@
+import math
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from . import commons
+from .modules import LayerNorm
+
+
+class Encoder(nn.Module):
+    def __init__(
+        self,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size=1,
+        p_dropout=0.0,
+        window_size=10,
+        **kwargs
+    ):
+        super().__init__()
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.window_size = window_size
+
+        self.drop = nn.Dropout(p_dropout)
+        self.attn_layers = nn.ModuleList()
+        self.norm_layers_1 = nn.ModuleList()
+        self.ffn_layers = nn.ModuleList()
+        self.norm_layers_2 = nn.ModuleList()
+        for i in range(self.n_layers):
+            self.attn_layers.append(
+                MultiHeadAttention(
+                    hidden_channels,
+                    hidden_channels,
+                    n_heads,
+                    p_dropout=p_dropout,
+                    window_size=window_size,
+                )
+            )
+            self.norm_layers_1.append(LayerNorm(hidden_channels))
+            self.ffn_layers.append(
+                FFN(
+                    hidden_channels,
+                    hidden_channels,
+                    filter_channels,
+                    kernel_size,
+                    p_dropout=p_dropout,
+                )
+            )
+            self.norm_layers_2.append(LayerNorm(hidden_channels))
+
+    def forward(self, x, x_mask):
+        attn_mask = x_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
+        x = x * x_mask
+        for i in range(self.n_layers):
+            y = self.attn_layers[i](x, x, attn_mask)
+            y = self.drop(y)
+            x = self.norm_layers_1[i](x + y)
+
+            y = self.ffn_layers[i](x, x_mask)
+            y = self.drop(y)
+            x = self.norm_layers_2[i](x + y)
+        x = x * x_mask
+        return x
+
+
+class Decoder(nn.Module):
+    def __init__(
+        self,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size=1,
+        p_dropout=0.0,
+        proximal_bias=False,
+        proximal_init=True,
+        **kwargs
+    ):
+        super().__init__()
+        self.hidden_channels = hidden_channels
+        self.filter_channels = filter_channels
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.proximal_bias = proximal_bias
+        self.proximal_init = proximal_init
+
+        self.drop = nn.Dropout(p_dropout)
+        self.self_attn_layers = nn.ModuleList()
+        self.norm_layers_0 = nn.ModuleList()
+        self.encdec_attn_layers = nn.ModuleList()
+        self.norm_layers_1 = nn.ModuleList()
+        self.ffn_layers = nn.ModuleList()
+        self.norm_layers_2 = nn.ModuleList()
+        for i in range(self.n_layers):
+            self.self_attn_layers.append(
+                MultiHeadAttention(
+                    hidden_channels,
+                    hidden_channels,
+                    n_heads,
+                    p_dropout=p_dropout,
+                    proximal_bias=proximal_bias,
+                    proximal_init=proximal_init,
+                )
+            )
+            self.norm_layers_0.append(LayerNorm(hidden_channels))
+            self.encdec_attn_layers.append(
+                MultiHeadAttention(
+                    hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout
+                )
+            )
+            self.norm_layers_1.append(LayerNorm(hidden_channels))
+            self.ffn_layers.append(
+                FFN(
+                    hidden_channels,
+                    hidden_channels,
+                    filter_channels,
+                    kernel_size,
+                    p_dropout=p_dropout,
+                    causal=True,
+                )
+            )
+            self.norm_layers_2.append(LayerNorm(hidden_channels))
+
+    def forward(self, x, x_mask, h, h_mask):
+        """
+        x: decoder input
+        h: encoder output
+        """
+        self_attn_mask = commons.subsequent_mask(x_mask.size(2)).to(
+            device=x.device, dtype=x.dtype
+        )
+        encdec_attn_mask = h_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
+        x = x * x_mask
+        for i in range(self.n_layers):
+            y = self.self_attn_layers[i](x, x, self_attn_mask)
+            y = self.drop(y)
+            x = self.norm_layers_0[i](x + y)
+
+            y = self.encdec_attn_layers[i](x, h, encdec_attn_mask)
+            y = self.drop(y)
+            x = self.norm_layers_1[i](x + y)
+
+            y = self.ffn_layers[i](x, x_mask)
+            y = self.drop(y)
+            x = self.norm_layers_2[i](x + y)
+        x = x * x_mask
+        return x
+
+
+class MultiHeadAttention(nn.Module):
+    def __init__(
+        self,
+        channels,
+        out_channels,
+        n_heads,
+        p_dropout=0.0,
+        window_size=None,
+        heads_share=True,
+        block_length=None,
+        proximal_bias=False,
+        proximal_init=False,
+    ):
+        super().__init__()
+        assert channels % n_heads == 0
+
+        self.channels = channels
+        self.out_channels = out_channels
+        self.n_heads = n_heads
+        self.p_dropout = p_dropout
+        self.window_size = window_size
+        self.heads_share = heads_share
+        self.block_length = block_length
+        self.proximal_bias = proximal_bias
+        self.proximal_init = proximal_init
+        self.attn = None
+
+        self.k_channels = channels // n_heads
+        self.conv_q = nn.Conv1d(channels, channels, 1)
+        self.conv_k = nn.Conv1d(channels, channels, 1)
+        self.conv_v = nn.Conv1d(channels, channels, 1)
+        self.conv_o = nn.Conv1d(channels, out_channels, 1)
+        self.drop = nn.Dropout(p_dropout)
+
+        if window_size is not None:
+            n_heads_rel = 1 if heads_share else n_heads
+            rel_stddev = self.k_channels**-0.5
+            self.emb_rel_k = nn.Parameter(
+                torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
+                * rel_stddev
+            )
+            self.emb_rel_v = nn.Parameter(
+                torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
+                * rel_stddev
+            )
+
+        nn.init.xavier_uniform_(self.conv_q.weight)
+        nn.init.xavier_uniform_(self.conv_k.weight)
+        nn.init.xavier_uniform_(self.conv_v.weight)
+        if proximal_init:
+            with torch.no_grad():
+                self.conv_k.weight.copy_(self.conv_q.weight)
+                self.conv_k.bias.copy_(self.conv_q.bias)
+
+    def forward(self, x, c, attn_mask=None):
+        q = self.conv_q(x)
+        k = self.conv_k(c)
+        v = self.conv_v(c)
+
+        x, self.attn = self.attention(q, k, v, mask=attn_mask)
+
+        x = self.conv_o(x)
+        return x
+
+    def attention(self, query, key, value, mask=None):
+        b, d, t_s, t_t = (*key.size(), query.size(2))
+        query = query.view(b, self.n_heads, self.k_channels, t_t).transpose(2, 3)
+        key = key.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
+        value = value.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
+
+        scores = torch.matmul(query / math.sqrt(self.k_channels), key.transpose(-2, -1))
+        if self.window_size is not None:
+            assert (
+                t_s == t_t
+            ), "Relative attention is only available for self-attention."
+            key_relative_embeddings = self._get_relative_embeddings(self.emb_rel_k, t_s)
+            rel_logits = self._matmul_with_relative_keys(
+                query / math.sqrt(self.k_channels), key_relative_embeddings
+            )
+            scores_local = self._relative_position_to_absolute_position(rel_logits)
+            scores = scores + scores_local
+        if self.proximal_bias:
+            assert t_s == t_t, "Proximal bias is only available for self-attention."
+            scores = scores + self._attention_bias_proximal(t_s).to(
+                device=scores.device, dtype=scores.dtype
+            )
+        if mask is not None:
+            scores = scores.masked_fill(mask == 0, -1e4)
+            if self.block_length is not None:
+                assert (
+                    t_s == t_t
+                ), "Local attention is only available for self-attention."
+                block_mask = (
+                    torch.ones_like(scores)
+                    .triu(-self.block_length)
+                    .tril(self.block_length)
+                )
+                scores = scores.masked_fill(block_mask == 0, -1e4)
+        p_attn = F.softmax(scores, dim=-1)
+        p_attn = self.drop(p_attn)
+        output = torch.matmul(p_attn, value)
+        if self.window_size is not None:
+            relative_weights = self._absolute_position_to_relative_position(p_attn)
+            value_relative_embeddings = self._get_relative_embeddings(
+                self.emb_rel_v, t_s
+            )
+            output = output + self._matmul_with_relative_values(
+                relative_weights, value_relative_embeddings
+            )
+        output = output.transpose(2, 3).contiguous().view(b, d, t_t)
+        return output, p_attn
+
+    def _matmul_with_relative_values(self, x, y):
+        """
+        x: [b, h, l, m]
+        y: [h or 1, m, d]
+        ret: [b, h, l, d]
+        """
+        ret = torch.matmul(x, y.unsqueeze(0))
+        return ret
+
+    def _matmul_with_relative_keys(self, x, y):
+        """
+        x: [b, h, l, d]
+        y: [h or 1, m, d]
+        ret: [b, h, l, m]
+        """
+        ret = torch.matmul(x, y.unsqueeze(0).transpose(-2, -1))
+        return ret
+
+    def _get_relative_embeddings(self, relative_embeddings, length):
+        pad_length = max(length - (self.window_size + 1), 0)
+        slice_start_position = max((self.window_size + 1) - length, 0)
+        slice_end_position = slice_start_position + 2 * length - 1
+        if pad_length > 0:
+            padded_relative_embeddings = F.pad(
+                relative_embeddings,
+                commons.convert_pad_shape([[0, 0], [pad_length, pad_length], [0, 0]]),
+            )
+        else:
+            padded_relative_embeddings = relative_embeddings
+        used_relative_embeddings = padded_relative_embeddings[
+            :, slice_start_position:slice_end_position
+        ]
+        return used_relative_embeddings
+
+    def _relative_position_to_absolute_position(self, x):
+        """
+        x: [b, h, l, 2*l-1]
+        ret: [b, h, l, l]
+        """
+        batch, heads, length, _ = x.size()
+
+        x = F.pad(x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, 1]]))
+        x_flat = x.view([batch, heads, length * 2 * length])
+        x_flat = F.pad(
+            x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [0, length - 1]])
+        )
+
+        x_final = x_flat.view([batch, heads, length + 1, 2 * length - 1])[
+            :, :, :length, length - 1 :
+        ]
+        return x_final
+
+    def _absolute_position_to_relative_position(self, x):
+        """
+        x: [b, h, l, l]
+        ret: [b, h, l, 2*l-1]
+        """
+        batch, heads, length, _ = x.size()
+        x = F.pad(
+            x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, length - 1]])
+        )
+        x_flat = x.view([batch, heads, length**2 + length * (length - 1)])
+        x_flat = F.pad(x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [length, 0]]))
+        x_final = x_flat.view([batch, heads, length, 2 * length])[:, :, :, 1:]
+        return x_final
+
+    def _attention_bias_proximal(self, length):
+        r = torch.arange(length, dtype=torch.float32)
+        diff = torch.unsqueeze(r, 0) - torch.unsqueeze(r, 1)
+        return torch.unsqueeze(torch.unsqueeze(-torch.log1p(torch.abs(diff)), 0), 0)
+
+
+class FFN(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        out_channels,
+        filter_channels,
+        kernel_size,
+        p_dropout=0.0,
+        activation=None,
+        causal=False,
+    ):
+        super().__init__()
+        self.in_channels = in_channels
+        self.out_channels = out_channels
+        self.filter_channels = filter_channels
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.activation = activation
+        self.causal = causal
+
+        if causal:
+            self.padding = self._causal_padding
+        else:
+            self.padding = self._same_padding
+
+        self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size)
+        self.conv_2 = nn.Conv1d(filter_channels, out_channels, kernel_size)
+        self.drop = nn.Dropout(p_dropout)
+
+    def forward(self, x, x_mask):
+        x = self.conv_1(self.padding(x * x_mask))
+        if self.activation == "gelu":
+            x = x * torch.sigmoid(1.702 * x)
+        else:
+            x = torch.relu(x)
+        x = self.drop(x)
+        x = self.conv_2(self.padding(x * x_mask))
+        return x * x_mask
+
+    def _causal_padding(self, x):
+        if self.kernel_size == 1:
+            return x
+        pad_l = self.kernel_size - 1
+        pad_r = 0
+        padding = [[0, 0], [0, 0], [pad_l, pad_r]]
+        x = F.pad(x, commons.convert_pad_shape(padding))
+        return x
+
+    def _same_padding(self, x):
+        if self.kernel_size == 1:
+            return x
+        pad_l = (self.kernel_size - 1) // 2
+        pad_r = self.kernel_size // 2
+        padding = [[0, 0], [0, 0], [pad_l, pad_r]]
+        x = F.pad(x, commons.convert_pad_shape(padding))
+        return x

system/tts_engines/rvc/lib/infer_pack/commons.py

@@ -0,0 +1,166 @@
+import math
+import numpy as np
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+
+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)
+
+
+def convert_pad_shape(pad_shape):
+    l = pad_shape[::-1]
+    pad_shape = [item for sublist in l for item in sublist]
+    return pad_shape
+
+
+def kl_divergence(m_p, logs_p, m_q, logs_q):
+    """KL(P||Q)"""
+    kl = (logs_q - logs_p) - 0.5
+    kl += (
+        0.5 * (torch.exp(2.0 * logs_p) + ((m_p - m_q) ** 2)) * torch.exp(-2.0 * logs_q)
+    )
+    return kl
+
+
+def rand_gumbel(shape):
+    """Sample from the Gumbel distribution, protect from overflows."""
+    uniform_samples = torch.rand(shape) * 0.99998 + 0.00001
+    return -torch.log(-torch.log(uniform_samples))
+
+
+def rand_gumbel_like(x):
+    g = rand_gumbel(x.size()).to(dtype=x.dtype, device=x.device)
+    return g
+
+
+def slice_segments(x, ids_str, segment_size=4):
+    ret = torch.zeros_like(x[:, :, :segment_size])
+    for i in range(x.size(0)):
+        idx_str = ids_str[i]
+        idx_end = idx_str + segment_size
+        ret[i] = x[i, :, idx_str:idx_end]
+    return ret
+
+
+def slice_segments2(x, ids_str, segment_size=4):
+    ret = torch.zeros_like(x[:, :segment_size])
+    for i in range(x.size(0)):
+        idx_str = ids_str[i]
+        idx_end = idx_str + segment_size
+        ret[i] = x[i, idx_str:idx_end]
+    return ret
+
+
+def rand_slice_segments(x, x_lengths=None, segment_size=4):
+    b, d, t = x.size()
+    if x_lengths is None:
+        x_lengths = t
+    ids_str_max = x_lengths - segment_size + 1
+    ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
+    ret = slice_segments(x, ids_str, segment_size)
+    return ret, ids_str
+
+
+def get_timing_signal_1d(length, channels, min_timescale=1.0, max_timescale=1.0e4):
+    position = torch.arange(length, dtype=torch.float)
+    num_timescales = channels // 2
+    log_timescale_increment = math.log(float(max_timescale) / float(min_timescale)) / (
+        num_timescales - 1
+    )
+    inv_timescales = min_timescale * torch.exp(
+        torch.arange(num_timescales, dtype=torch.float) * -log_timescale_increment
+    )
+    scaled_time = position.unsqueeze(0) * inv_timescales.unsqueeze(1)
+    signal = torch.cat([torch.sin(scaled_time), torch.cos(scaled_time)], 0)
+    signal = F.pad(signal, [0, 0, 0, channels % 2])
+    signal = signal.view(1, channels, length)
+    return signal
+
+
+def add_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4):
+    b, channels, length = x.size()
+    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
+    return x + signal.to(dtype=x.dtype, device=x.device)
+
+
+def cat_timing_signal_1d(x, min_timescale=1.0, max_timescale=1.0e4, axis=1):
+    b, channels, length = x.size()
+    signal = get_timing_signal_1d(length, channels, min_timescale, max_timescale)
+    return torch.cat([x, signal.to(dtype=x.dtype, device=x.device)], axis)
+
+
+def subsequent_mask(length):
+    mask = torch.tril(torch.ones(length, length)).unsqueeze(0).unsqueeze(0)
+    return mask
+
+
+@torch.jit.script
+def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
+    n_channels_int = n_channels[0]
+    in_act = input_a + input_b
+    t_act = torch.tanh(in_act[:, :n_channels_int, :])
+    s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
+    acts = t_act * s_act
+    return acts
+
+
+def convert_pad_shape(pad_shape):
+    l = pad_shape[::-1]
+    pad_shape = [item for sublist in l for item in sublist]
+    return pad_shape
+
+
+def shift_1d(x):
+    x = F.pad(x, convert_pad_shape([[0, 0], [0, 0], [1, 0]]))[:, :, :-1]
+    return x
+
+
+def sequence_mask(length, max_length=None):
+    if max_length is None:
+        max_length = length.max()
+    x = torch.arange(max_length, dtype=length.dtype, device=length.device)
+    return x.unsqueeze(0) < length.unsqueeze(1)
+
+
+def generate_path(duration, mask):
+    """
+    duration: [b, 1, t_x]
+    mask: [b, 1, t_y, t_x]
+    """
+    device = duration.device
+
+    b, _, t_y, t_x = mask.shape
+    cum_duration = torch.cumsum(duration, -1)
+
+    cum_duration_flat = cum_duration.view(b * t_x)
+    path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype)
+    path = path.view(b, t_x, t_y)
+    path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1]
+    path = path.unsqueeze(1).transpose(2, 3) * mask
+    return path
+
+
+def clip_grad_value_(parameters, clip_value, norm_type=2):
+    if isinstance(parameters, torch.Tensor):
+        parameters = [parameters]
+    parameters = list(filter(lambda p: p.grad is not None, parameters))
+    norm_type = float(norm_type)
+    if clip_value is not None:
+        clip_value = float(clip_value)
+
+    total_norm = 0
+    for p in parameters:
+        param_norm = p.grad.data.norm(norm_type)
+        total_norm += param_norm.item() ** norm_type
+        if clip_value is not None:
+            p.grad.data.clamp_(min=-clip_value, max=clip_value)
+    total_norm = total_norm ** (1.0 / norm_type)
+    return total_norm

system/tts_engines/rvc/lib/infer_pack/modules.py

@@ -0,0 +1,517 @@
+import math
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from torch.nn import Conv1d
+from torch.nn.utils import remove_weight_norm
+from torch.nn.utils.parametrizations import weight_norm  # Updated import
+
+from . import commons
+from .commons import init_weights, get_padding
+from .transforms import piecewise_rational_quadratic_transform
+
+
+LRELU_SLOPE = 0.1
+
+
+class LayerNorm(nn.Module):
+    def __init__(self, channels, eps=1e-5):
+        super().__init__()
+        self.channels = channels
+        self.eps = eps
+
+        self.gamma = nn.Parameter(torch.ones(channels))
+        self.beta = nn.Parameter(torch.zeros(channels))
+
+    def forward(self, x):
+        x = x.transpose(1, -1)
+        x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps)
+        return x.transpose(1, -1)
+
+
+class ConvReluNorm(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        hidden_channels,
+        out_channels,
+        kernel_size,
+        n_layers,
+        p_dropout,
+    ):
+        super().__init__()
+        self.in_channels = in_channels
+        self.hidden_channels = hidden_channels
+        self.out_channels = out_channels
+        self.kernel_size = kernel_size
+        self.n_layers = n_layers
+        self.p_dropout = p_dropout
+        assert n_layers > 1, "Number of layers should be larger than 0."
+
+        self.conv_layers = nn.ModuleList()
+        self.norm_layers = nn.ModuleList()
+        self.conv_layers.append(
+            nn.Conv1d(
+                in_channels, hidden_channels, kernel_size, padding=kernel_size // 2
+            )
+        )
+        self.norm_layers.append(LayerNorm(hidden_channels))
+        self.relu_drop = nn.Sequential(nn.ReLU(), nn.Dropout(p_dropout))
+        for _ in range(n_layers - 1):
+            self.conv_layers.append(
+                nn.Conv1d(
+                    hidden_channels,
+                    hidden_channels,
+                    kernel_size,
+                    padding=kernel_size // 2,
+                )
+            )
+            self.norm_layers.append(LayerNorm(hidden_channels))
+        self.proj = nn.Conv1d(hidden_channels, out_channels, 1)
+        self.proj.weight.data.zero_()
+        self.proj.bias.data.zero_()
+
+    def forward(self, x, x_mask):
+        x_org = x
+        for i in range(self.n_layers):
+            x = self.conv_layers[i](x * x_mask)
+            x = self.norm_layers[i](x)
+            x = self.relu_drop(x)
+        x = x_org + self.proj(x)
+        return x * x_mask
+
+
+class DDSConv(nn.Module):
+    def __init__(self, channels, kernel_size, n_layers, p_dropout=0.0):
+        super().__init__()
+        self.channels = channels
+        self.kernel_size = kernel_size
+        self.n_layers = n_layers
+        self.p_dropout = p_dropout
+
+        self.drop = nn.Dropout(p_dropout)
+        self.convs_sep = nn.ModuleList()
+        self.convs_1x1 = nn.ModuleList()
+        self.norms_1 = nn.ModuleList()
+        self.norms_2 = nn.ModuleList()
+        for i in range(n_layers):
+            dilation = kernel_size**i
+            padding = (kernel_size * dilation - dilation) // 2
+            self.convs_sep.append(
+                nn.Conv1d(
+                    channels,
+                    channels,
+                    kernel_size,
+                    groups=channels,
+                    dilation=dilation,
+                    padding=padding,
+                )
+            )
+            self.convs_1x1.append(nn.Conv1d(channels, channels, 1))
+            self.norms_1.append(LayerNorm(channels))
+            self.norms_2.append(LayerNorm(channels))
+
+    def forward(self, x, x_mask, g=None):
+        if g is not None:
+            x = x + g
+        for i in range(self.n_layers):
+            y = self.convs_sep[i](x * x_mask)
+            y = self.norms_1[i](y)
+            y = F.gelu(y)
+            y = self.convs_1x1[i](y)
+            y = self.norms_2[i](y)
+            y = F.gelu(y)
+            y = self.drop(y)
+            x = x + y
+        return x * x_mask
+
+
+class WN(torch.nn.Module):
+    def __init__(
+        self,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        gin_channels=0,
+        p_dropout=0,
+    ):
+        super(WN, self).__init__()
+        assert kernel_size % 2 == 1
+        self.hidden_channels = hidden_channels
+        self.kernel_size = (kernel_size,)
+        self.dilation_rate = dilation_rate
+        self.n_layers = n_layers
+        self.gin_channels = gin_channels
+        self.p_dropout = p_dropout
+
+        self.in_layers = torch.nn.ModuleList()
+        self.res_skip_layers = torch.nn.ModuleList()
+        self.drop = nn.Dropout(p_dropout)
+
+        if gin_channels != 0:
+            cond_layer = torch.nn.Conv1d(
+                gin_channels, 2 * hidden_channels * n_layers, 1
+            )
+            #self.cond_layer = torch.nn.utils.parametrizations.weight_norm(cond_layer, name="weight")
+            self.cond_layer = weight_norm(cond_layer, name="weight")  # Updated to use the new import
+
+        for i in range(n_layers):
+            dilation = dilation_rate**i
+            padding = int((kernel_size * dilation - dilation) / 2)
+            in_layer = torch.nn.Conv1d(
+                hidden_channels,
+                2 * hidden_channels,
+                kernel_size,
+                dilation=dilation,
+                padding=padding,
+            )
+            #in_layer = torch.nn.utils.parametrizations.weight_norm(in_layer, name="weight")
+            in_layer = weight_norm(in_layer, name="weight")  # Updated to use the new impor
+            self.in_layers.append(in_layer)
+            if i < n_layers - 1:
+                res_skip_channels = 2 * hidden_channels
+            else:
+                res_skip_channels = hidden_channels
+
+            res_skip_layer = torch.nn.Conv1d(hidden_channels, res_skip_channels, 1)
+            #res_skip_layer = torch.nn.utils.parametrizations.weight_norm(res_skip_layer, name="weight")
+            res_skip_layer = weight_norm(res_skip_layer, name="weight")  # Updated to use the new import
+            self.res_skip_layers.append(res_skip_layer)
+
+    def forward(self, x, x_mask, g=None, **kwargs):
+        output = torch.zeros_like(x)
+        n_channels_tensor = torch.IntTensor([self.hidden_channels])
+
+        if g is not None:
+            g = self.cond_layer(g)
+
+        for i in range(self.n_layers):
+            x_in = self.in_layers[i](x)
+            if g is not None:
+                cond_offset = i * 2 * self.hidden_channels
+                g_l = g[:, cond_offset : cond_offset + 2 * self.hidden_channels, :]
+            else:
+                g_l = torch.zeros_like(x_in)
+
+            acts = commons.fused_add_tanh_sigmoid_multiply(x_in, g_l, n_channels_tensor)
+            acts = self.drop(acts)
+
+            res_skip_acts = self.res_skip_layers[i](acts)
+            if i < self.n_layers - 1:
+                res_acts = res_skip_acts[:, : self.hidden_channels, :]
+                x = (x + res_acts) * x_mask
+                output = output + res_skip_acts[:, self.hidden_channels :, :]
+            else:
+                output = output + res_skip_acts
+        return output * x_mask
+
+    def remove_weight_norm(self):
+        if self.gin_channels != 0:
+            torch.nn.utils.remove_weight_norm(self.cond_layer)
+        for l in self.in_layers:
+            torch.nn.utils.remove_weight_norm(l)
+        for l in self.res_skip_layers:
+            torch.nn.utils.remove_weight_norm(l)
+
+
+class ResBlock1(torch.nn.Module):
+    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
+        super(ResBlock1, self).__init__()
+        self.convs1 = nn.ModuleList(
+            [
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=dilation[0],
+                        padding=get_padding(kernel_size, dilation[0]),
+                    )
+                ),
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=dilation[1],
+                        padding=get_padding(kernel_size, dilation[1]),
+                    )
+                ),
+                weight_norm(
+                    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(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=1,
+                        padding=get_padding(kernel_size, 1),
+                    )
+                ),
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=1,
+                        padding=get_padding(kernel_size, 1),
+                    )
+                ),
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=1,
+                        padding=get_padding(kernel_size, 1),
+                    )
+                ),
+            ]
+        )
+        self.convs2.apply(init_weights)
+
+    def forward(self, x, x_mask=None):
+        for c1, c2 in zip(self.convs1, self.convs2):
+            xt = F.leaky_relu(x, LRELU_SLOPE)
+            if x_mask is not None:
+                xt = xt * x_mask
+            xt = c1(xt)
+            xt = F.leaky_relu(xt, LRELU_SLOPE)
+            if x_mask is not None:
+                xt = xt * x_mask
+            xt = c2(xt)
+            x = xt + x
+        if x_mask is not None:
+            x = x * x_mask
+        return x
+
+    def remove_weight_norm(self):
+        for l in self.convs1:
+            remove_weight_norm(l)
+        for l in self.convs2:
+            remove_weight_norm(l)
+
+
+class ResBlock2(torch.nn.Module):
+    def __init__(self, channels, kernel_size=3, dilation=(1, 3)):
+        super(ResBlock2, self).__init__()
+        self.convs = nn.ModuleList(
+            [
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=dilation[0],
+                        padding=get_padding(kernel_size, dilation[0]),
+                    )
+                ),
+                weight_norm(
+                    Conv1d(
+                        channels,
+                        channels,
+                        kernel_size,
+                        1,
+                        dilation=dilation[1],
+                        padding=get_padding(kernel_size, dilation[1]),
+                    )
+                ),
+            ]
+        )
+        self.convs.apply(init_weights)
+
+    def forward(self, x, x_mask=None):
+        for c in self.convs:
+            xt = F.leaky_relu(x, LRELU_SLOPE)
+            if x_mask is not None:
+                xt = xt * x_mask
+            xt = c(xt)
+            x = xt + x
+        if x_mask is not None:
+            x = x * x_mask
+        return x
+
+    def remove_weight_norm(self):
+        for l in self.convs:
+            remove_weight_norm(l)
+
+
+class Log(nn.Module):
+    def forward(self, x, x_mask, reverse=False, **kwargs):
+        if not reverse:
+            y = torch.log(torch.clamp_min(x, 1e-5)) * x_mask
+            logdet = torch.sum(-y, [1, 2])
+            return y, logdet
+        else:
+            x = torch.exp(x) * x_mask
+            return x
+
+
+class Flip(nn.Module):
+    def forward(self, x, *args, reverse=False, **kwargs):
+        x = torch.flip(x, [1])
+        if not reverse:
+            logdet = torch.zeros(x.size(0)).to(dtype=x.dtype, device=x.device)
+            return x, logdet
+        else:
+            return x
+
+
+class ElementwiseAffine(nn.Module):
+    def __init__(self, channels):
+        super().__init__()
+        self.channels = channels
+        self.m = nn.Parameter(torch.zeros(channels, 1))
+        self.logs = nn.Parameter(torch.zeros(channels, 1))
+
+    def forward(self, x, x_mask, reverse=False, **kwargs):
+        if not reverse:
+            y = self.m + torch.exp(self.logs) * x
+            y = y * x_mask
+            logdet = torch.sum(self.logs * x_mask, [1, 2])
+            return y, logdet
+        else:
+            x = (x - self.m) * torch.exp(-self.logs) * x_mask
+            return x
+
+
+class ResidualCouplingLayer(nn.Module):
+    def __init__(
+        self,
+        channels,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        p_dropout=0,
+        gin_channels=0,
+        mean_only=False,
+    ):
+        assert channels % 2 == 0, "channels should be divisible by 2"
+        super().__init__()
+        self.channels = channels
+        self.hidden_channels = hidden_channels
+        self.kernel_size = kernel_size
+        self.dilation_rate = dilation_rate
+        self.n_layers = n_layers
+        self.half_channels = channels // 2
+        self.mean_only = mean_only
+
+        self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
+        self.enc = WN(
+            hidden_channels,
+            kernel_size,
+            dilation_rate,
+            n_layers,
+            p_dropout=p_dropout,
+            gin_channels=gin_channels,
+        )
+        self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
+        self.post.weight.data.zero_()
+        self.post.bias.data.zero_()
+
+    def forward(self, x, x_mask, g=None, reverse=False):
+        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
+        h = self.pre(x0) * x_mask
+        h = self.enc(h, x_mask, g=g)
+        stats = self.post(h) * x_mask
+        if not self.mean_only:
+            m, logs = torch.split(stats, [self.half_channels] * 2, 1)
+        else:
+            m = stats
+            logs = torch.zeros_like(m)
+
+        if not reverse:
+            x1 = m + x1 * torch.exp(logs) * x_mask
+            x = torch.cat([x0, x1], 1)
+            logdet = torch.sum(logs, [1, 2])
+            return x, logdet
+        else:
+            x1 = (x1 - m) * torch.exp(-logs) * x_mask
+            x = torch.cat([x0, x1], 1)
+            return x
+
+    def remove_weight_norm(self):
+        self.enc.remove_weight_norm()
+
+
+class ConvFlow(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        filter_channels,
+        kernel_size,
+        n_layers,
+        num_bins=10,
+        tail_bound=5.0,
+    ):
+        super().__init__()
+        self.in_channels = in_channels
+        self.filter_channels = filter_channels
+        self.kernel_size = kernel_size
+        self.n_layers = n_layers
+        self.num_bins = num_bins
+        self.tail_bound = tail_bound
+        self.half_channels = in_channels // 2
+
+        self.pre = nn.Conv1d(self.half_channels, filter_channels, 1)
+        self.convs = DDSConv(filter_channels, kernel_size, n_layers, p_dropout=0.0)
+        self.proj = nn.Conv1d(
+            filter_channels, self.half_channels * (num_bins * 3 - 1), 1
+        )
+        self.proj.weight.data.zero_()
+        self.proj.bias.data.zero_()
+
+    def forward(self, x, x_mask, g=None, reverse=False):
+        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
+        h = self.pre(x0)
+        h = self.convs(h, x_mask, g=g)
+        h = self.proj(h) * x_mask
+
+        b, c, t = x0.shape
+        h = h.reshape(b, c, -1, t).permute(0, 1, 3, 2)
+
+        unnormalized_widths = h[..., : self.num_bins] / math.sqrt(self.filter_channels)
+        unnormalized_heights = h[..., self.num_bins : 2 * self.num_bins] / math.sqrt(
+            self.filter_channels
+        )
+        unnormalized_derivatives = h[..., 2 * self.num_bins :]
+
+        x1, logabsdet = piecewise_rational_quadratic_transform(
+            x1,
+            unnormalized_widths,
+            unnormalized_heights,
+            unnormalized_derivatives,
+            inverse=reverse,
+            tails="linear",
+            tail_bound=self.tail_bound,
+        )
+
+        x = torch.cat([x0, x1], 1) * x_mask
+        logdet = torch.sum(logabsdet * x_mask, [1, 2])
+        if not reverse:
+            return x, logdet
+        else:
+            return x

system/tts_engines/rvc/lib/infer_pack/modules/F0Predictor/DioF0Predictor.py

@@ -0,0 +1,86 @@
+from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
+import pyworld
+import numpy as np
+
+
+class DioF0Predictor(F0Predictor):
+    def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
+        self.hop_length = hop_length
+        self.f0_min = f0_min
+        self.f0_max = f0_max
+        self.sampling_rate = sampling_rate
+
+    def interpolate_f0(self, f0):
+        data = np.reshape(f0, (f0.size, 1))
+
+        vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
+        vuv_vector[data > 0.0] = 1.0
+        vuv_vector[data <= 0.0] = 0.0
+
+        ip_data = data
+
+        frame_number = data.size
+        last_value = 0.0
+        for i in range(frame_number):
+            if data[i] <= 0.0:
+                j = i + 1
+                for j in range(i + 1, frame_number):
+                    if data[j] > 0.0:
+                        break
+                if j < frame_number - 1:
+                    if last_value > 0.0:
+                        step = (data[j] - data[i - 1]) / float(j - i)
+                        for k in range(i, j):
+                            ip_data[k] = data[i - 1] + step * (k - i + 1)
+                    else:
+                        for k in range(i, j):
+                            ip_data[k] = data[j]
+                else:
+                    for k in range(i, frame_number):
+                        ip_data[k] = last_value
+            else:
+                ip_data[i] = data[i]  # 这里可能存在一个没有必要的拷贝
+                last_value = data[i]
+
+        return ip_data[:, 0], vuv_vector[:, 0]
+
+    def resize_f0(self, x, target_len):
+        source = np.array(x)
+        source[source < 0.001] = np.nan
+        target = np.interp(
+            np.arange(0, len(source) * target_len, len(source)) / target_len,
+            np.arange(0, len(source)),
+            source,
+        )
+        res = np.nan_to_num(target)
+        return res
+
+    def compute_f0(self, wav, p_len=None):
+        if p_len is None:
+            p_len = wav.shape[0] // self.hop_length
+        f0, t = pyworld.dio(
+            wav.astype(np.double),
+            fs=self.sampling_rate,
+            f0_floor=self.f0_min,
+            f0_ceil=self.f0_max,
+            frame_period=1000 * self.hop_length / self.sampling_rate,
+        )
+        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
+        for index, pitch in enumerate(f0):
+            f0[index] = round(pitch, 1)
+        return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
+
+    def compute_f0_uv(self, wav, p_len=None):
+        if p_len is None:
+            p_len = wav.shape[0] // self.hop_length
+        f0, t = pyworld.dio(
+            wav.astype(np.double),
+            fs=self.sampling_rate,
+            f0_floor=self.f0_min,
+            f0_ceil=self.f0_max,
+            frame_period=1000 * self.hop_length / self.sampling_rate,
+        )
+        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
+        for index, pitch in enumerate(f0):
+            f0[index] = round(pitch, 1)
+        return self.interpolate_f0(self.resize_f0(f0, p_len))

system/tts_engines/rvc/lib/infer_pack/modules/F0Predictor/F0Predictor.py

@@ -0,0 +1,6 @@
+class F0Predictor(object):
+    def compute_f0(self, wav, p_len):
+        pass
+
+    def compute_f0_uv(self, wav, p_len):
+        pass

system/tts_engines/rvc/lib/infer_pack/modules/F0Predictor/HarvestF0Predictor.py

@@ -0,0 +1,82 @@
+from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
+import pyworld
+import numpy as np
+
+
+class HarvestF0Predictor(F0Predictor):
+    def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
+        self.hop_length = hop_length
+        self.f0_min = f0_min
+        self.f0_max = f0_max
+        self.sampling_rate = sampling_rate
+
+    def interpolate_f0(self, f0):
+        data = np.reshape(f0, (f0.size, 1))
+
+        vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
+        vuv_vector[data > 0.0] = 1.0
+        vuv_vector[data <= 0.0] = 0.0
+
+        ip_data = data
+
+        frame_number = data.size
+        last_value = 0.0
+        for i in range(frame_number):
+            if data[i] <= 0.0:
+                j = i + 1
+                for j in range(i + 1, frame_number):
+                    if data[j] > 0.0:
+                        break
+                if j < frame_number - 1:
+                    if last_value > 0.0:
+                        step = (data[j] - data[i - 1]) / float(j - i)
+                        for k in range(i, j):
+                            ip_data[k] = data[i - 1] + step * (k - i + 1)
+                    else:
+                        for k in range(i, j):
+                            ip_data[k] = data[j]
+                else:
+                    for k in range(i, frame_number):
+                        ip_data[k] = last_value
+            else:
+                ip_data[i] = data[i]
+                last_value = data[i]
+
+        return ip_data[:, 0], vuv_vector[:, 0]
+
+    def resize_f0(self, x, target_len):
+        source = np.array(x)
+        source[source < 0.001] = np.nan
+        target = np.interp(
+            np.arange(0, len(source) * target_len, len(source)) / target_len,
+            np.arange(0, len(source)),
+            source,
+        )
+        res = np.nan_to_num(target)
+        return res
+
+    def compute_f0(self, wav, p_len=None):
+        if p_len is None:
+            p_len = wav.shape[0] // self.hop_length
+        f0, t = pyworld.harvest(
+            wav.astype(np.double),
+            fs=self.sampling_rate,
+            f0_ceil=self.f0_max,
+            f0_floor=self.f0_min,
+            frame_period=1000 * self.hop_length / self.sampling_rate,
+        )
+        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.fs)
+        return self.interpolate_f0(self.resize_f0(f0, p_len))[0]
+
+    def compute_f0_uv(self, wav, p_len=None):
+        if p_len is None:
+            p_len = wav.shape[0] // self.hop_length
+        f0, t = pyworld.harvest(
+            wav.astype(np.double),
+            fs=self.sampling_rate,
+            f0_floor=self.f0_min,
+            f0_ceil=self.f0_max,
+            frame_period=1000 * self.hop_length / self.sampling_rate,
+        )
+        f0 = pyworld.stonemask(wav.astype(np.double), f0, t, self.sampling_rate)
+        return self.interpolate_f0(self.resize_f0(f0, p_len))

system/tts_engines/rvc/lib/infer_pack/modules/F0Predictor/PMF0Predictor.py

@@ -0,0 +1,93 @@
+from infer_pack.modules.F0Predictor.F0Predictor import F0Predictor
+import parselmouth
+import numpy as np
+
+
+class PMF0Predictor(F0Predictor):
+    def __init__(self, hop_length=512, f0_min=50, f0_max=1100, sampling_rate=44100):
+        self.hop_length = hop_length
+        self.f0_min = f0_min
+        self.f0_max = f0_max
+        self.sampling_rate = sampling_rate
+
+    def interpolate_f0(self, f0):
+        data = np.reshape(f0, (f0.size, 1))
+
+        vuv_vector = np.zeros((data.size, 1), dtype=np.float32)
+        vuv_vector[data > 0.0] = 1.0
+        vuv_vector[data <= 0.0] = 0.0
+
+        ip_data = data
+
+        frame_number = data.size
+        last_value = 0.0
+        for i in range(frame_number):
+            if data[i] <= 0.0:
+                j = i + 1
+                for j in range(i + 1, frame_number):
+                    if data[j] > 0.0:
+                        break
+                if j < frame_number - 1:
+                    if last_value > 0.0:
+                        step = (data[j] - data[i - 1]) / float(j - i)
+                        for k in range(i, j):
+                            ip_data[k] = data[i - 1] + step * (k - i + 1)
+                    else:
+                        for k in range(i, j):
+                            ip_data[k] = data[j]
+                else:
+                    for k in range(i, frame_number):
+                        ip_data[k] = last_value
+            else:
+                ip_data[i] = data[i]  # 这里可能存在一个没有必要的拷贝
+                last_value = data[i]
+
+        return ip_data[:, 0], vuv_vector[:, 0]
+
+    def compute_f0(self, wav, p_len=None):
+        x = wav
+        if p_len is None:
+            p_len = x.shape[0] // self.hop_length
+        else:
+            assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
+        time_step = self.hop_length / self.sampling_rate * 1000
+        f0 = (
+            parselmouth.Sound(x, self.sampling_rate)
+            .to_pitch_ac(
+                time_step=time_step / 1000,
+                voicing_threshold=0.6,
+                pitch_floor=self.f0_min,
+                pitch_ceiling=self.f0_max,
+            )
+            .selected_array["frequency"]
+        )
+
+        pad_size = (p_len - len(f0) + 1) // 2
+        if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+            f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
+        f0, uv = self.interpolate_f0(f0)
+        return f0
+
+    def compute_f0_uv(self, wav, p_len=None):
+        x = wav
+        if p_len is None:
+            p_len = x.shape[0] // self.hop_length
+        else:
+            assert abs(p_len - x.shape[0] // self.hop_length) < 4, "pad length error"
+        time_step = self.hop_length / self.sampling_rate * 1000
+        f0 = (
+            parselmouth.Sound(x, self.sampling_rate)
+            .to_pitch_ac(
+                time_step=time_step / 1000,
+                voicing_threshold=0.6,
+                pitch_floor=self.f0_min,
+                pitch_ceiling=self.f0_max,
+            )
+            .selected_array["frequency"]
+        )
+
+        pad_size = (p_len - len(f0) + 1) // 2
+        if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+            f0 = np.pad(f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant")
+        f0, uv = self.interpolate_f0(f0)
+        return f0, uv

system/tts_engines/rvc/lib/infer_pack/transforms.py

@@ -0,0 +1,209 @@
+import torch
+from torch.nn import functional as F
+
+import numpy as np
+
+
+DEFAULT_MIN_BIN_WIDTH = 1e-3
+DEFAULT_MIN_BIN_HEIGHT = 1e-3
+DEFAULT_MIN_DERIVATIVE = 1e-3
+
+
+def piecewise_rational_quadratic_transform(
+    inputs,
+    unnormalized_widths,
+    unnormalized_heights,
+    unnormalized_derivatives,
+    inverse=False,
+    tails=None,
+    tail_bound=1.0,
+    min_bin_width=DEFAULT_MIN_BIN_WIDTH,
+    min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
+    min_derivative=DEFAULT_MIN_DERIVATIVE,
+):
+    if tails is None:
+        spline_fn = rational_quadratic_spline
+        spline_kwargs = {}
+    else:
+        spline_fn = unconstrained_rational_quadratic_spline
+        spline_kwargs = {"tails": tails, "tail_bound": tail_bound}
+
+    outputs, logabsdet = spline_fn(
+        inputs=inputs,
+        unnormalized_widths=unnormalized_widths,
+        unnormalized_heights=unnormalized_heights,
+        unnormalized_derivatives=unnormalized_derivatives,
+        inverse=inverse,
+        min_bin_width=min_bin_width,
+        min_bin_height=min_bin_height,
+        min_derivative=min_derivative,
+        **spline_kwargs
+    )
+    return outputs, logabsdet
+
+
+def searchsorted(bin_locations, inputs, eps=1e-6):
+    bin_locations[..., -1] += eps
+    return torch.sum(inputs[..., None] >= bin_locations, dim=-1) - 1
+
+
+def unconstrained_rational_quadratic_spline(
+    inputs,
+    unnormalized_widths,
+    unnormalized_heights,
+    unnormalized_derivatives,
+    inverse=False,
+    tails="linear",
+    tail_bound=1.0,
+    min_bin_width=DEFAULT_MIN_BIN_WIDTH,
+    min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
+    min_derivative=DEFAULT_MIN_DERIVATIVE,
+):
+    inside_interval_mask = (inputs >= -tail_bound) & (inputs <= tail_bound)
+    outside_interval_mask = ~inside_interval_mask
+
+    outputs = torch.zeros_like(inputs)
+    logabsdet = torch.zeros_like(inputs)
+
+    if tails == "linear":
+        unnormalized_derivatives = F.pad(unnormalized_derivatives, pad=(1, 1))
+        constant = np.log(np.exp(1 - min_derivative) - 1)
+        unnormalized_derivatives[..., 0] = constant
+        unnormalized_derivatives[..., -1] = constant
+
+        outputs[outside_interval_mask] = inputs[outside_interval_mask]
+        logabsdet[outside_interval_mask] = 0
+    else:
+        raise RuntimeError("{} tails are not implemented.".format(tails))
+
+    (
+        outputs[inside_interval_mask],
+        logabsdet[inside_interval_mask],
+    ) = rational_quadratic_spline(
+        inputs=inputs[inside_interval_mask],
+        unnormalized_widths=unnormalized_widths[inside_interval_mask, :],
+        unnormalized_heights=unnormalized_heights[inside_interval_mask, :],
+        unnormalized_derivatives=unnormalized_derivatives[inside_interval_mask, :],
+        inverse=inverse,
+        left=-tail_bound,
+        right=tail_bound,
+        bottom=-tail_bound,
+        top=tail_bound,
+        min_bin_width=min_bin_width,
+        min_bin_height=min_bin_height,
+        min_derivative=min_derivative,
+    )
+
+    return outputs, logabsdet
+
+
+def rational_quadratic_spline(
+    inputs,
+    unnormalized_widths,
+    unnormalized_heights,
+    unnormalized_derivatives,
+    inverse=False,
+    left=0.0,
+    right=1.0,
+    bottom=0.0,
+    top=1.0,
+    min_bin_width=DEFAULT_MIN_BIN_WIDTH,
+    min_bin_height=DEFAULT_MIN_BIN_HEIGHT,
+    min_derivative=DEFAULT_MIN_DERIVATIVE,
+):
+    if torch.min(inputs) < left or torch.max(inputs) > right:
+        raise ValueError("Input to a transform is not within its domain")
+
+    num_bins = unnormalized_widths.shape[-1]
+
+    if min_bin_width * num_bins > 1.0:
+        raise ValueError("Minimal bin width too large for the number of bins")
+    if min_bin_height * num_bins > 1.0:
+        raise ValueError("Minimal bin height too large for the number of bins")
+
+    widths = F.softmax(unnormalized_widths, dim=-1)
+    widths = min_bin_width + (1 - min_bin_width * num_bins) * widths
+    cumwidths = torch.cumsum(widths, dim=-1)
+    cumwidths = F.pad(cumwidths, pad=(1, 0), mode="constant", value=0.0)
+    cumwidths = (right - left) * cumwidths + left
+    cumwidths[..., 0] = left
+    cumwidths[..., -1] = right
+    widths = cumwidths[..., 1:] - cumwidths[..., :-1]
+
+    derivatives = min_derivative + F.softplus(unnormalized_derivatives)
+
+    heights = F.softmax(unnormalized_heights, dim=-1)
+    heights = min_bin_height + (1 - min_bin_height * num_bins) * heights
+    cumheights = torch.cumsum(heights, dim=-1)
+    cumheights = F.pad(cumheights, pad=(1, 0), mode="constant", value=0.0)
+    cumheights = (top - bottom) * cumheights + bottom
+    cumheights[..., 0] = bottom
+    cumheights[..., -1] = top
+    heights = cumheights[..., 1:] - cumheights[..., :-1]
+
+    if inverse:
+        bin_idx = searchsorted(cumheights, inputs)[..., None]
+    else:
+        bin_idx = searchsorted(cumwidths, inputs)[..., None]
+
+    input_cumwidths = cumwidths.gather(-1, bin_idx)[..., 0]
+    input_bin_widths = widths.gather(-1, bin_idx)[..., 0]
+
+    input_cumheights = cumheights.gather(-1, bin_idx)[..., 0]
+    delta = heights / widths
+    input_delta = delta.gather(-1, bin_idx)[..., 0]
+
+    input_derivatives = derivatives.gather(-1, bin_idx)[..., 0]
+    input_derivatives_plus_one = derivatives[..., 1:].gather(-1, bin_idx)[..., 0]
+
+    input_heights = heights.gather(-1, bin_idx)[..., 0]
+
+    if inverse:
+        a = (inputs - input_cumheights) * (
+            input_derivatives + input_derivatives_plus_one - 2 * input_delta
+        ) + input_heights * (input_delta - input_derivatives)
+        b = input_heights * input_derivatives - (inputs - input_cumheights) * (
+            input_derivatives + input_derivatives_plus_one - 2 * input_delta
+        )
+        c = -input_delta * (inputs - input_cumheights)
+
+        discriminant = b.pow(2) - 4 * a * c
+        assert (discriminant >= 0).all()
+
+        root = (2 * c) / (-b - torch.sqrt(discriminant))
+        outputs = root * input_bin_widths + input_cumwidths
+
+        theta_one_minus_theta = root * (1 - root)
+        denominator = input_delta + (
+            (input_derivatives + input_derivatives_plus_one - 2 * input_delta)
+            * theta_one_minus_theta
+        )
+        derivative_numerator = input_delta.pow(2) * (
+            input_derivatives_plus_one * root.pow(2)
+            + 2 * input_delta * theta_one_minus_theta
+            + input_derivatives * (1 - root).pow(2)
+        )
+        logabsdet = torch.log(derivative_numerator) - 2 * torch.log(denominator)
+
+        return outputs, -logabsdet
+    else:
+        theta = (inputs - input_cumwidths) / input_bin_widths
+        theta_one_minus_theta = theta * (1 - theta)
+
+        numerator = input_heights * (
+            input_delta * theta.pow(2) + input_derivatives * theta_one_minus_theta
+        )
+        denominator = input_delta + (
+            (input_derivatives + input_derivatives_plus_one - 2 * input_delta)
+            * theta_one_minus_theta
+        )
+        outputs = input_cumheights + numerator / denominator
+
+        derivative_numerator = input_delta.pow(2) * (
+            input_derivatives_plus_one * theta.pow(2)
+            + 2 * input_delta * theta_one_minus_theta
+            + input_derivatives * (1 - theta).pow(2)
+        )
+        logabsdet = torch.log(derivative_numerator) - 2 * torch.log(denominator)
+
+        return outputs, logabsdet

system/tts_engines/rvc/lib/rmvpe.py

@@ -0,0 +1,390 @@
+import torch.nn as nn
+import torch, numpy as np
+import torch.nn.functional as F
+from librosa.filters import mel
+
+
+class BiGRU(nn.Module):
+    def __init__(self, input_features, hidden_features, num_layers):
+        super(BiGRU, self).__init__()
+        self.gru = nn.GRU(
+            input_features,
+            hidden_features,
+            num_layers=num_layers,
+            batch_first=True,
+            bidirectional=True,
+        )
+
+    def forward(self, x):
+        return self.gru(x)[0]
+
+
+class ConvBlockRes(nn.Module):
+    def __init__(self, in_channels, out_channels, momentum=0.01):
+        super(ConvBlockRes, self).__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(
+                in_channels=in_channels,
+                out_channels=out_channels,
+                kernel_size=(3, 3),
+                stride=(1, 1),
+                padding=(1, 1),
+                bias=False,
+            ),
+            nn.BatchNorm2d(out_channels, momentum=momentum),
+            nn.ReLU(),
+            nn.Conv2d(
+                in_channels=out_channels,
+                out_channels=out_channels,
+                kernel_size=(3, 3),
+                stride=(1, 1),
+                padding=(1, 1),
+                bias=False,
+            ),
+            nn.BatchNorm2d(out_channels, momentum=momentum),
+            nn.ReLU(),
+        )
+        if in_channels != out_channels:
+            self.shortcut = nn.Conv2d(in_channels, out_channels, (1, 1))
+            self.is_shortcut = True
+        else:
+            self.is_shortcut = False
+
+    def forward(self, x):
+        if self.is_shortcut:
+            return self.conv(x) + self.shortcut(x)
+        else:
+            return self.conv(x) + x
+
+
+class Encoder(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        in_size,
+        n_encoders,
+        kernel_size,
+        n_blocks,
+        out_channels=16,
+        momentum=0.01,
+    ):
+        super(Encoder, self).__init__()
+        self.n_encoders = n_encoders
+        self.bn = nn.BatchNorm2d(in_channels, momentum=momentum)
+        self.layers = nn.ModuleList()
+        self.latent_channels = []
+        for i in range(self.n_encoders):
+            self.layers.append(
+                ResEncoderBlock(
+                    in_channels, out_channels, kernel_size, n_blocks, momentum=momentum
+                )
+            )
+            self.latent_channels.append([out_channels, in_size])
+            in_channels = out_channels
+            out_channels *= 2
+            in_size //= 2
+        self.out_size = in_size
+        self.out_channel = out_channels
+
+    def forward(self, x):
+        concat_tensors = []
+        x = self.bn(x)
+        for i in range(self.n_encoders):
+            _, x = self.layers[i](x)
+            concat_tensors.append(_)
+        return x, concat_tensors
+
+
+class ResEncoderBlock(nn.Module):
+    def __init__(
+        self, in_channels, out_channels, kernel_size, n_blocks=1, momentum=0.01
+    ):
+        super(ResEncoderBlock, self).__init__()
+        self.n_blocks = n_blocks
+        self.conv = nn.ModuleList()
+        self.conv.append(ConvBlockRes(in_channels, out_channels, momentum))
+        for i in range(n_blocks - 1):
+            self.conv.append(ConvBlockRes(out_channels, out_channels, momentum))
+        self.kernel_size = kernel_size
+        if self.kernel_size is not None:
+            self.pool = nn.AvgPool2d(kernel_size=kernel_size)
+
+    def forward(self, x):
+        for i in range(self.n_blocks):
+            x = self.conv[i](x)
+        if self.kernel_size is not None:
+            return x, self.pool(x)
+        else:
+            return x
+
+
+class Intermediate(nn.Module):  #
+    def __init__(self, in_channels, out_channels, n_inters, n_blocks, momentum=0.01):
+        super(Intermediate, self).__init__()
+        self.n_inters = n_inters
+        self.layers = nn.ModuleList()
+        self.layers.append(
+            ResEncoderBlock(in_channels, out_channels, None, n_blocks, momentum)
+        )
+        for i in range(self.n_inters - 1):
+            self.layers.append(
+                ResEncoderBlock(out_channels, out_channels, None, n_blocks, momentum)
+            )
+
+    def forward(self, x):
+        for i in range(self.n_inters):
+            x = self.layers[i](x)
+        return x
+
+
+class ResDecoderBlock(nn.Module):
+    def __init__(self, in_channels, out_channels, stride, n_blocks=1, momentum=0.01):
+        super(ResDecoderBlock, self).__init__()
+        out_padding = (0, 1) if stride == (1, 2) else (1, 1)
+        self.n_blocks = n_blocks
+        self.conv1 = nn.Sequential(
+            nn.ConvTranspose2d(
+                in_channels=in_channels,
+                out_channels=out_channels,
+                kernel_size=(3, 3),
+                stride=stride,
+                padding=(1, 1),
+                output_padding=out_padding,
+                bias=False,
+            ),
+            nn.BatchNorm2d(out_channels, momentum=momentum),
+            nn.ReLU(),
+        )
+        self.conv2 = nn.ModuleList()
+        self.conv2.append(ConvBlockRes(out_channels * 2, out_channels, momentum))
+        for i in range(n_blocks - 1):
+            self.conv2.append(ConvBlockRes(out_channels, out_channels, momentum))
+
+    def forward(self, x, concat_tensor):
+        x = self.conv1(x)
+        x = torch.cat((x, concat_tensor), dim=1)
+        for i in range(self.n_blocks):
+            x = self.conv2[i](x)
+        return x
+
+
+class Decoder(nn.Module):
+    def __init__(self, in_channels, n_decoders, stride, n_blocks, momentum=0.01):
+        super(Decoder, self).__init__()
+        self.layers = nn.ModuleList()
+        self.n_decoders = n_decoders
+        for i in range(self.n_decoders):
+            out_channels = in_channels // 2
+            self.layers.append(
+                ResDecoderBlock(in_channels, out_channels, stride, n_blocks, momentum)
+            )
+            in_channels = out_channels
+
+    def forward(self, x, concat_tensors):
+        for i in range(self.n_decoders):
+            x = self.layers[i](x, concat_tensors[-1 - i])
+        return x
+
+
+class DeepUnet(nn.Module):
+    def __init__(
+        self,
+        kernel_size,
+        n_blocks,
+        en_de_layers=5,
+        inter_layers=4,
+        in_channels=1,
+        en_out_channels=16,
+    ):
+        super(DeepUnet, self).__init__()
+        self.encoder = Encoder(
+            in_channels, 128, en_de_layers, kernel_size, n_blocks, en_out_channels
+        )
+        self.intermediate = Intermediate(
+            self.encoder.out_channel // 2,
+            self.encoder.out_channel,
+            inter_layers,
+            n_blocks,
+        )
+        self.decoder = Decoder(
+            self.encoder.out_channel, en_de_layers, kernel_size, n_blocks
+        )
+
+    def forward(self, x):
+        x, concat_tensors = self.encoder(x)
+        x = self.intermediate(x)
+        x = self.decoder(x, concat_tensors)
+        return x
+
+
+class E2E(nn.Module):
+    def __init__(
+        self,
+        n_blocks,
+        n_gru,
+        kernel_size,
+        en_de_layers=5,
+        inter_layers=4,
+        in_channels=1,
+        en_out_channels=16,
+    ):
+        super(E2E, self).__init__()
+        self.unet = DeepUnet(
+            kernel_size,
+            n_blocks,
+            en_de_layers,
+            inter_layers,
+            in_channels,
+            en_out_channels,
+        )
+        self.cnn = nn.Conv2d(en_out_channels, 3, (3, 3), padding=(1, 1))
+        if n_gru:
+            self.fc = nn.Sequential(
+                BiGRU(3 * 128, 256, n_gru),
+                nn.Linear(512, 360),
+                nn.Dropout(0.25),
+                nn.Sigmoid(),
+            )
+
+    def forward(self, mel):
+        mel = mel.transpose(-1, -2).unsqueeze(1)
+        x = self.cnn(self.unet(mel)).transpose(1, 2).flatten(-2)
+        x = self.fc(x)
+        return x
+
+
+class MelSpectrogram(torch.nn.Module):
+    def __init__(
+        self,
+        is_half,
+        n_mel_channels,
+        sampling_rate,
+        win_length,
+        hop_length,
+        n_fft=None,
+        mel_fmin=0,
+        mel_fmax=None,
+        clamp=1e-5,
+    ):
+        super().__init__()
+        n_fft = win_length if n_fft is None else n_fft
+        self.hann_window = {}
+        mel_basis = mel(
+            sr=sampling_rate,
+            n_fft=n_fft,
+            n_mels=n_mel_channels,
+            fmin=mel_fmin,
+            fmax=mel_fmax,
+            htk=True,
+        )
+        mel_basis = torch.from_numpy(mel_basis).float()
+        self.register_buffer("mel_basis", mel_basis)
+        self.n_fft = win_length if n_fft is None else n_fft
+        self.hop_length = hop_length
+        self.win_length = win_length
+        self.sampling_rate = sampling_rate
+        self.n_mel_channels = n_mel_channels
+        self.clamp = clamp
+        self.is_half = is_half
+
+    def forward(self, audio, keyshift=0, speed=1, center=True):
+        factor = 2 ** (keyshift / 12)
+        n_fft_new = int(np.round(self.n_fft * factor))
+        win_length_new = int(np.round(self.win_length * factor))
+        hop_length_new = int(np.round(self.hop_length * speed))
+        keyshift_key = str(keyshift) + "_" + str(audio.device)
+        if keyshift_key not in self.hann_window:
+            self.hann_window[keyshift_key] = torch.hann_window(win_length_new).to(
+                audio.device
+            )
+        fft = torch.stft(
+            audio,
+            n_fft=n_fft_new,
+            hop_length=hop_length_new,
+            win_length=win_length_new,
+            window=self.hann_window[keyshift_key],
+            center=center,
+            return_complex=True,
+        )
+        magnitude = torch.sqrt(fft.real.pow(2) + fft.imag.pow(2))
+        if keyshift != 0:
+            size = self.n_fft // 2 + 1
+            resize = magnitude.size(1)
+            if resize < size:
+                magnitude = F.pad(magnitude, (0, 0, 0, size - resize))
+            magnitude = magnitude[:, :size, :] * self.win_length / win_length_new
+        mel_output = torch.matmul(self.mel_basis, magnitude)
+        if self.is_half == True:
+            mel_output = mel_output.half()
+        log_mel_spec = torch.log(torch.clamp(mel_output, min=self.clamp))
+        return log_mel_spec
+
+
+class RMVPE:
+    def __init__(self, model_path, is_half, device=None):
+        #print("RMVPE - model_path is:", model_path)
+        #print("RMVPE - is_half is:", is_half)
+        self.resample_kernel = {}
+        model = E2E(4, 1, (2, 2))
+        ckpt = torch.load(model_path, map_location="cpu")
+        model.load_state_dict(ckpt)
+        model.eval()
+        if is_half == True:
+            model = model.half()
+        self.model = model
+        self.resample_kernel = {}
+        self.is_half = is_half
+        if device is None:
+            device = "cuda" if torch.cuda.is_available() else "cpu"
+        self.device = device
+        self.mel_extractor = MelSpectrogram(
+            is_half, 128, 16000, 1024, 160, None, 30, 8000
+        ).to(device)
+        self.model = self.model.to(device)
+        cents_mapping = 20 * np.arange(360) + 1997.3794084376191
+        self.cents_mapping = np.pad(cents_mapping, (4, 4))  # 368
+
+    def mel2hidden(self, mel):
+        with torch.no_grad():
+            n_frames = mel.shape[-1]
+            mel = F.pad(
+                mel, (0, 32 * ((n_frames - 1) // 32 + 1) - n_frames), mode="reflect"
+            )
+            hidden = self.model(mel)
+            return hidden[:, :n_frames]
+
+    def decode(self, hidden, thred=0.03):
+        cents_pred = self.to_local_average_cents(hidden, thred=thred)
+        f0 = 10 * (2 ** (cents_pred / 1200))
+        f0[f0 == 10] = 0
+        return f0
+
+    def infer_from_audio(self, audio, thred=0.03):
+        audio = torch.from_numpy(audio).float().to(self.device).unsqueeze(0)
+        mel = self.mel_extractor(audio, center=True)
+        hidden = self.mel2hidden(mel)
+        hidden = hidden.squeeze(0).cpu().numpy()
+        if self.is_half == True:
+            hidden = hidden.astype("float32")
+        f0 = self.decode(hidden, thred=thred)
+        return f0
+
+    def to_local_average_cents(self, salience, thred=0.05):
+        center = np.argmax(salience, axis=1)
+        salience = np.pad(salience, ((0, 0), (4, 4)))
+        center += 4
+        todo_salience = []
+        todo_cents_mapping = []
+        starts = center - 4
+        ends = center + 5
+        for idx in range(salience.shape[0]):
+            todo_salience.append(salience[:, starts[idx] : ends[idx]][idx])
+            todo_cents_mapping.append(self.cents_mapping[starts[idx] : ends[idx]])
+        todo_salience = np.array(todo_salience)
+        todo_cents_mapping = np.array(todo_cents_mapping)
+        product_sum = np.sum(todo_salience * todo_cents_mapping, 1)
+        weight_sum = np.sum(todo_salience, 1)
+        devided = product_sum / weight_sum
+        maxx = np.max(salience, axis=1)
+        devided[maxx <= thred] = 0
+        return devided

system/tts_engines/rvc/lib/tools/analyzer.py

@@ -0,0 +1,76 @@
+import numpy as np
+import matplotlib.pyplot as plt
+import librosa.display
+import librosa
+
+
+def calculate_features(y, sr):
+    stft = np.abs(librosa.stft(y))
+    duration = librosa.get_duration(y=y, sr=sr)
+    cent = librosa.feature.spectral_centroid(S=stft, sr=sr)[0]
+    bw = librosa.feature.spectral_bandwidth(S=stft, sr=sr)[0]
+    rolloff = librosa.feature.spectral_rolloff(S=stft, sr=sr)[0]
+    return stft, duration, cent, bw, rolloff
+
+
+def plot_title(title):
+    plt.suptitle(title, fontsize=16, fontweight="bold")
+
+
+def plot_spectrogram(y, sr, stft, duration, cmap="inferno"):
+    plt.subplot(3, 1, 1)
+    plt.imshow(
+        librosa.amplitude_to_db(stft, ref=np.max),
+        origin="lower",
+        extent=[0, duration, 0, sr / 1000],
+        aspect="auto",
+        cmap=cmap,  # Change the colormap here
+    )
+    plt.colorbar(format="%+2.0f dB")
+    plt.xlabel("Time (s)")
+    plt.ylabel("Frequency (kHz)")
+    plt.title("Spectrogram")
+
+
+def plot_waveform(y, sr, duration):
+    plt.subplot(3, 1, 2)
+    librosa.display.waveshow(y, sr=sr)
+    plt.xlabel("Time (s)")
+    plt.ylabel("Amplitude")
+    plt.title("Waveform")
+
+
+def plot_features(times, cent, bw, rolloff, duration):
+    plt.subplot(3, 1, 3)
+    plt.plot(times, cent, label="Spectral Centroid (kHz)", color="b")
+    plt.plot(times, bw, label="Spectral Bandwidth (kHz)", color="g")
+    plt.plot(times, rolloff, label="Spectral Rolloff (kHz)", color="r")
+    plt.xlabel("Time (s)")
+    plt.title("Spectral Features")
+    plt.legend()
+
+
+def analyze_audio(audio_file, save_plot_path="logs/audio_analysis.png"):
+    y, sr = librosa.load(audio_file)
+    stft, duration, cent, bw, rolloff = calculate_features(y, sr)
+
+    plt.figure(figsize=(12, 10))
+
+    plot_title("Audio Analysis" + " - " + audio_file.split("/")[-1])
+    plot_spectrogram(y, sr, stft, duration)
+    plot_waveform(y, sr, duration)
+    plot_features(librosa.times_like(cent), cent, bw, rolloff, duration)
+
+    plt.tight_layout()
+
+    if save_plot_path:
+        plt.savefig(save_plot_path, bbox_inches="tight", dpi=300)
+    plt.close()
+
+    audio_info = f"""Sample Rate: {sr}\nDuration: {(
+            str(round(duration, 2)) + " seconds"
+            if duration < 60
+            else str(round(duration / 60, 2)) + " minutes"
+    )}\nNumber of Samples: {len(y)}\nBits per Sample: {librosa.get_samplerate(audio_file)}\nChannels: {"Mono (1)" if y.ndim == 1 else "Stereo (2)"}"""
+
+    return audio_info, save_plot_path

system/tts_engines/rvc/lib/tools/gdown.py

@@ -0,0 +1,409 @@
+from __future__ import print_function
+
+import json
+import os
+import os.path as osp
+import re
+import warnings
+from six.moves import urllib_parse
+import shutil
+import sys
+import tempfile
+import textwrap
+import time
+
+import requests
+import six
+import tqdm
+
+
+def indent(text, prefix):
+    def prefixed_lines():
+        for line in text.splitlines(True):
+            yield (prefix + line if line.strip() else line)
+
+    return "".join(prefixed_lines())
+
+
+class FileURLRetrievalError(Exception):
+    pass
+
+
+class FolderContentsMaximumLimitError(Exception):
+    pass
+
+
+def parse_url(url, warning=True):
+    """Parse URLs especially for Google Drive links.
+
+    file_id: ID of file on Google Drive.
+    is_download_link: Flag if it is download link of Google Drive.
+    """
+    parsed = urllib_parse.urlparse(url)
+    query = urllib_parse.parse_qs(parsed.query)
+    is_gdrive = parsed.hostname in ["drive.google.com", "docs.google.com"]
+    is_download_link = parsed.path.endswith("/uc")
+
+    if not is_gdrive:
+        return is_gdrive, is_download_link
+
+    file_id = None
+    if "id" in query:
+        file_ids = query["id"]
+        if len(file_ids) == 1:
+            file_id = file_ids[0]
+    else:
+        patterns = [
+            r"^/file/d/(.*?)/(edit|view)$",
+            r"^/file/u/[0-9]+/d/(.*?)/(edit|view)$",
+            r"^/document/d/(.*?)/(edit|htmlview|view)$",
+            r"^/document/u/[0-9]+/d/(.*?)/(edit|htmlview|view)$",
+            r"^/presentation/d/(.*?)/(edit|htmlview|view)$",
+            r"^/presentation/u/[0-9]+/d/(.*?)/(edit|htmlview|view)$",
+            r"^/spreadsheets/d/(.*?)/(edit|htmlview|view)$",
+            r"^/spreadsheets/u/[0-9]+/d/(.*?)/(edit|htmlview|view)$",
+        ]
+        for pattern in patterns:
+            match = re.match(pattern, parsed.path)
+            if match:
+                file_id = match.groups()[0]
+                break
+
+    if warning and not is_download_link:
+        warnings.warn(
+            "You specified a Google Drive link that is not the correct link "
+            "to download a file. You might want to try `--fuzzy` option "
+            "or the following url: {url}".format(
+                url="https://drive.google.com/uc?id={}".format(file_id)
+            )
+        )
+
+    return file_id, is_download_link
+
+
+CHUNK_SIZE = 512 * 1024  # 512KB
+home = osp.expanduser("~")
+
+
+def get_url_from_gdrive_confirmation(contents):
+    url = ""
+    m = re.search(r'href="(\/uc\?export=download[^"]+)', contents)
+    if m:
+        url = "https://docs.google.com" + m.groups()[0]
+        url = url.replace("&", "&")
+        return url
+
+    m = re.search(r'href="/open\?id=([^"]+)"', contents)
+    if m:
+        url = m.groups()[0]
+        uuid = re.search(
+            r'<input\s+type="hidden"\s+name="uuid"\s+value="([^"]+)"', contents
+        )
+        uuid = uuid.groups()[0]
+        url = (
+            "https://drive.usercontent.google.com/download?id="
+            + url
+            + "&confirm=t&uuid="
+            + uuid
+        )
+        return url
+
+    m = re.search(r'"downloadUrl":"([^"]+)', contents)
+    if m:
+        url = m.groups()[0]
+        url = url.replace("\\u003d", "=")
+        url = url.replace("\\u0026", "&")
+        return url
+
+    m = re.search(r'<p class="uc-error-subcaption">(.*)</p>', contents)
+    if m:
+        error = m.groups()[0]
+        raise FileURLRetrievalError(error)
+
+    raise FileURLRetrievalError(
+        "Cannot retrieve the public link of the file. "
+        "You may need to change the permission to "
+        "'Anyone with the link', or have had many accesses."
+    )
+
+
+def _get_session(proxy, use_cookies, return_cookies_file=False):
+    sess = requests.session()
+
+    sess.headers.update(
+        {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6)"}
+    )
+
+    if proxy is not None:
+        sess.proxies = {"http": proxy, "https": proxy}
+        print("Using proxy:", proxy, file=sys.stderr)
+
+    # Load cookies if exists
+    cookies_file = osp.join(home, ".cache/gdown/cookies.json")
+    if osp.exists(cookies_file) and use_cookies:
+        with open(cookies_file) as f:
+            cookies = json.load(f)
+        for k, v in cookies:
+            sess.cookies[k] = v
+
+    if return_cookies_file:
+        return sess, cookies_file
+    else:
+        return sess
+
+
+def download(
+    url=None,
+    output=None,
+    quiet=False,
+    proxy=None,
+    speed=None,
+    use_cookies=True,
+    verify=True,
+    id=None,
+    fuzzy=True,
+    resume=False,
+    format=None,
+):
+    """Download file from URL.
+
+    Parameters
+    ----------
+    url: str
+        URL. Google Drive URL is also supported.
+    output: str
+        Output filename. Default is basename of URL.
+    quiet: bool
+        Suppress terminal output. Default is False.
+    proxy: str
+        Proxy.
+    speed: float
+        Download byte size per second (e.g., 256KB/s = 256 * 1024).
+    use_cookies: bool
+        Flag to use cookies. Default is True.
+    verify: bool or string
+        Either a bool, in which case it controls whether the server's TLS
+        certificate is verified, or a string, in which case it must be a path
+        to a CA bundle to use. Default is True.
+    id: str
+        Google Drive's file ID.
+    fuzzy: bool
+        Fuzzy extraction of Google Drive's file Id. Default is False.
+    resume: bool
+        Resume the download from existing tmp file if possible.
+        Default is False.
+    format: str, optional
+        Format of Google Docs, Spreadsheets and Slides. Default is:
+            - Google Docs: 'docx'
+            - Google Spreadsheet: 'xlsx'
+            - Google Slides: 'pptx'
+
+    Returns
+    -------
+    output: str
+        Output filename.
+    """
+    if not (id is None) ^ (url is None):
+        raise ValueError("Either url or id has to be specified")
+    if id is not None:
+        url = "https://drive.google.com/uc?id={id}".format(id=id)
+
+    url_origin = url
+
+    sess, cookies_file = _get_session(
+        proxy=proxy, use_cookies=use_cookies, return_cookies_file=True
+    )
+
+    gdrive_file_id, is_gdrive_download_link = parse_url(url, warning=not fuzzy)
+
+    if fuzzy and gdrive_file_id:
+        # overwrite the url with fuzzy match of a file id
+        url = "https://drive.google.com/uc?id={id}".format(id=gdrive_file_id)
+        url_origin = url
+        is_gdrive_download_link = True
+
+    while True:
+        res = sess.get(url, stream=True, verify=verify)
+
+        if url == url_origin and res.status_code == 500:
+            # The file could be Google Docs or Spreadsheets.
+            url = "https://drive.google.com/open?id={id}".format(id=gdrive_file_id)
+            continue
+
+        if res.headers["Content-Type"].startswith("text/html"):
+            m = re.search("<title>(.+)</title>", res.text)
+            if m and m.groups()[0].endswith(" - Google Docs"):
+                url = (
+                    "https://docs.google.com/document/d/{id}/export"
+                    "?format={format}".format(
+                        id=gdrive_file_id,
+                        format="docx" if format is None else format,
+                    )
+                )
+                continue
+            elif m and m.groups()[0].endswith(" - Google Sheets"):
+                url = (
+                    "https://docs.google.com/spreadsheets/d/{id}/export"
+                    "?format={format}".format(
+                        id=gdrive_file_id,
+                        format="xlsx" if format is None else format,
+                    )
+                )
+                continue
+            elif m and m.groups()[0].endswith(" - Google Slides"):
+                url = (
+                    "https://docs.google.com/presentation/d/{id}/export"
+                    "?format={format}".format(
+                        id=gdrive_file_id,
+                        format="pptx" if format is None else format,
+                    )
+                )
+                continue
+        elif (
+            "Content-Disposition" in res.headers
+            and res.headers["Content-Disposition"].endswith("pptx")
+            and format not in {None, "pptx"}
+        ):
+            url = (
+                "https://docs.google.com/presentation/d/{id}/export"
+                "?format={format}".format(
+                    id=gdrive_file_id,
+                    format="pptx" if format is None else format,
+                )
+            )
+            continue
+
+        if use_cookies:
+            if not osp.exists(osp.dirname(cookies_file)):
+                os.makedirs(osp.dirname(cookies_file))
+            # Save cookies
+            with open(cookies_file, "w") as f:
+                cookies = [
+                    (k, v)
+                    for k, v in sess.cookies.items()
+                    if not k.startswith("download_warning_")
+                ]
+                json.dump(cookies, f, indent=2)
+
+        if "Content-Disposition" in res.headers:
+            # This is the file
+            break
+        if not (gdrive_file_id and is_gdrive_download_link):
+            break
+
+        # Need to redirect with confirmation
+        try:
+            url = get_url_from_gdrive_confirmation(res.text)
+        except FileURLRetrievalError as e:
+            message = (
+                "Failed to retrieve file url:\n\n{}\n\n"
+                "You may still be able to access the file from the browser:"
+                "\n\n\t{}\n\n"
+                "but Gdown can't. Please check connections and permissions."
+            ).format(
+                indent("\n".join(textwrap.wrap(str(e))), prefix="\t"),
+                url_origin,
+            )
+            raise FileURLRetrievalError(message)
+
+    if gdrive_file_id and is_gdrive_download_link:
+        content_disposition = six.moves.urllib_parse.unquote(
+            res.headers["Content-Disposition"]
+        )
+
+        m = re.search(r"filename\*=UTF-8''(.*)", content_disposition)
+        if not m:
+            m = re.search(r'filename=["\']?(.*?)["\']?$', content_disposition)
+        filename_from_url = m.groups()[0]
+        filename_from_url = filename_from_url.replace(osp.sep, "_")
+    else:
+        filename_from_url = osp.basename(url)
+
+    if output is None:
+        output = filename_from_url
+
+    output_is_path = isinstance(output, six.string_types)
+    if output_is_path and output.endswith(osp.sep):
+        if not osp.exists(output):
+            os.makedirs(output)
+        output = osp.join(output, filename_from_url)
+
+    if output_is_path:
+        existing_tmp_files = []
+        for file in os.listdir(osp.dirname(output) or "."):
+            if file.startswith(osp.basename(output)):
+                existing_tmp_files.append(osp.join(osp.dirname(output), file))
+        if resume and existing_tmp_files:
+            if len(existing_tmp_files) != 1:
+                print(
+                    "There are multiple temporary files to resume:",
+                    file=sys.stderr,
+                )
+                print("\n")
+                for file in existing_tmp_files:
+                    print("\t", file, file=sys.stderr)
+                print("\n")
+                print(
+                    "Please remove them except one to resume downloading.",
+                    file=sys.stderr,
+                )
+                return
+            tmp_file = existing_tmp_files[0]
+        else:
+            resume = False
+            # mkstemp is preferred, but does not work on Windows
+            # https://github.com/wkentaro/gdown/issues/153
+            tmp_file = tempfile.mktemp(
+                suffix=tempfile.template,
+                prefix=osp.basename(output),
+                dir=osp.dirname(output),
+            )
+        f = open(tmp_file, "ab")
+    else:
+        tmp_file = None
+        f = output
+
+    if tmp_file is not None and f.tell() != 0:
+        headers = {"Range": "bytes={}-".format(f.tell())}
+        res = sess.get(url, headers=headers, stream=True, verify=verify)
+
+    if not quiet:
+        # print("Downloading...", file=sys.stderr)
+        if resume:
+            print("Resume:", tmp_file, file=sys.stderr)
+        # if url_origin != url:
+        #     print("From (original):", url_origin, file=sys.stderr)
+        #     print("From (redirected):", url, file=sys.stderr)
+        # else:
+        #     print("From:", url, file=sys.stderr)
+        print(
+            "To:",
+            osp.abspath(output) if output_is_path else output,
+            file=sys.stderr,
+        )
+
+    try:
+        total = res.headers.get("Content-Length")
+        if total is not None:
+            total = int(total)
+        if not quiet:
+            pbar = tqdm.tqdm(total=total, unit="B", unit_scale=True)
+        t_start = time.time()
+        for chunk in res.iter_content(chunk_size=CHUNK_SIZE):
+            f.write(chunk)
+            if not quiet:
+                pbar.update(len(chunk))
+            if speed is not None:
+                elapsed_time_expected = 1.0 * pbar.n / speed
+                elapsed_time = time.time() - t_start
+                if elapsed_time < elapsed_time_expected:
+                    time.sleep(elapsed_time_expected - elapsed_time)
+        if not quiet:
+            pbar.close()
+        if tmp_file:
+            f.close()
+            shutil.move(tmp_file, output)
+    finally:
+        sess.close()
+
+    return output

system/tts_engines/rvc/lib/tools/launch_tensorboard.py

@@ -0,0 +1,16 @@
+import time
+from tensorboard import program
+
+log_path = "logs"
+
+
+def launch_tensorboard_pipeline():
+    tb = program.TensorBoard()
+    tb.configure(argv=[None, "--logdir", log_path])
+    url = tb.launch()
+    print(
+        f"Access the tensorboard using the following link:\n{url}?pinnedCards=%5B%7B%22plugin%22%3A%22scalars%22%2C%22tag%22%3A%22loss%2Fg%2Ftotal%22%7D%2C%7B%22plugin%22%3A%22scalars%22%2C%22tag%22%3A%22loss%2Fd%2Ftotal%22%7D%2C%7B%22plugin%22%3A%22scalars%22%2C%22tag%22%3A%22loss%2Fg%2Fkl%22%7D%2C%7B%22plugin%22%3A%22scalars%22%2C%22tag%22%3A%22loss%2Fg%2Fmel%22%7D%5D"
+    )
+
+    while True:
+        time.sleep(600)

system/tts_engines/rvc/lib/tools/model_download.py

@@ -0,0 +1,353 @@
+import os
+import sys
+import wget
+import zipfile
+from bs4 import BeautifulSoup
+import requests
+from urllib.parse import unquote, urlencode, parse_qs, urlparse
+import re
+import shutil
+import six
+
+
+def find_folder_parent(search_dir, folder_name):
+    for dirpath, dirnames, _ in os.walk(search_dir):
+        if folder_name in dirnames:
+            return os.path.abspath(dirpath)
+    return None
+
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+
+from rvc.lib.utils import format_title
+
+from rvc.lib.tools import gdown
+
+file_path = find_folder_parent(now_dir, "logs")
+
+zips_path = os.getcwd() + "/logs/zips"
+
+
+def search_pth_index(folder):
+    pth_paths = [
+        os.path.join(folder, file)
+        for file in os.listdir(folder)
+        if os.path.isfile(os.path.join(folder, file)) and file.endswith(".pth")
+    ]
+    index_paths = [
+        os.path.join(folder, file)
+        for file in os.listdir(folder)
+        if os.path.isfile(os.path.join(folder, file)) and file.endswith(".index")
+    ]
+
+    return pth_paths, index_paths
+
+
+def get_mediafire_download_link(url):
+    response = requests.get(url)
+    response.raise_for_status()
+    soup = BeautifulSoup(response.text, "html.parser")
+    download_button = soup.find(
+        "a", {"class": "input popsok", "aria-label": "Download file"}
+    )
+    if download_button:
+        download_link = download_button.get("href")
+        return download_link
+    else:
+        return None
+
+
+def download_from_url(url):
+    os.makedirs(zips_path, exist_ok=True)
+    if url != "":
+        if "drive.google.com" in url:
+            if "file/d/" in url:
+                file_id = url.split("file/d/")[1].split("/")[0]
+            elif "id=" in url:
+                file_id = url.split("id=")[1].split("&")[0]
+            else:
+                return None
+
+            if file_id:
+                os.chdir(zips_path)
+                try:
+                    gdown.download(
+                        f"https://drive.google.com/uc?id={file_id}",
+                        quiet=True,
+                        fuzzy=True,
+                    )
+                except Exception as error:
+                    error_message = str(error)
+                    if (
+                        "Too many users have viewed or downloaded this file recently"
+                        in error_message
+                    ):
+                        os.chdir(now_dir)
+                        return "too much use"
+                    elif (
+                        "Cannot retrieve the public link of the file." in error_message
+                    ):
+                        os.chdir(now_dir)
+                        return "private link"
+                    else:
+                        print(error_message)
+                        os.chdir(now_dir)
+                        return None
+        elif "disk.yandex.ru" in url:
+            base_url = "https://cloud-api.yandex.net/v1/disk/public/resources/download?"
+            public_key = url
+            final_url = base_url + urlencode(dict(public_key=public_key))
+            response = requests.get(final_url)
+            download_url = response.json()["href"]
+            download_response = requests.get(download_url)
+
+            if download_response.status_code == 200:
+                filename = parse_qs(urlparse(unquote(download_url)).query).get(
+                    "filename", [""]
+                )[0]
+                if filename:
+                    os.chdir(zips_path)
+                    with open(filename, "wb") as f:
+                        f.write(download_response.content)
+            else:
+                print("Failed to get filename from URL.")
+                return None
+
+        elif "pixeldrain.com" in url:
+            try:
+                file_id = url.split("pixeldrain.com/u/")[1]
+                os.chdir(zips_path)
+                print(file_id)
+                response = requests.get(f"https://pixeldrain.com/api/file/{file_id}")
+                if response.status_code == 200:
+                    file_name = (
+                        response.headers.get("Content-Disposition")
+                        .split("filename=")[-1]
+                        .strip('";')
+                    )
+                    os.makedirs(zips_path, exist_ok=True)
+                    with open(os.path.join(zips_path, file_name), "wb") as newfile:
+                        newfile.write(response.content)
+                        os.chdir(file_path)
+                        return "downloaded"
+                else:
+                    os.chdir(file_path)
+                    return None
+            except Exception as e:
+                print(e)
+                os.chdir(file_path)
+                return None
+
+        elif "cdn.discordapp.com" in url:
+            file = requests.get(url)
+            os.chdir(zips_path)
+            if file.status_code == 200:
+                name = url.split("/")
+                with open(os.path.join(name[-1]), "wb") as newfile:
+                    newfile.write(file.content)
+            else:
+                return None
+        elif "/blob/" in url or "/resolve/" in url:
+            os.chdir(zips_path)
+            if "/blob/" in url:
+                url = url.replace("/blob/", "/resolve/")
+
+            response = requests.get(url, stream=True)
+            if response.status_code == 200:
+                content_disposition = six.moves.urllib_parse.unquote(
+                    response.headers["Content-Disposition"]
+                )
+                m = re.search(r'filename="([^"]+)"', content_disposition)
+                file_name = m.groups()[0]
+                file_name = file_name.replace(os.path.sep, "_")
+                total_size_in_bytes = int(response.headers.get("content-length", 0))
+                block_size = 1024
+                progress_bar_length = 50
+                progress = 0
+
+                with open(os.path.join(zips_path, file_name), "wb") as file:
+                    for data in response.iter_content(block_size):
+                        file.write(data)
+                        progress += len(data)
+                        progress_percent = int((progress / total_size_in_bytes) * 100)
+                        num_dots = int(
+                            (progress / total_size_in_bytes) * progress_bar_length
+                        )
+                        progress_bar = (
+                            "["
+                            + "." * num_dots
+                            + " " * (progress_bar_length - num_dots)
+                            + "]"
+                        )
+                        print(
+                            f"{progress_percent}% {progress_bar} {progress}/{total_size_in_bytes}  ",
+                            end="\r",
+                        )
+                        if progress_percent == 100:
+                            print("\n")
+
+            else:
+                os.chdir(now_dir)
+                return None
+        elif "/tree/main" in url:
+            os.chdir(zips_path)
+            response = requests.get(url)
+            soup = BeautifulSoup(response.content, "html.parser")
+            temp_url = ""
+            for link in soup.find_all("a", href=True):
+                if link["href"].endswith(".zip"):
+                    temp_url = link["href"]
+                    break
+            if temp_url:
+                url = temp_url
+                url = url.replace("blob", "resolve")
+                if "huggingface.co" not in url:
+                    url = "https://huggingface.co" + url
+
+                    wget.download(url)
+            else:
+                os.chdir(now_dir)
+                return None
+
+            params = {"id": f"eq.{id_number}"}
+            response = requests.get(url, headers=headers, params=params)
+            if response.status_code == 200:
+                json_response = response.json()
+                print(json_response)
+                if json_response:
+                    link = json_response[0]["link"]
+                    verify = download_from_url(link)
+                    if verify == "downloaded":
+                        return "downloaded"
+                    else:
+                        return None
+            else:
+                return None
+        else:
+            try:
+                os.chdir(zips_path)
+                wget.download(url)
+            except Exception as error:
+                os.chdir(now_dir)
+                print(error)
+                return None
+
+        for currentPath, _, zipFiles in os.walk(zips_path):
+            for Files in zipFiles:
+                filePart = Files.split(".")
+                extensionFile = filePart[len(filePart) - 1]
+                filePart.pop()
+                nameFile = "_".join(filePart)
+                realPath = os.path.join(currentPath, Files)
+                os.rename(realPath, nameFile + "." + extensionFile)
+
+        os.chdir(now_dir)
+        return "downloaded"
+
+    os.chdir(now_dir)
+    return None
+
+
+def extract_and_show_progress(zipfile_path, unzips_path):
+    try:
+        with zipfile.ZipFile(zipfile_path, "r") as zip_ref:
+            for file_info in zip_ref.infolist():
+                zip_ref.extract(file_info, unzips_path)
+        os.remove(zipfile_path)
+        return True
+    except Exception as error:
+        print(error)
+        return False
+
+
+def unzip_file(zip_path, zip_file_name):
+    zip_file_path = os.path.join(zip_path, zip_file_name + ".zip")
+    extract_path = os.path.join(file_path, zip_file_name)
+    with zipfile.ZipFile(zip_file_path, "r") as zip_ref:
+        zip_ref.extractall(extract_path)
+    os.remove(zip_file_path)
+
+
+def model_download_pipeline(url):
+    verify = download_from_url(url)
+    if verify == "downloaded":
+        extract_folder_path = ""
+        for filename in os.listdir(zips_path):
+            if filename.endswith(".zip"):
+                zipfile_path = os.path.join(zips_path, filename)
+                print("Proceeding with the extraction...")
+
+                model_zip = os.path.basename(zipfile_path)
+                model_name = format_title(model_zip.split(".zip")[0])
+                extract_folder_path = os.path.join(
+                    "logs",
+                    os.path.normpath(model_name),
+                )
+
+                success = extract_and_show_progress(zipfile_path, extract_folder_path)
+
+                subfolders = [
+                    f
+                    for f in os.listdir(extract_folder_path)
+                    if os.path.isdir(os.path.join(extract_folder_path, f))
+                ]
+                if len(subfolders) == 1:
+                    subfolder_path = os.path.join(extract_folder_path, subfolders[0])
+                    for item in os.listdir(subfolder_path):
+                        s = os.path.join(subfolder_path, item)
+                        d = os.path.join(extract_folder_path, item)
+                        shutil.move(s, d)
+                    os.rmdir(subfolder_path)
+
+                for item in os.listdir(extract_folder_path):
+                    if ".pth" in item:
+                        file_name = item.split(".pth")[0]
+                        if file_name != model_name:
+                            os.rename(
+                                os.path.join(extract_folder_path, item),
+                                os.path.join(extract_folder_path, model_name + ".pth"),
+                            )
+                    else:
+                        if "v2" not in item:
+                            file_name = item.split("_nprobe_1_")[1].split("_v1")[0]
+                            if file_name != model_name:
+                                new_file_name = (
+                                    item.split("_nprobe_1_")[0]
+                                    + "_nprobe_1_"
+                                    + model_name
+                                    + "_v1"
+                                )
+                                os.rename(
+                                    os.path.join(extract_folder_path, item),
+                                    os.path.join(
+                                        extract_folder_path, new_file_name + ".index"
+                                    ),
+                                )
+                        else:
+                            file_name = item.split("_nprobe_1_")[1].split("_v2")[0]
+                            if file_name != model_name:
+                                new_file_name = (
+                                    item.split("_nprobe_1_")[0]
+                                    + "_nprobe_1_"
+                                    + model_name
+                                    + "_v2"
+                                )
+                                os.rename(
+                                    os.path.join(extract_folder_path, item),
+                                    os.path.join(
+                                        extract_folder_path, new_file_name + ".index"
+                                    ),
+                                )
+
+                if success:
+                    print(f"Model {model_name} downloaded!")
+                else:
+                    print(f"Error downloading {model_name}")
+                    sys.exit()
+        if extract_folder_path == "":
+            print("Zip file was not found.")
+            sys.exit()
+        result = search_pth_index(extract_folder_path)
+    else:
+        message = "Error"

system/tts_engines/rvc/lib/tools/prerequisites_download.py

@@ -0,0 +1,96 @@
+import os
+import wget
+
+url_base = "https://huggingface.co/nolinkhere"
+pretraineds_v1_list = [
+    (
+        "pretrained_v1/",
+        [
+            "D32k.pth",
+            "D40k.pth",
+            "D48k.pth",
+            "G32k.pth",
+            "G40k.pth",
+            "G48k.pth",
+            "f0D32k.pth",
+            "f0D40k.pth",
+            "f0D48k.pth",
+            "f0G32k.pth",
+            "f0G40k.pth",
+            "f0G48k.pth",
+        ],
+    ),
+]
+pretraineds_v2_list = [
+    (
+        "pretrained_v2/",
+        [
+            "D32k.pth",
+            "D40k.pth",
+            "D48k.pth",
+            "G32k.pth",
+            "G40k.pth",
+            "G48k.pth",
+            "f0D32k.pth",
+            "f0D40k.pth",
+            "f0D48k.pth",
+            "f0G32k.pth",
+            "f0G40k.pth",
+            "f0G48k.pth",
+        ],
+    ),
+]
+
+models_list = [
+    "hubert_base.pt",
+    "contentvec_base.pt",
+    "rmvpe.pt",
+    "fcpe.pt",
+    # "rmvpe.onnx"
+]
+
+executables_list = ["ffmpeg.exe", "ffprobe.exe"]
+
+folder_mapping_list = {
+    "pretrained_v1/": "rvc/pretraineds/pretrained_v1/",
+    "pretrained_v2/": "rvc/pretraineds/pretrained_v2/",
+}
+
+
+def prequisites_download_pipeline(pretraineds_v1, pretraineds_v2, models, exe):
+    def download_files(file_list):
+        for file_name in file_list:
+            destination_path = os.path.join(file_name)
+            url = f"{url_base}/{file_name}"
+            if not os.path.exists(destination_path):
+                os.makedirs(os.path.dirname(destination_path) or ".", exist_ok=True)
+                print(f"\nDownloading {url} to {destination_path}...")
+                wget.download(url, out=destination_path)
+
+    if models == "True":
+        download_files(models_list)
+
+    if exe == "True" and os.name == "nt":
+        download_files(executables_list)
+
+    if pretraineds_v1 == "True":
+        for remote_folder, file_list in pretraineds_v1_list:
+            local_folder = folder_mapping_list.get(remote_folder, "")
+            for file in file_list:
+                destination_path = os.path.join(local_folder, file)
+                url = f"{url_base}/{remote_folder}{file}"
+                if not os.path.exists(destination_path):
+                    os.makedirs(os.path.dirname(destination_path) or ".", exist_ok=True)
+                    print(f"\nDownloading {url} to {destination_path}...")
+                    wget.download(url, out=destination_path)
+
+    if pretraineds_v2 == "True":
+        for remote_folder, file_list in pretraineds_v2_list:
+            local_folder = folder_mapping_list.get(remote_folder, "")
+            for file in file_list:
+                destination_path = os.path.join(local_folder, file)
+                url = f"{url_base}/{remote_folder}{file}"
+                if not os.path.exists(destination_path):
+                    os.makedirs(os.path.dirname(destination_path) or ".", exist_ok=True)
+                    print(f"\nDownloading {url} to {destination_path}...")
+                    wget.download(url, out=destination_path)

system/tts_engines/rvc/lib/tools/pretrained_selector.py

@@ -0,0 +1,63 @@
+def pretrained_selector(pitch_guidance):
+    if pitch_guidance:
+        return {
+            "v1": {
+                "32000": (
+                    "rvc/pretraineds/pretrained_v1/f0G32k.pth",
+                    "rvc/pretraineds/pretrained_v1/f0D32k.pth",
+                ),
+                "40000": (
+                    "rvc/pretraineds/pretrained_v1/f0G40k.pth",
+                    "rvc/pretraineds/pretrained_v1/f0D40k.pth",
+                ),
+                "48000": (
+                    "rvc/pretraineds/pretrained_v1/f0G48k.pth",
+                    "rvc/pretraineds/pretrained_v1/f0D48k.pth",
+                ),
+            },
+            "v2": {
+                "32000": (
+                    "rvc/pretraineds/pretrained_v2/f0G32k.pth",
+                    "rvc/pretraineds/pretrained_v2/f0D32k.pth",
+                ),
+                "40000": (
+                    "rvc/pretraineds/pretrained_v2/f0G40k.pth",
+                    "rvc/pretraineds/pretrained_v2/f0D40k.pth",
+                ),
+                "48000": (
+                    "rvc/pretraineds/pretrained_v2/f0G48k.pth",
+                    "rvc/pretraineds/pretrained_v2/f0D48k.pth",
+                ),
+            },
+        }
+    else:
+        return {
+            "v1": {
+                "32000": (
+                    "rvc/pretraineds/pretrained_v1/G32k.pth",
+                    "rvc/pretraineds/pretrained_v1/D32k.pth",
+                ),
+                "40000": (
+                    "rvc/pretraineds/pretrained_v1/G40k.pth",
+                    "rvc/pretraineds/pretrained_v1/D40k.pth",
+                ),
+                "48000": (
+                    "rvc/pretraineds/pretrained_v1/G48k.pth",
+                    "rvc/pretraineds/pretrained_v1/D48k.pth",
+                ),
+            },
+            "v2": {
+                "32000": (
+                    "rvc/pretraineds/pretrained_v2/G32k.pth",
+                    "rvc/pretraineds/pretrained_v2/D32k.pth",
+                ),
+                "40000": (
+                    "rvc/pretraineds/pretrained_v2/G40k.pth",
+                    "rvc/pretraineds/pretrained_v2/D40k.pth",
+                ),
+                "48000": (
+                    "rvc/pretraineds/pretrained_v2/G48k.pth",
+                    "rvc/pretraineds/pretrained_v2/D48k.pth",
+                ),
+            },
+        }

system/tts_engines/rvc/lib/tools/split_audio.py

@@ -0,0 +1,107 @@
+from pydub.silence import detect_nonsilent
+from pydub import AudioSegment
+import numpy as np
+import re
+import os
+
+from ...lib.utils import format_title
+
+
+def process_audio(file_path):
+    try:
+        # load audio file
+        song = AudioSegment.from_file(file_path)
+
+        # set silence threshold and duration
+        silence_thresh = -70  # dB
+        min_silence_len = 750  # ms, adjust as needed
+
+        # detect nonsilent parts
+        nonsilent_parts = detect_nonsilent(
+            song, min_silence_len=min_silence_len, silence_thresh=silence_thresh
+        )
+
+        # Create a new directory to store chunks
+        file_dir = os.path.dirname(file_path)
+        file_name = os.path.basename(file_path).split(".")[0]
+        file_name = format_title(file_name)
+        new_dir_path = os.path.join(file_dir, file_name)
+        os.makedirs(new_dir_path, exist_ok=True)
+
+        # Check if timestamps file exists, if so delete it
+        timestamps_file = os.path.join(file_dir, f"{file_name}_timestamps.txt")
+        if os.path.isfile(timestamps_file):
+            os.remove(timestamps_file)
+
+        # export chunks and save start times
+        segment_count = 0
+        for i, (start_i, end_i) in enumerate(nonsilent_parts):
+            chunk = song[start_i:end_i]
+            chunk_file_path = os.path.join(new_dir_path, f"chunk{i}.wav")
+            chunk.export(chunk_file_path, format="wav")
+
+            print(f"Segment {i} created!")
+            segment_count += 1
+
+            # write start times to file
+            with open(timestamps_file, "a", encoding="utf-8") as f:
+                f.write(f"{chunk_file_path} starts at {start_i} ms\n")
+
+        print(f"Total segments created: {segment_count}")
+        print(f"Split all chunks for {file_path} successfully!")
+
+        return "Finish", new_dir_path
+
+    except Exception as e:
+        print(f"An error occurred: {e}")
+        return "Error", None
+
+
+def merge_audio(timestamps_file):
+    try:
+        # Extract prefix from the timestamps filename
+        prefix = os.path.basename(timestamps_file).replace("_timestamps.txt", "")
+        timestamps_dir = os.path.dirname(timestamps_file)
+
+        # Open the timestamps file
+        with open(timestamps_file, "r", encoding="utf-8") as f:
+            lines = f.readlines()
+
+        # Initialize empty list to hold audio segments
+        audio_segments = []
+        last_end_time = 0
+
+        print(f"Processing file: {timestamps_file}")
+
+        for line in lines:
+            # Extract filename and start time from line
+            match = re.search(r"(chunk\d+.wav) starts at (\d+) ms", line)
+            if match:
+                filename, start_time = match.groups()
+                start_time = int(start_time)
+
+                # Construct the complete path to the chunk file
+                chunk_file = os.path.join(timestamps_dir, prefix, filename)
+
+                # Add silence from last_end_time to start_time
+                silence_duration = max(start_time - last_end_time, 0)
+                silence = AudioSegment.silent(duration=silence_duration)
+                audio_segments.append(silence)
+
+                # Load audio file and append to list
+                audio = AudioSegment.from_wav(chunk_file)
+                audio_segments.append(audio)
+
+                # Update last_end_time
+                last_end_time = start_time + len(audio)
+
+                print(f"Processed chunk: {chunk_file}")
+
+        # Concatenate all audio_segments and export
+        merged_audio = sum(audio_segments)
+        merged_audio_np = np.array(merged_audio.get_array_of_samples())
+        # print(f"Exported merged file: {merged_filename}\n")
+        return merged_audio.frame_rate, merged_audio_np
+
+    except Exception as e:
+        print(f"An error occurred: {e}")

system/tts_engines/rvc/lib/tools/tts.py

@@ -0,0 +1,19 @@
+import sys
+import asyncio
+import edge_tts
+
+
+async def main():
+    text = sys.argv[1]
+    voice = sys.argv[2]
+    rate = int(sys.argv[3])
+    output_file = sys.argv[4]
+
+    rates = f"+{rate}%" if rate >= 0 else f"{rate}%"
+
+    await edge_tts.Communicate(text, voice, rate=rates).save(output_file)
+    print(f"TTS with {voice} completed. Output TTS file: '{output_file}'")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

system/tts_engines/rvc/lib/utils.py

@@ -0,0 +1,87 @@
+import numpy as np
+import re
+import unicodedata
+from fairseq import checkpoint_utils
+
+import logging
+
+logging.getLogger("fairseq").setLevel(logging.WARNING)
+import sys
+import os
+import numpy as np
+import asyncio
+from ffmpeg.asyncio import FFmpeg
+from pathlib import Path
+import subprocess
+
+# Get the parent directory of the current file
+this_dir = Path(__file__).resolve().parent.parent.parent.parent.parent
+
+def load_audio(file, sampling_rate):
+    try:
+        # Get the parent directory of the current file
+        this_dir = Path(__file__).resolve().parent.parent.parent.parent.parent
+        file = file.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+
+        # Set the ffmpeg_path variable based on the operating system
+        if sys.platform == "win32":
+            ffmpeg_path = os.path.join(this_dir, "system", "win_ffmpeg", "ffmpeg.exe")
+        else:
+            ffmpeg_path = "ffmpeg"  # Default path for Linux and macOS
+
+        # Initialize the process variable
+        process = subprocess.Popen(
+            [ffmpeg_path, "-y", "-i", file, "-f", "f32le", "-acodec", "pcm_f32le", "-ac", "1", "-ar", str(sampling_rate), "pipe:1"],
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE
+        )
+        
+        out, err = process.communicate()
+        if process.returncode != 0:
+            print(f"FFmpeg error: {err.decode('utf-8')}")  # Debug statement
+            raise RuntimeError(f"FFmpeg error: {err.decode('utf-8')}")
+        #print("Audio loaded successfully")  # Debug statement
+    except Exception as error:
+        print(f"Error loading audio: {error}")  # Debug statement
+        raise RuntimeError(f"Failed to load audio: {error}")
+
+    return np.frombuffer(out, np.float32).flatten()
+
+
+
+def format_title(title):
+    formatted_title = (
+        unicodedata.normalize("NFKD", title).encode("ascii", "ignore").decode("utf-8")
+    )
+    formatted_title = re.sub(r"[\u2500-\u257F]+", "", formatted_title)
+    formatted_title = re.sub(r"[^\w\s.-]", "", formatted_title)
+    formatted_title = re.sub(r"\s+", "_", formatted_title)
+    return formatted_title
+
+
+def load_embedding(embedder_model):
+    #print("EMBEDDER MODEL IS", embedder_model)
+    embedding_list = {
+        "contentvec": "contentvec_base.pt",
+        "hubert": "hubert_base.pt",
+    }
+    
+    try:
+        this_dir = Path(__file__).resolve().parent.parent.parent.parent.parent
+        model_path = this_dir / "models" / "rvc_base" / embedding_list[embedder_model]
+        #print("MODEL PATH IS", model_path)
+        
+        # Load model ensemble and task
+        models = checkpoint_utils.load_model_ensemble_and_task(
+            [f"{model_path}"],
+            suffix="",
+        )
+        
+        #print(f"Embedding model {embedder_model} loaded successfully.")
+        return models
+    except KeyError as e:
+        logging.error(f"Invalid embedder model name: {embedder_model}")
+        raise ValueError(f"Invalid embedder model name: {embedder_model}") from e
+    except Exception as e:
+        logging.error(f"Error loading embedding model: {e}")
+        raise RuntimeError(f"Error loading embedding model: {e}") from e