Upload 20 files

Vietnam-F-TTS/LOAD/attentions.py

@@ -0,0 +1,330 @@
+import math
+
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+# import commons
+from LOAD.commons import convert_pad_shape
+from LOAD.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=4,
+        **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 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.attention(q, k, v, mask=attn_mask)
+
+        x = self.conv_o(x)
+        return x
+
+    def attention(self, query, key, value, mask=None):
+        # reshape [b, d, t] -> [b, n_h, t, d_k]
+        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)  # [b, n_h, t_t, t_s]
+        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)
+        )  # [b, n_h, t_t, d_k] -> [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):
+        max_relative_position = 2 * self.window_size + 1
+        # Pad first before slice to avoid using cond ops.
+        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,
+                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()
+        # Concat columns of pad to shift from relative to absolute indexing.
+        x = F.pad(x, convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, 1]]))
+
+        # Concat extra elements so to add up to shape (len+1, 2*len-1).
+        x_flat = x.view([batch, heads, length * 2 * length])
+        x_flat = F.pad(
+            x_flat, convert_pad_shape([[0, 0], [0, 0], [0, length - 1]])
+        )
+
+        # Reshape and slice out the padded elements.
+        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.shape
+        # padd along column
+        x = F.pad(
+            x, convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, length - 1]])
+        )
+        x_flat = x.view([batch, heads, length * length + length * (length - 1)])
+        # add 0's in the beginning that will skew the elements after reshape
+        x_flat = F.pad(x_flat, 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):
+        """Bias for self-attention to encourage attention to close positions.
+        Args:
+          length: an integer scalar.
+        Returns:
+          a Tensor with shape [1, 1, length, 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, 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, convert_pad_shape(padding))
+        return x

Vietnam-F-TTS/LOAD/commons.py

@@ -0,0 +1,162 @@
+import math
+
+import torch
+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 intersperse(lst, item):
+    result = [item] * (len(lst) * 2 + 1)
+    result[1::2] = lst
+    return result
+
+
+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 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

Vietnam-F-TTS/LOAD/flow.py

@@ -0,0 +1,120 @@
+import torch
+from torch import nn
+
+from LOAD.modules import WN
+
+DEFAULT_MIN_BIN_WIDTH = 1e-3
+DEFAULT_MIN_BIN_HEIGHT = 1e-3
+DEFAULT_MIN_DERIVATIVE = 1e-3
+
+
+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
+
+
+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 ResidualCouplingBlock(nn.Module):
+    def __init__(
+        self,
+        channels,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        n_flows=4,
+        gin_channels=0,
+    ):
+        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.n_flows = n_flows
+        self.gin_channels = gin_channels
+
+        self.flows = nn.ModuleList()
+        for i in range(n_flows):
+            self.flows.append(
+                ResidualCouplingLayer(
+                    channels,
+                    hidden_channels,
+                    kernel_size,
+                    dilation_rate,
+                    n_layers,
+                    gin_channels=gin_channels,
+                    mean_only=True,
+                )
+            )
+            self.flows.append(Flip())
+
+    def forward(self, x, x_mask, g=None, reverse=False):
+        if not reverse:
+            for flow in self.flows:
+                x, _ = flow(x, x_mask, g=g, reverse=reverse)
+        else:
+            for flow in reversed(self.flows):
+                x = flow(x, x_mask, g=g, reverse=reverse)
+        return x

Vietnam-F-TTS/LOAD/models.py

@@ -0,0 +1,493 @@
+import math
+
+import torch
+from torch import nn
+from torch.nn import Conv1d, Conv2d, ConvTranspose1d
+from torch.nn import functional as F
+from torch.nn.utils import remove_weight_norm, spectral_norm, weight_norm
+from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence
+
+
+from LOAD.attentions import Encoder
+from LOAD.modules import WN, ResBlock1, ResBlock2, LRELU_SLOPE
+
+from LOAD.commons import get_padding, init_weights, sequence_mask, rand_slice_segments
+from LOAD.flow import ResidualCouplingBlock
+
+
+class PriorEncoder(nn.Module):
+    def __init__(
+        self,
+        n_vocab,
+        out_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+    ):
+        super().__init__()
+        self.n_vocab = n_vocab
+        self.out_channels = out_channels
+        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.emb = nn.Embedding(n_vocab, hidden_channels)
+        nn.init.normal_(self.emb.weight, 0.0, hidden_channels**-0.5)
+        self.pre_attn_encoder = Encoder(
+            hidden_channels,
+            filter_channels,
+            n_heads,
+            n_layers // 2,
+            kernel_size,
+            p_dropout,
+        )
+        self.post_attn_encoder = Encoder(
+            hidden_channels,
+            filter_channels,
+            n_heads,
+            n_layers - n_layers // 2,
+            kernel_size,
+            p_dropout,
+        )
+        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+    def forward(self, x, x_lengths, y_lengths, attn):
+        x = self.emb(x) * math.sqrt(self.hidden_channels)  # [b, t, h]
+        x = torch.transpose(x, 1, -1)  # [b, h, t]
+        x_mask = torch.unsqueeze(sequence_mask(x_lengths, x.size(2)), 1).to(
+            x.dtype
+        )
+        x = self.pre_attn_encoder(x * x_mask, x_mask)
+        y = torch.einsum("bht,blt->bhl", x, attn)
+        y_mask = torch.unsqueeze(sequence_mask(y_lengths, y.size(2)), 1).to(
+            y.dtype
+        )
+        y = self.post_attn_encoder(y * y_mask, y_mask)
+        stats = self.proj(y) * y_mask
+
+        m, logs = torch.split(stats, self.out_channels, dim=1)
+        return y, m, logs, y_mask
+
+
+class PosteriorEncoder(nn.Module):
+    def __init__(
+        self,
+        in_channels,
+        out_channels,
+        hidden_channels,
+        kernel_size,
+        dilation_rate,
+        n_layers,
+        gin_channels=0,
+    ):
+        super().__init__()
+        self.in_channels = in_channels
+        self.out_channels = out_channels
+        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.pre = nn.Conv1d(in_channels, hidden_channels, 1)
+        self.enc = WN(
+            hidden_channels,
+            kernel_size,
+            dilation_rate,
+            n_layers,
+            gin_channels=gin_channels,
+        )
+        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+    def forward(self, x, x_lengths, g=None):
+        x_mask = torch.unsqueeze(sequence_mask(x_lengths, x.size(2)), 1).to(
+            x.dtype
+        )
+        x = self.pre(x) * x_mask
+        x = self.enc(x, x_mask, g=g)
+        stats = self.proj(x) * x_mask
+        m, logs = torch.split(stats, self.out_channels, dim=1)
+        z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask
+        return z, m, logs, x_mask
+
+
+class Generator(torch.nn.Module):
+    def __init__(
+        self,
+        initial_channel,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        gin_channels=0,
+    ):
+        super(Generator, self).__init__()
+        self.num_kernels = len(resblock_kernel_sizes)
+        self.num_upsamples = len(upsample_rates)
+        self.conv_pre = Conv1d(
+            initial_channel, upsample_initial_channel, 7, 1, padding=3
+        )
+        
+        resblock = ResBlock1 if resblock == "1" else ResBlock2
+
+        self.ups = nn.ModuleList()
+        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
+            self.ups.append(
+                weight_norm(
+                    ConvTranspose1d(
+                        upsample_initial_channel // (2**i),
+                        upsample_initial_channel // (2 ** (i + 1)),
+                        k,
+                        u,
+                        padding=(k - u) // 2,
+                    )
+                )
+            )
+
+        self.resblocks = nn.ModuleList()
+        for i in range(len(self.ups)):
+            ch = upsample_initial_channel // (2 ** (i + 1))
+            for j, (k, d) in enumerate(
+                zip(resblock_kernel_sizes, resblock_dilation_sizes)
+            ):
+                self.resblocks.append(resblock(ch, k, d))
+
+        self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
+        self.ups.apply(init_weights)
+
+        if gin_channels != 0:
+            self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
+
+    def forward(self, x, g=None):
+        x = self.conv_pre(x)
+        if g is not None:
+            x = x + self.cond(g)
+
+        for i in range(self.num_upsamples):
+            
+            x = F.leaky_relu(x, LRELU_SLOPE)
+            x = self.ups[i](x)
+            xs = None
+            for j in range(self.num_kernels):
+                if xs is None:
+                    xs = self.resblocks[i * self.num_kernels + j](x)
+                else:
+                    xs += self.resblocks[i * self.num_kernels + j](x)
+            x = xs / self.num_kernels
+        x = F.leaky_relu(x)
+        x = self.conv_post(x)
+        x = torch.tanh(x)
+
+        return x
+
+    def remove_weight_norm(self):
+        print("Removing weight norm...")
+        for l in self.ups:
+            remove_weight_norm(l)
+        for l in self.resblocks:
+            l.remove_weight_norm()
+
+
+class DiscriminatorP(torch.nn.Module):
+    def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False):
+        super(DiscriminatorP, self).__init__()
+        self.period = period
+        self.use_spectral_norm = use_spectral_norm
+        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+        self.convs = nn.ModuleList(
+            [
+                norm_f(
+                    Conv2d(
+                        1,
+                        32,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        32,
+                        128,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        128,
+                        512,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        512,
+                        1024,
+                        (kernel_size, 1),
+                        (stride, 1),
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+                norm_f(
+                    Conv2d(
+                        1024,
+                        1024,
+                        (kernel_size, 1),
+                        1,
+                        padding=(get_padding(kernel_size, 1), 0),
+                    )
+                ),
+            ]
+        )
+        self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))
+
+    def forward(self, x):
+        fmap = []
+
+        # 1d to 2d
+        b, c, t = x.shape
+        if t % self.period != 0:  # pad first
+            n_pad = self.period - (t % self.period)
+            x = F.pad(x, (0, n_pad), "reflect")
+            t = t + n_pad
+        x = x.view(b, c, t // self.period, self.period)
+
+        for l in self.convs:
+            x = l(x)
+
+            x = F.leaky_relu(x, LRELU_SLOPE)
+            fmap.append(x)
+        x = self.conv_post(x)
+        fmap.append(x)
+        x = torch.flatten(x, 1, -1)
+
+        return x, fmap
+
+
+class DiscriminatorS(torch.nn.Module):
+    def __init__(self, use_spectral_norm=False):
+        super(DiscriminatorS, self).__init__()
+        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
+        self.convs = nn.ModuleList(
+            [
+                norm_f(Conv1d(1, 16, 15, 1, padding=7)),
+                norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)),
+                norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)),
+                norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)),
+                norm_f(Conv1d(1024, 1024, 41, 4, groups=256, padding=20)),
+                norm_f(Conv1d(1024, 1024, 5, 1, padding=2)),
+            ]
+        )
+        self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1))
+
+    def forward(self, x):
+        fmap = []
+
+        for l in self.convs:
+            x = l(x)
+            
+            x = F.leaky_relu(x, LRELU_SLOPE)
+            fmap.append(x)
+        x = self.conv_post(x)
+        fmap.append(x)
+        x = torch.flatten(x, 1, -1)
+
+        return x, fmap
+
+
+class MultiPeriodDiscriminator(torch.nn.Module):
+    def __init__(self, use_spectral_norm=False):
+        super(MultiPeriodDiscriminator, self).__init__()
+        periods = [2, 3, 5, 7, 11]
+
+        discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)]
+        discs = discs + [
+            DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods
+        ]
+        self.discriminators = nn.ModuleList(discs)
+
+    def forward(self, y, y_hat):
+        y_d_rs = []
+        y_d_gs = []
+        fmap_rs = []
+        fmap_gs = []
+        for i, d in enumerate(self.discriminators):
+            y_d_r, fmap_r = d(y)
+            y_d_g, fmap_g = d(y_hat)
+            y_d_rs.append(y_d_r)
+            y_d_gs.append(y_d_g)
+            fmap_rs.append(fmap_r)
+            fmap_gs.append(fmap_g)
+
+        return y_d_rs, y_d_gs, fmap_rs, fmap_gs
+
+
+class SynthesizerTrn(nn.Module):
+    """
+    Synthesizer for Training
+    """
+
+    def __init__(
+        self,
+        n_vocab,
+        spec_channels,
+        segment_size,
+        inter_channels,
+        hidden_channels,
+        filter_channels,
+        n_heads,
+        n_layers,
+        kernel_size,
+        p_dropout,
+        resblock,
+        resblock_kernel_sizes,
+        resblock_dilation_sizes,
+        upsample_rates,
+        upsample_initial_channel,
+        upsample_kernel_sizes,
+        n_speakers=0,
+        gin_channels=0,
+        **kwargs
+    ):
+        super().__init__()
+        self.n_vocab = n_vocab
+        self.spec_channels = spec_channels
+        self.inter_channels = inter_channels
+        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.resblock = resblock
+        self.resblock_kernel_sizes = resblock_kernel_sizes
+        self.resblock_dilation_sizes = resblock_dilation_sizes
+        self.upsample_rates = upsample_rates
+        self.upsample_initial_channel = upsample_initial_channel
+        self.upsample_kernel_sizes = upsample_kernel_sizes
+        self.segment_size = segment_size
+        self.n_speakers = n_speakers
+        self.gin_channels = gin_channels
+
+        self.enc_p = PriorEncoder(
+            n_vocab,
+            inter_channels,
+            hidden_channels,
+            filter_channels,
+            n_heads,
+            n_layers,
+            kernel_size,
+            p_dropout,
+        )
+        self.dec = Generator(
+            inter_channels,
+            resblock,
+            resblock_kernel_sizes,
+            resblock_dilation_sizes,
+            upsample_rates,
+            upsample_initial_channel,
+            upsample_kernel_sizes,
+            gin_channels=gin_channels,
+        )
+        self.enc_q = PosteriorEncoder(
+            spec_channels,
+            inter_channels,
+            hidden_channels,
+            5,
+            1,
+            16,
+            gin_channels=gin_channels,
+        )
+        self.flow = ResidualCouplingBlock(
+            inter_channels, hidden_channels, 5, 2, 4, gin_channels=gin_channels
+        )
+
+        if n_speakers > 1:
+            self.emb_g = nn.Embedding(n_speakers, gin_channels)
+
+    def forward(self, x, x_lengths, attn, y, y_lengths, sid=None):
+        x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, y_lengths, attn=attn)
+        if self.n_speakers > 0:
+            g = self.emb_g(sid).unsqueeze(-1)  # [b, h, 1]
+        else:
+            g = None
+
+        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
+        z_p = self.flow(z, y_mask, g=g)
+        z_slice, ids_slice = rand_slice_segments(
+            z, y_lengths, self.segment_size
+        )
+        o = self.dec(z_slice, g=g)
+        l_length = None
+        return (
+            o,
+            l_length,
+            attn,
+            ids_slice,
+            x_mask,
+            y_mask,
+            (z, z_p, m_p, logs_p, m_q, logs_q),
+        )
+
+    def infer(
+        self,
+        x,
+        x_lengths,
+        y_lengths,
+        attn,
+        sid=None,
+        noise_scale=1,
+        max_len=None,
+    ):
+        x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, y_lengths, attn=attn)
+        if self.n_speakers > 0:
+            g = self.emb_g(sid).unsqueeze(-1)  # [b, h, 1]
+        else:
+            g = None
+
+        y_mask = torch.unsqueeze(sequence_mask(y_lengths, attn.shape[1]), 1).to(
+            x_mask.dtype
+        )
+        z_p = m_p + torch.randn_like(m_p) * torch.exp(logs_p) * noise_scale
+        z = self.flow(z_p, y_mask, g=g, reverse=True)
+        o = self.dec((z * y_mask)[:, :, :max_len], g=g)
+        return o, attn, y_mask, (z, z_p, m_p, logs_p)
+
+
+class DurationNet(torch.nn.Module):
+    def __init__(self, vocab_size: int, dim: int, num_layers=2):
+        super().__init__()
+        self.embed = torch.nn.Embedding(vocab_size, embedding_dim=dim)
+        self.rnn = torch.nn.GRU(
+            dim,
+            dim,
+            num_layers=num_layers,
+            batch_first=True,
+            bidirectional=True,
+            dropout=0.2,
+        )
+        self.proj = torch.nn.Linear(2 * dim, 1)
+
+    def forward(self, token, lengths):
+        x = self.embed(token)
+        lengths = lengths.long().cpu()
+        x = pack_padded_sequence(
+            x, lengths=lengths, batch_first=True, enforce_sorted=False
+        )
+        x, _ = self.rnn(x)
+        x, _ = pad_packed_sequence(x, batch_first=True, total_length=token.shape[1])
+        x = self.proj(x)
+        x = torch.nn.functional.softplus(x)
+        return x

Vietnam-F-TTS/LOAD/modules.py

@@ -0,0 +1,356 @@
+import torch
+from torch import nn
+from torch.nn import Conv1d
+from torch.nn import functional as F
+from torch.nn.utils import remove_weight_norm, weight_norm
+
+# import commons
+from LOAD.commons import get_padding, init_weights, fused_add_tanh_sigmoid_multiply
+
+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):
+    """
+    Dialted and Depth-Separable Convolution
+    """
+
+    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.weight_norm(cond_layer, name="weight")
+
+        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.weight_norm(in_layer, name="weight")
+            self.in_layers.append(in_layer)
+
+            # last one is not necessary
+            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.weight_norm(res_skip_layer, name="weight")
+            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 = 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)

Vietnam-F-TTS/TTS.py

@@ -0,0 +1,232 @@
+import torch
+import json
+import re
+import unicodedata
+import numpy as np
+import regex
+
+from types import SimpleNamespace
+from LOAD.models import DurationNet, SynthesizerTrn
+
+import scipy.io.wavfile as wav
+
+
+config_file = "config.json"
+duration_model_path = "duration_model.pth"
+lightspeed_model_path = "gen_630k.pth"
+phone_set_file = "phone_set.json"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+with open(config_file, "rb") as f:
+    hps = json.load(f, object_hook=lambda x: SimpleNamespace(**x))
+
+# Load phone set json file
+with open(phone_set_file, "r") as f:
+    phone_set = json.load(f)
+
+assert phone_set[0][1:-1] == "SEP"
+assert "sil" in phone_set
+sil_idx = phone_set.index("sil")
+
+space_re = regex.compile(r"\s+")
+number_re = regex.compile("([0-9]+)")
+digits = ["không", "một", "hai", "ba", "bốn", "năm", "sáu", "bảy", "tám", "chín"]
+num_re = regex.compile(r"([0-9.,]*[0-9])")
+alphabet = "aàáảãạăằắẳẵặâầấẩẫậeèéẻẽẹêềếểễệiìíỉĩịoòóỏõọôồốổỗộơờớởỡợuùúủũụưừứửữựyỳýỷỹỵbcdđghklmnpqrstvx"
+keep_text_and_num_re = regex.compile(rf"[^\s{alphabet}.,0-9]")
+keep_text_re = regex.compile(rf"[^\s{alphabet}]")
+
+
+def read_number(num: str) -> str:
+    if len(num) == 1:
+        return digits[int(num)]
+    elif len(num) == 2 and num.isdigit():
+        n = int(num)
+        end = digits[n % 10]
+        if n == 10:
+            return "mười"
+        if n % 10 == 5:
+            end = "lăm"
+        if n % 10 == 0:
+            return digits[n // 10] + " mươi"
+        elif n < 20:
+            return "mười " + end
+        else:
+            if n % 10 == 1:
+                end = "mốt"
+            return digits[n // 10] + " mươi " + end
+    elif len(num) == 3 and num.isdigit():
+        n = int(num)
+        if n % 100 == 0:
+            return digits[n // 100] + " trăm"
+        elif num[1] == "0":
+            return digits[n // 100] + " trăm lẻ " + digits[n % 100]
+        else:
+            return digits[n // 100] + " trăm " + read_number(num[1:])
+    elif len(num) >= 4 and len(num) <= 6 and num.isdigit():
+        n = int(num)
+        n1 = n // 1000
+        return read_number(str(n1)) + " ngàn " + read_number(num[-3:])
+    elif "," in num:
+        n1, n2 = num.split(",")
+        return read_number(n1) + " phẩy " + read_number(n2)
+    elif "." in num:
+        parts = num.split(".")
+        if len(parts) == 2:
+            if parts[1] == "000":
+                return read_number(parts[0]) + " ngàn"
+            elif parts[1].startswith("00"):
+                end = digits[int(parts[1][2:])]
+                return read_number(parts[0]) + " ngàn lẻ " + end
+            else:
+                return read_number(parts[0]) + " ngàn " + read_number(parts[1])
+        elif len(parts) == 3:
+            return (
+                read_number(parts[0])
+                + " triệu "
+                + read_number(parts[1])
+                + " ngàn "
+                + read_number(parts[2])
+            )
+    return num
+
+
+def text_to_phone_idx(text):
+    # lowercase
+    text = text.lower()
+    # unicode normalize
+    text = unicodedata.normalize("NFKC", text)
+    text = text.replace(".", " . ")
+    text = text.replace(",", " , ")
+    text = text.replace(";", " ; ")
+    text = text.replace(":", " : ")
+    text = text.replace("!", " ! ")
+    text = text.replace("?", " ? ")
+    text = text.replace("(", " ( ")
+
+    text = num_re.sub(r" \1 ", text)
+    words = text.split()
+    words = [read_number(w) if num_re.fullmatch(w) else w for w in words]
+    text = " ".join(words)
+
+    # remove redundant spaces
+    text = re.sub(r"\s+", " ", text)
+    # remove leading and trailing spaces
+    text = text.strip()
+    # convert words to phone indices
+    tokens = []
+    for c in text:
+        # if c is "," or ".", add <sil> phone
+        if c in ":,.!?;(":
+            tokens.append(sil_idx)
+        elif c in phone_set:
+            tokens.append(phone_set.index(c))
+        elif c == " ":
+            # add <sep> phone
+            tokens.append(0)
+    if tokens[0] != sil_idx:
+        # insert <sil> phone at the beginning
+        tokens = [sil_idx, 0] + tokens
+    if tokens[-1] != sil_idx:
+        tokens = tokens + [0, sil_idx]
+    return tokens
+
+
+def text_to_speech(duration_net, generator, text):
+    # prevent too long text
+    # if len(text) > 500:
+    #     text = text[:500]
+
+    phone_idx = text_to_phone_idx(text)
+    batch = {
+        "phone_idx": np.array([phone_idx]),
+        "phone_length": np.array([len(phone_idx)]),
+    }
+
+    # predict phoneme duration
+    phone_length = torch.from_numpy(batch["phone_length"].copy()).long().to(device)
+    phone_idx = torch.from_numpy(batch["phone_idx"].copy()).long().to(device)
+    with torch.inference_mode():
+        phone_duration = duration_net(phone_idx, phone_length)[:, :, 0] * 1000
+    phone_duration = torch.where(
+        phone_idx == sil_idx, torch.clamp_min(phone_duration, 200), phone_duration
+    )
+    phone_duration = torch.where(phone_idx == 0, 0, phone_duration)
+
+    # generate waveform
+    end_time = torch.cumsum(phone_duration, dim=-1)
+    start_time = end_time - phone_duration
+    start_frame = start_time / 1000 * hps.data.sampling_rate / hps.data.hop_length
+    end_frame = end_time / 1000 * hps.data.sampling_rate / hps.data.hop_length
+    spec_length = end_frame.max(dim=-1).values
+    pos = torch.arange(0, spec_length.item(), device=device)
+    attn = torch.logical_and(
+        pos[None, :, None] >= start_frame[:, None, :],
+        pos[None, :, None] < end_frame[:, None, :],
+    ).float()
+    with torch.inference_mode():
+        y_hat = generator.infer(
+            phone_idx, phone_length, spec_length, attn, max_len=None, noise_scale=0.0
+        )[0]
+    wave = y_hat[0, 0].data.cpu().numpy()
+    return (wave * (2**15)).astype(np.int16)
+
+
+def load_models():
+    duration_net = DurationNet(hps.data.vocab_size, 64, 4).to(device)
+    duration_net.load_state_dict(torch.load(duration_model_path, map_location=device))
+    duration_net = duration_net.eval()
+    generator = SynthesizerTrn(
+        hps.data.vocab_size,
+        hps.data.filter_length // 2 + 1,
+        hps.train.segment_size // hps.data.hop_length,
+        **vars(hps.model),
+    ).to(device)
+    del generator.enc_q
+    ckpt = torch.load(lightspeed_model_path, map_location=device)
+    params = {}
+    for k, v in ckpt["net_g"].items():
+        k = k[7:] if k.startswith("module.") else k
+        params[k] = v
+    generator.load_state_dict(params, strict=False)
+    del ckpt, params
+    generator = generator.eval()
+    return duration_net, generator
+
+
+def speak(text):
+    # Assuming load_models returns duration_net and generator
+    duration_net, generator = load_models()
+    paragraphs = text.split("\n")
+    clips = []  # List to store audio clips
+    max_chunk_length = 400  # Maximum number of characters in each chunk
+
+    for paragraph in paragraphs:
+        paragraph = paragraph.strip()
+        if paragraph == "":
+            continue
+        # Split the paragraph into chunks of maximum length max_chunk_length
+        chunks = [
+            paragraph[i : i + max_chunk_length]
+            for i in range(0, len(paragraph), max_chunk_length)
+        ]
+        for chunk in chunks:
+            clips.append(text_to_speech(duration_net, generator, chunk))
+            # Assuming text_to_speech converts text to audio clip using the models
+            # Append silence if needed
+            # clips.append(silence)
+
+    # Concatenate all audio clips into one
+    y = np.concatenate(clips)
+    # Assuming hps.data.sampling_rate is defined somewhere
+    return hps.data.sampling_rate, y
+
+
+def textToMp3(text, outWAV):
+    sampling_rate, audio = speak(text)
+
+    # Save the audio data to a WAV file
+    wav.write(outWAV, sampling_rate, audio)
+
+
+textToMp3('bây giờ là mấy giờ', 'test.wav')

Vietnam-F-TTS/config.json

@@ -0,0 +1,72 @@
+{
+    "train": {
+        "learning_rate": 2e-4,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-9,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "vocab_size": 256,
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

Vietnam-F-TTS/duration_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e86ab30448a328933b112e5ed6c4c22d7f05f1673528e61d340c98a9cc899eb
+size 1164051

Vietnam-F-TTS/gen_210k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f8485f44f492262492231e90633fead68b5db3f65bd1a73621d618a6f3a173
+size 111280752

Vietnam-F-TTS/gen_543k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e11e4b12e3e9a67ad23ec0cfafbcbd8e810f83d55fb6c38f61a6e9886c94cc5
+size 111280752

Vietnam-F-TTS/gen_630k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fd8e41a8138978e387db561e32ad6ca0798cb09d44aefa239add5ac47e13a6
+size 111280317

Vietnam-F-TTS/phone_set.json

@@ -0,0 +1 @@
+["[SEP]", "a", "b", "c", "d", "e", "g", "h", "i", "k", "l", "m", "n", "o", "p", "q", "r", "s", "sil", "spn", "t", "u", "v", "x", "y", "\u00e0", "\u00e1", "\u00e2", "\u00e3", "\u00e8", "\u00e9", "\u00ea", "\u00ec", "\u00ed", "\u00f2", "\u00f3", "\u00f4", "\u00f5", "\u00f9", "\u00fa", "\u00fd", "\u0103", "\u0111", "\u0129", "\u0169", "\u01a1", "\u01b0", "\u1ea1", "\u1ea3", "\u1ea5", "\u1ea7", "\u1ea9", "\u1eab", "\u1ead", "\u1eaf", "\u1eb1", "\u1eb3", "\u1eb5", "\u1eb7", "\u1eb9", "\u1ebb", "\u1ebd", "\u1ebf", "\u1ec1", "\u1ec3", "\u1ec5", "\u1ec7", "\u1ec9", "\u1ecb", "\u1ecd", "\u1ecf", "\u1ed1", "\u1ed3", "\u1ed5", "\u1ed7", "\u1ed9", "\u1edb", "\u1edd", "\u1edf", "\u1ee1", "\u1ee3", "\u1ee5", "\u1ee7", "\u1ee9", "\u1eeb", "\u1eed", "\u1eef", "\u1ef1", "\u1ef3", "\u1ef5", "\u1ef7", "\u1ef9"]

Vietnam-F-TTS/requirements.txt

@@ -0,0 +1,79 @@
+# requirements.txt
+
+# python 3.9
+
+aiofiles==23.2.1
+altair==5.3.0
+annotated-types==0.6.0
+anyio==4.3.0
+attrs==23.2.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.1
+cycler==0.12.1
+exceptiongroup==1.2.0
+fastapi==0.110.1
+ffmpy==0.3.2
+filelock==3.13.3
+fonttools==4.50.0
+fsspec==2024.3.1
+gradio==4.25.0
+gradio_client==0.15.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+huggingface-hub==0.22.2
+idna==3.6
+importlib_resources==6.4.0
+Jinja2==3.1.3
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.3
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.2.1
+numpy==1.26.4
+orjson==3.10.0
+packaging==24.0
+pandas==2.2.1
+pillow==10.3.0
+pydantic==2.6.4
+pydantic_core==2.16.3
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.34.0
+regex==2023.12.25
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+ruff==0.3.5
+scipy==1.13.0
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
+sympy==1.12
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.2.2
+tqdm==4.66.2
+typer==0.12.0
+typer-cli==0.12.0
+typer-slim==0.12.0
+typing_extensions==4.10.0
+tzdata==2024.1
+urllib3==2.2.1
+uvicorn==0.29.0
+websockets==11.0.3
+zipp==3.18.1

mms-tts-vie/config.json

@@ -0,0 +1,82 @@
+{
+  "activation_dropout": 0.1,
+  "architectures": [
+    "VitsModel"
+  ],
+  "attention_dropout": 0.1,
+  "depth_separable_channels": 2,
+  "depth_separable_num_layers": 3,
+  "duration_predictor_dropout": 0.5,
+  "duration_predictor_filter_channels": 256,
+  "duration_predictor_flow_bins": 10,
+  "duration_predictor_kernel_size": 3,
+  "duration_predictor_num_flows": 4,
+  "duration_predictor_tail_bound": 5.0,
+  "ffn_dim": 768,
+  "ffn_kernel_size": 3,
+  "flow_size": 192,
+  "hidden_act": "relu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 192,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "leaky_relu_slope": 0.1,
+  "model_type": "vits",
+  "noise_scale": 0.667,
+  "noise_scale_duration": 0.8,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 6,
+  "num_speakers": 1,
+  "posterior_encoder_num_wavenet_layers": 16,
+  "prior_encoder_num_flows": 4,
+  "prior_encoder_num_wavenet_layers": 4,
+  "resblock_dilation_sizes": [
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ],
+    [
+      1,
+      3,
+      5
+    ]
+  ],
+  "resblock_kernel_sizes": [
+    3,
+    7,
+    11
+  ],
+  "sampling_rate": 16000,
+  "speaker_embedding_size": 0,
+  "speaking_rate": 1.0,
+  "spectrogram_bins": 513,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0.dev0",
+  "upsample_initial_channel": 512,
+  "upsample_kernel_sizes": [
+    16,
+    16,
+    4,
+    4
+  ],
+  "upsample_rates": [
+    8,
+    8,
+    2,
+    2
+  ],
+  "use_bias": true,
+  "use_stochastic_duration_prediction": true,
+  "vocab_size": 95,
+  "wavenet_dilation_rate": 1,
+  "wavenet_dropout": 0.0,
+  "wavenet_kernel_size": 5,
+  "window_size": 4
+}

mms-tts-vie/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ded90c3e57dc2814fa2cdfe3f9e7a5c28e1223b06c0a260a4495b080762ffd
+size 145271288

mms-tts-vie/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab7d240fb0b6c83474a15affcb70194742af8dbbf79083deb6684e162ff0cb5
+size 145432498

mms-tts-vie/special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "ụ",
+  "unk_token": "<unk>"
+}

mms-tts-vie/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_blank": true,
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "vie",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "ụ",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

mms-tts-vie/vocab.json

@@ -0,0 +1,97 @@
+{
+  " ": 84,
+  "'": 44,
+  "-": 94,
+  "2": 52,
+  "_": 17,
+  "a": 29,
+  "b": 88,
+  "c": 13,
+  "d": 63,
+  "e": 54,
+  "g": 21,
+  "h": 85,
+  "i": 30,
+  "k": 79,
+  "l": 82,
+  "m": 68,
+  "n": 90,
+  "o": 31,
+  "p": 78,
+  "q": 47,
+  "r": 92,
+  "s": 2,
+  "t": 80,
+  "u": 8,
+  "v": 14,
+  "x": 1,
+  "y": 75,
+  "à": 35,
+  "á": 77,
+  "â": 12,
+  "ã": 51,
+  "è": 3,
+  "é": 58,
+  "ê": 91,
+  "ì": 4,
+  "í": 74,
+  "ò": 45,
+  "ó": 56,
+  "ô": 28,
+  "õ": 25,
+  "ù": 38,
+  "ú": 76,
+  "ý": 37,
+  "ă": 89,
+  "đ": 55,
+  "ĩ": 23,
+  "ũ": 70,
+  "ơ": 7,
+  "ư": 9,
+  "ạ": 22,
+  "ả": 24,
+  "ấ": 81,
+  "ầ": 57,
+  "ẩ": 49,
+  "ẫ": 67,
+  "ậ": 87,
+  "ắ": 65,
+  "ằ": 10,
+  "ẳ": 27,
+  "ẵ": 42,
+  "ặ": 5,
+  "ẹ": 72,
+  "ẻ": 20,
+  "ẽ": 66,
+  "ế": 60,
+  "ề": 40,
+  "ể": 69,
+  "ễ": 41,
+  "ệ": 15,
+  "ỉ": 71,
+  "ị": 53,
+  "ọ": 48,
+  "ỏ": 43,
+  "ố": 46,
+  "ồ": 16,
+  "ổ": 34,
+  "ỗ": 73,
+  "ộ": 19,
+  "ớ": 59,
+  "ờ": 36,
+  "ở": 83,
+  "ỡ": 26,
+  "ợ": 93,
+  "ụ": 0,
+  "ủ": 61,
+  "ứ": 6,
+  "ừ": 32,
+  "ử": 62,
+  "ữ": 64,
+  "ự": 50,
+  "ỳ": 11,
+  "ỵ": 18,
+  "ỷ": 86,
+  "ỹ": 33,
+  "–": 39
+}