Upload 16 files

app.py

@@ -0,0 +1,108 @@
+from models import SynthesizerTrn
+from vits_pinyin import VITS_PinYin
+from text import cleaned_text_to_sequence
+from text.symbols import symbols
+import gradio as gr
+import utils
+import torch
+import argparse
+import os
+import re
+import logging
+
+logging.getLogger('numba').setLevel(logging.WARNING)
+limitation = os.getenv("SYSTEM") == "spaces"
+
+
+def create_calback(net_g: SynthesizerTrn, tts_front: VITS_PinYin):
+    def tts_calback(text, dur_scale):
+        if limitation:
+            text_len = len(re.sub("\[([A-Z]{2})\]", "", text))
+            max_len = 150
+            if text_len > max_len:
+                return "Error: Text is too long", None
+
+        phonemes, char_embeds = tts_front.chinese_to_phonemes(text)
+        input_ids = cleaned_text_to_sequence(phonemes)
+        with torch.no_grad():
+            x_tst = torch.LongTensor(input_ids).unsqueeze(0).to(device)
+            x_tst_lengths = torch.LongTensor([len(input_ids)]).to(device)
+            x_tst_prosody = torch.FloatTensor(
+                char_embeds).unsqueeze(0).to(device)
+            audio = net_g.infer(x_tst, x_tst_lengths, x_tst_prosody, noise_scale=0.5,
+                                length_scale=dur_scale)[0][0, 0].data.cpu().float().numpy()
+        del x_tst, x_tst_lengths, x_tst_prosody
+        return "Success", (16000, audio)
+
+    return tts_calback
+
+
+example = [['天空呈现的透心的蓝，像极了当年。总在这样的时候，透过窗棂，心，在天空里无尽的游弋！柔柔的，浓浓的，痴痴的风，牵引起心底灵动的思潮；情愫悠悠，思情绵绵，风里默坐，红尘中的浅醉，诗词中的优柔，任那自在飞花轻似梦的情怀，裁一束霓衣，织就清浅淡薄的安寂。', 1],
+           ['风的影子翻阅过淡蓝色的信笺，柔和的文字浅浅地漫过我安静的眸，一如几朵悠闲的云儿，忽而氤氲成汽，忽而修饰成花，铅华洗尽后的透彻和靓丽，爽爽朗朗，轻轻盈盈', 1],
+           ['时光仿佛有穿越到了从前，在你诗情画意的眼波中，在你舒适浪漫的暇思里，我如风中的思绪徜徉广阔天际，仿佛一片沾染了快乐的羽毛，在云环影绕颤动里浸润着风的呼吸，风的诗韵，那清新的耳语，那婉约的甜蜜，那恬淡的温馨，将一腔情澜染得愈发的缠绵。', 1],]
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--share", action="store_true",
+                        default=False, help="share gradio app")
+    args = parser.parse_args()
+
+    device = torch.device("cpu")
+
+    # pinyin
+    tts_front = VITS_PinYin("./bert", device)
+
+    # config
+    hps = utils.get_hparams_from_file("./configs/bert_vits.json")
+
+    # model
+    net_g = SynthesizerTrn(
+        len(symbols),
+        hps.data.filter_length // 2 + 1,
+        hps.train.segment_size // hps.data.hop_length,
+        **hps.model)
+
+    model_path = "vits_bert_model.pth"
+    utils.load_model(model_path, net_g)
+    net_g.eval()
+    net_g.to(device)
+
+    tts_calback = create_calback(net_g, tts_front)
+
+    app = gr.Blocks()
+    with app:
+        gr.Markdown("# Best TTS based on BERT and VITS with some Natural Speech Features Of Microsoft\n\n"
+                    "code : github.com/PlayVoice/vits_chinese\n\n"
+                    "1, Hidden prosody embedding from BERT，get natural pauses in grammar\n\n"
+                    "2, Infer loss from NaturalSpeech，get less sound error\n\n"
+                    "3, Framework of VITS，get high audio quality\n\n"
+                    "<video id='video' controls='' preload='yes'>\n\n"
+                    "<source id='mp4' src='https://user-images.githubusercontent.com/16432329/220678182-4775dec8-9229-4578-870f-2eebc3a5d660.mp4' type='video/mp4'>\n\n"
+                    "</videos>\n\n"
+                    )
+
+        with gr.Tabs():
+            with gr.TabItem("TTS"):
+                with gr.Row():
+                    with gr.Column():
+                        textbox = gr.TextArea(label="Text",
+                                              placeholder="Type your sentence here (Maximum 150 words)",
+                                              value="中文语音合成", elem_id=f"tts-input")
+                        duration_slider = gr.Slider(minimum=0.1, maximum=5, value=1, step=0.1,
+                                                    label='速度 Speed')
+                    with gr.Column():
+                        text_output = gr.Textbox(label="Message")
+                        audio_output = gr.Audio(
+                            label="Output Audio", elem_id="tts-audio")
+                        btn = gr.Button("Generate!")
+                        btn.click(tts_calback,
+                                  inputs=[textbox, duration_slider],
+                                  outputs=[text_output, audio_output])
+            gr.Examples(
+                examples=example,
+                inputs=[textbox, duration_slider],
+                outputs=[text_output, audio_output],
+                fn=tts_calback
+            )
+    app.queue(concurrency_count=3).launch(show_api=False, share=args.share)

attentions.py

@@ -0,0 +1,417 @@
+import copy
+import math
+import numpy as np
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+import commons
+import modules
+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=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 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):
+        # 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,
+                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()
+        # Concat columns of pad to shift from relative to absolute indexing.
+        x = F.pad(x, commons.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, commons.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.size()
+        # padd along column
+        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)])
+        # add 0's in the beginning that will skew the elements after reshape
+        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):
+        """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, 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

bert/ProsodyModel.py

@@ -0,0 +1,75 @@
+import os
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from transformers import BertModel, BertConfig, BertTokenizer
+
+
+class CharEmbedding(nn.Module):
+    def __init__(self, model_dir):
+        super().__init__()
+        self.tokenizer = BertTokenizer.from_pretrained(model_dir)
+        self.bert_config = BertConfig.from_pretrained(model_dir)
+        self.hidden_size = self.bert_config.hidden_size
+        self.bert = BertModel(self.bert_config)
+        self.proj = nn.Linear(self.hidden_size, 256)
+        self.linear = nn.Linear(256, 3)
+
+    def text2Token(self, text):
+        token = self.tokenizer.tokenize(text)
+        txtid = self.tokenizer.convert_tokens_to_ids(token)
+        return txtid
+
+    def forward(self, inputs_ids, inputs_masks, tokens_type_ids):
+        out_seq = self.bert(input_ids=inputs_ids,
+                            attention_mask=inputs_masks,
+                            token_type_ids=tokens_type_ids)[0]
+        out_seq = self.proj(out_seq)
+        return out_seq
+
+
+class TTSProsody(object):
+    def __init__(self, path, device):
+        self.device = device
+        self.char_model = CharEmbedding(path)
+        self.char_model.load_state_dict(
+            torch.load(
+                os.path.join(path, 'prosody_model.pt'),
+                map_location="cpu"
+            ),
+            strict=False
+        )
+        self.char_model.eval()
+        self.char_model.to(self.device)
+
+    def get_char_embeds(self, text):
+        input_ids = self.char_model.text2Token(text)
+        input_masks = [1] * len(input_ids)
+        type_ids = [0] * len(input_ids)
+        input_ids = torch.LongTensor([input_ids]).to(self.device)
+        input_masks = torch.LongTensor([input_masks]).to(self.device)
+        type_ids = torch.LongTensor([type_ids]).to(self.device)
+
+        with torch.no_grad():
+            char_embeds = self.char_model(
+                input_ids, input_masks, type_ids).squeeze(0).cpu()
+        return char_embeds
+
+    def expand_for_phone(self, char_embeds, length):  # length of phones for char
+        assert char_embeds.size(0) == len(length)
+        expand_vecs = list()
+        for vec, leng in zip(char_embeds, length):
+            vec = vec.expand(leng, -1)
+            expand_vecs.append(vec)
+        expand_embeds = torch.cat(expand_vecs, 0)
+        assert expand_embeds.size(0) == sum(length)
+        return expand_embeds.numpy()
+
+
+if __name__ == "__main__":
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    prosody = TTSProsody('./bert/', device)
+    while True:
+        text = input("请输入文本：")
+        prosody.get_char_embeds(text)

bert/__init__.py

@@ -0,0 +1 @@
+from .ProsodyModel import TTSProsody

bert/config.json

@@ -0,0 +1,19 @@
+{
+  "attention_probs_dropout_prob": 0.1, 
+  "directionality": "bidi", 
+  "hidden_act": "gelu", 
+  "hidden_dropout_prob": 0.1, 
+  "hidden_size": 768, 
+  "initializer_range": 0.02, 
+  "intermediate_size": 3072, 
+  "max_position_embeddings": 512, 
+  "num_attention_heads": 12, 
+  "num_hidden_layers": 12, 
+  "pooler_fc_size": 768, 
+  "pooler_num_attention_heads": 12, 
+  "pooler_num_fc_layers": 3, 
+  "pooler_size_per_head": 128, 
+  "pooler_type": "first_token_transform", 
+  "type_vocab_size": 2, 
+  "vocab_size": 21128
+}

bert/prosody_tool.py

@@ -0,0 +1,426 @@
+def is_chinese(uchar):
+    if uchar >= u'\u4e00' and uchar <= u'\u9fa5':
+        return True
+    else:
+        return False
+
+
+pinyin_dict = {
+    "a": ("^", "a"),
+    "ai": ("^", "ai"),
+    "an": ("^", "an"),
+    "ang": ("^", "ang"),
+    "ao": ("^", "ao"),
+    "ba": ("b", "a"),
+    "bai": ("b", "ai"),
+    "ban": ("b", "an"),
+    "bang": ("b", "ang"),
+    "bao": ("b", "ao"),
+    "be": ("b", "e"),
+    "bei": ("b", "ei"),
+    "ben": ("b", "en"),
+    "beng": ("b", "eng"),
+    "bi": ("b", "i"),
+    "bian": ("b", "ian"),
+    "biao": ("b", "iao"),
+    "bie": ("b", "ie"),
+    "bin": ("b", "in"),
+    "bing": ("b", "ing"),
+    "bo": ("b", "o"),
+    "bu": ("b", "u"),
+    "ca": ("c", "a"),
+    "cai": ("c", "ai"),
+    "can": ("c", "an"),
+    "cang": ("c", "ang"),
+    "cao": ("c", "ao"),
+    "ce": ("c", "e"),
+    "cen": ("c", "en"),
+    "ceng": ("c", "eng"),
+    "cha": ("ch", "a"),
+    "chai": ("ch", "ai"),
+    "chan": ("ch", "an"),
+    "chang": ("ch", "ang"),
+    "chao": ("ch", "ao"),
+    "che": ("ch", "e"),
+    "chen": ("ch", "en"),
+    "cheng": ("ch", "eng"),
+    "chi": ("ch", "iii"),
+    "chong": ("ch", "ong"),
+    "chou": ("ch", "ou"),
+    "chu": ("ch", "u"),
+    "chua": ("ch", "ua"),
+    "chuai": ("ch", "uai"),
+    "chuan": ("ch", "uan"),
+    "chuang": ("ch", "uang"),
+    "chui": ("ch", "uei"),
+    "chun": ("ch", "uen"),
+    "chuo": ("ch", "uo"),
+    "ci": ("c", "ii"),
+    "cong": ("c", "ong"),
+    "cou": ("c", "ou"),
+    "cu": ("c", "u"),
+    "cuan": ("c", "uan"),
+    "cui": ("c", "uei"),
+    "cun": ("c", "uen"),
+    "cuo": ("c", "uo"),
+    "da": ("d", "a"),
+    "dai": ("d", "ai"),
+    "dan": ("d", "an"),
+    "dang": ("d", "ang"),
+    "dao": ("d", "ao"),
+    "de": ("d", "e"),
+    "dei": ("d", "ei"),
+    "den": ("d", "en"),
+    "deng": ("d", "eng"),
+    "di": ("d", "i"),
+    "dia": ("d", "ia"),
+    "dian": ("d", "ian"),
+    "diao": ("d", "iao"),
+    "die": ("d", "ie"),
+    "ding": ("d", "ing"),
+    "diu": ("d", "iou"),
+    "dong": ("d", "ong"),
+    "dou": ("d", "ou"),
+    "du": ("d", "u"),
+    "duan": ("d", "uan"),
+    "dui": ("d", "uei"),
+    "dun": ("d", "uen"),
+    "duo": ("d", "uo"),
+    "e": ("^", "e"),
+    "ei": ("^", "ei"),
+    "en": ("^", "en"),
+    "ng": ("^", "en"),
+    "eng": ("^", "eng"),
+    "er": ("^", "er"),
+    "fa": ("f", "a"),
+    "fan": ("f", "an"),
+    "fang": ("f", "ang"),
+    "fei": ("f", "ei"),
+    "fen": ("f", "en"),
+    "feng": ("f", "eng"),
+    "fo": ("f", "o"),
+    "fou": ("f", "ou"),
+    "fu": ("f", "u"),
+    "ga": ("g", "a"),
+    "gai": ("g", "ai"),
+    "gan": ("g", "an"),
+    "gang": ("g", "ang"),
+    "gao": ("g", "ao"),
+    "ge": ("g", "e"),
+    "gei": ("g", "ei"),
+    "gen": ("g", "en"),
+    "geng": ("g", "eng"),
+    "gong": ("g", "ong"),
+    "gou": ("g", "ou"),
+    "gu": ("g", "u"),
+    "gua": ("g", "ua"),
+    "guai": ("g", "uai"),
+    "guan": ("g", "uan"),
+    "guang": ("g", "uang"),
+    "gui": ("g", "uei"),
+    "gun": ("g", "uen"),
+    "guo": ("g", "uo"),
+    "ha": ("h", "a"),
+    "hai": ("h", "ai"),
+    "han": ("h", "an"),
+    "hang": ("h", "ang"),
+    "hao": ("h", "ao"),
+    "he": ("h", "e"),
+    "hei": ("h", "ei"),
+    "hen": ("h", "en"),
+    "heng": ("h", "eng"),
+    "hong": ("h", "ong"),
+    "hou": ("h", "ou"),
+    "hu": ("h", "u"),
+    "hua": ("h", "ua"),
+    "huai": ("h", "uai"),
+    "huan": ("h", "uan"),
+    "huang": ("h", "uang"),
+    "hui": ("h", "uei"),
+    "hun": ("h", "uen"),
+    "huo": ("h", "uo"),
+    "ji": ("j", "i"),
+    "jia": ("j", "ia"),
+    "jian": ("j", "ian"),
+    "jiang": ("j", "iang"),
+    "jiao": ("j", "iao"),
+    "jie": ("j", "ie"),
+    "jin": ("j", "in"),
+    "jing": ("j", "ing"),
+    "jiong": ("j", "iong"),
+    "jiu": ("j", "iou"),
+    "ju": ("j", "v"),
+    "juan": ("j", "van"),
+    "jue": ("j", "ve"),
+    "jun": ("j", "vn"),
+    "ka": ("k", "a"),
+    "kai": ("k", "ai"),
+    "kan": ("k", "an"),
+    "kang": ("k", "ang"),
+    "kao": ("k", "ao"),
+    "ke": ("k", "e"),
+    "kei": ("k", "ei"),
+    "ken": ("k", "en"),
+    "keng": ("k", "eng"),
+    "kong": ("k", "ong"),
+    "kou": ("k", "ou"),
+    "ku": ("k", "u"),
+    "kua": ("k", "ua"),
+    "kuai": ("k", "uai"),
+    "kuan": ("k", "uan"),
+    "kuang": ("k", "uang"),
+    "kui": ("k", "uei"),
+    "kun": ("k", "uen"),
+    "kuo": ("k", "uo"),
+    "la": ("l", "a"),
+    "lai": ("l", "ai"),
+    "lan": ("l", "an"),
+    "lang": ("l", "ang"),
+    "lao": ("l", "ao"),
+    "le": ("l", "e"),
+    "lei": ("l", "ei"),
+    "leng": ("l", "eng"),
+    "li": ("l", "i"),
+    "lia": ("l", "ia"),
+    "lian": ("l", "ian"),
+    "liang": ("l", "iang"),
+    "liao": ("l", "iao"),
+    "lie": ("l", "ie"),
+    "lin": ("l", "in"),
+    "ling": ("l", "ing"),
+    "liu": ("l", "iou"),
+    "lo": ("l", "o"),
+    "long": ("l", "ong"),
+    "lou": ("l", "ou"),
+    "lu": ("l", "u"),
+    "lv": ("l", "v"),
+    "luan": ("l", "uan"),
+    "lve": ("l", "ve"),
+    "lue": ("l", "ve"),
+    "lun": ("l", "uen"),
+    "luo": ("l", "uo"),
+    "ma": ("m", "a"),
+    "mai": ("m", "ai"),
+    "man": ("m", "an"),
+    "mang": ("m", "ang"),
+    "mao": ("m", "ao"),
+    "me": ("m", "e"),
+    "mei": ("m", "ei"),
+    "men": ("m", "en"),
+    "meng": ("m", "eng"),
+    "mi": ("m", "i"),
+    "mian": ("m", "ian"),
+    "miao": ("m", "iao"),
+    "mie": ("m", "ie"),
+    "min": ("m", "in"),
+    "ming": ("m", "ing"),
+    "miu": ("m", "iou"),
+    "mo": ("m", "o"),
+    "mou": ("m", "ou"),
+    "mu": ("m", "u"),
+    "na": ("n", "a"),
+    "nai": ("n", "ai"),
+    "nan": ("n", "an"),
+    "nang": ("n", "ang"),
+    "nao": ("n", "ao"),
+    "ne": ("n", "e"),
+    "nei": ("n", "ei"),
+    "nen": ("n", "en"),
+    "neng": ("n", "eng"),
+    "ni": ("n", "i"),
+    "nia": ("n", "ia"),
+    "nian": ("n", "ian"),
+    "niang": ("n", "iang"),
+    "niao": ("n", "iao"),
+    "nie": ("n", "ie"),
+    "nin": ("n", "in"),
+    "ning": ("n", "ing"),
+    "niu": ("n", "iou"),
+    "nong": ("n", "ong"),
+    "nou": ("n", "ou"),
+    "nu": ("n", "u"),
+    "nv": ("n", "v"),
+    "nuan": ("n", "uan"),
+    "nve": ("n", "ve"),
+    "nue": ("n", "ve"),
+    "nuo": ("n", "uo"),
+    "o": ("^", "o"),
+    "ou": ("^", "ou"),
+    "pa": ("p", "a"),
+    "pai": ("p", "ai"),
+    "pan": ("p", "an"),
+    "pang": ("p", "ang"),
+    "pao": ("p", "ao"),
+    "pe": ("p", "e"),
+    "pei": ("p", "ei"),
+    "pen": ("p", "en"),
+    "peng": ("p", "eng"),
+    "pi": ("p", "i"),
+    "pian": ("p", "ian"),
+    "piao": ("p", "iao"),
+    "pie": ("p", "ie"),
+    "pin": ("p", "in"),
+    "ping": ("p", "ing"),
+    "po": ("p", "o"),
+    "pou": ("p", "ou"),
+    "pu": ("p", "u"),
+    "qi": ("q", "i"),
+    "qia": ("q", "ia"),
+    "qian": ("q", "ian"),
+    "qiang": ("q", "iang"),
+    "qiao": ("q", "iao"),
+    "qie": ("q", "ie"),
+    "qin": ("q", "in"),
+    "qing": ("q", "ing"),
+    "qiong": ("q", "iong"),
+    "qiu": ("q", "iou"),
+    "qu": ("q", "v"),
+    "quan": ("q", "van"),
+    "que": ("q", "ve"),
+    "qun": ("q", "vn"),
+    "ran": ("r", "an"),
+    "rang": ("r", "ang"),
+    "rao": ("r", "ao"),
+    "re": ("r", "e"),
+    "ren": ("r", "en"),
+    "reng": ("r", "eng"),
+    "ri": ("r", "iii"),
+    "rong": ("r", "ong"),
+    "rou": ("r", "ou"),
+    "ru": ("r", "u"),
+    "rua": ("r", "ua"),
+    "ruan": ("r", "uan"),
+    "rui": ("r", "uei"),
+    "run": ("r", "uen"),
+    "ruo": ("r", "uo"),
+    "sa": ("s", "a"),
+    "sai": ("s", "ai"),
+    "san": ("s", "an"),
+    "sang": ("s", "ang"),
+    "sao": ("s", "ao"),
+    "se": ("s", "e"),
+    "sen": ("s", "en"),
+    "seng": ("s", "eng"),
+    "sha": ("sh", "a"),
+    "shai": ("sh", "ai"),
+    "shan": ("sh", "an"),
+    "shang": ("sh", "ang"),
+    "shao": ("sh", "ao"),
+    "she": ("sh", "e"),
+    "shei": ("sh", "ei"),
+    "shen": ("sh", "en"),
+    "sheng": ("sh", "eng"),
+    "shi": ("sh", "iii"),
+    "shou": ("sh", "ou"),
+    "shu": ("sh", "u"),
+    "shua": ("sh", "ua"),
+    "shuai": ("sh", "uai"),
+    "shuan": ("sh", "uan"),
+    "shuang": ("sh", "uang"),
+    "shui": ("sh", "uei"),
+    "shun": ("sh", "uen"),
+    "shuo": ("sh", "uo"),
+    "si": ("s", "ii"),
+    "song": ("s", "ong"),
+    "sou": ("s", "ou"),
+    "su": ("s", "u"),
+    "suan": ("s", "uan"),
+    "sui": ("s", "uei"),
+    "sun": ("s", "uen"),
+    "suo": ("s", "uo"),
+    "ta": ("t", "a"),
+    "tai": ("t", "ai"),
+    "tan": ("t", "an"),
+    "tang": ("t", "ang"),
+    "tao": ("t", "ao"),
+    "te": ("t", "e"),
+    "tei": ("t", "ei"),
+    "teng": ("t", "eng"),
+    "ti": ("t", "i"),
+    "tian": ("t", "ian"),
+    "tiao": ("t", "iao"),
+    "tie": ("t", "ie"),
+    "ting": ("t", "ing"),
+    "tong": ("t", "ong"),
+    "tou": ("t", "ou"),
+    "tu": ("t", "u"),
+    "tuan": ("t", "uan"),
+    "tui": ("t", "uei"),
+    "tun": ("t", "uen"),
+    "tuo": ("t", "uo"),
+    "wa": ("^", "ua"),
+    "wai": ("^", "uai"),
+    "wan": ("^", "uan"),
+    "wang": ("^", "uang"),
+    "wei": ("^", "uei"),
+    "wen": ("^", "uen"),
+    "weng": ("^", "ueng"),
+    "wo": ("^", "uo"),
+    "wu": ("^", "u"),
+    "xi": ("x", "i"),
+    "xia": ("x", "ia"),
+    "xian": ("x", "ian"),
+    "xiang": ("x", "iang"),
+    "xiao": ("x", "iao"),
+    "xie": ("x", "ie"),
+    "xin": ("x", "in"),
+    "xing": ("x", "ing"),
+    "xiong": ("x", "iong"),
+    "xiu": ("x", "iou"),
+    "xu": ("x", "v"),
+    "xuan": ("x", "van"),
+    "xue": ("x", "ve"),
+    "xun": ("x", "vn"),
+    "ya": ("^", "ia"),
+    "yan": ("^", "ian"),
+    "yang": ("^", "iang"),
+    "yao": ("^", "iao"),
+    "ye": ("^", "ie"),
+    "yi": ("^", "i"),
+    "yin": ("^", "in"),
+    "ying": ("^", "ing"),
+    "yo": ("^", "iou"),
+    "yong": ("^", "iong"),
+    "you": ("^", "iou"),
+    "yu": ("^", "v"),
+    "yuan": ("^", "van"),
+    "yue": ("^", "ve"),
+    "yun": ("^", "vn"),
+    "za": ("z", "a"),
+    "zai": ("z", "ai"),
+    "zan": ("z", "an"),
+    "zang": ("z", "ang"),
+    "zao": ("z", "ao"),
+    "ze": ("z", "e"),
+    "zei": ("z", "ei"),
+    "zen": ("z", "en"),
+    "zeng": ("z", "eng"),
+    "zha": ("zh", "a"),
+    "zhai": ("zh", "ai"),
+    "zhan": ("zh", "an"),
+    "zhang": ("zh", "ang"),
+    "zhao": ("zh", "ao"),
+    "zhe": ("zh", "e"),
+    "zhei": ("zh", "ei"),
+    "zhen": ("zh", "en"),
+    "zheng": ("zh", "eng"),
+    "zhi": ("zh", "iii"),
+    "zhong": ("zh", "ong"),
+    "zhou": ("zh", "ou"),
+    "zhu": ("zh", "u"),
+    "zhua": ("zh", "ua"),
+    "zhuai": ("zh", "uai"),
+    "zhuan": ("zh", "uan"),
+    "zhuang": ("zh", "uang"),
+    "zhui": ("zh", "uei"),
+    "zhun": ("zh", "uen"),
+    "zhuo": ("zh", "uo"),
+    "zi": ("z", "ii"),
+    "zong": ("z", "ong"),
+    "zou": ("z", "ou"),
+    "zu": ("z", "u"),
+    "zuan": ("z", "uan"),
+    "zui": ("z", "uei"),
+    "zun": ("z", "uen"),
+    "zuo": ("z", "uo"),
+}

commons.py

@@ -0,0 +1,163 @@
+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 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

configs/bert_vits.json

@@ -0,0 +1,50 @@
+{
+  "train": {
+    "log_interval": 100,
+    "eval_interval": 10000,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 8,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 12800,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "training_files":"filelists/train.txt",
+    "validation_files":"filelists/valid.txt",
+    "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,
+    "add_blank": false,
+    "n_speakers": 0
+  },
+  "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
+  }
+}

models.py

@@ -0,0 +1,533 @@
+import copy
+import math
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+import commons
+import modules
+import attentions
+
+from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
+from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
+from commons import init_weights, get_padding
+
+
+class DurationPredictor(nn.Module):
+    def __init__(
+        self, in_channels, filter_channels, kernel_size, p_dropout, gin_channels=0
+    ):
+        super().__init__()
+
+        self.in_channels = in_channels
+        self.filter_channels = filter_channels
+        self.kernel_size = kernel_size
+        self.p_dropout = p_dropout
+        self.gin_channels = gin_channels
+
+        self.drop = nn.Dropout(p_dropout)
+        self.conv_1 = nn.Conv1d(
+            in_channels, filter_channels, kernel_size, padding=kernel_size // 2
+        )
+        self.norm_1 = modules.LayerNorm(filter_channels)
+        self.conv_2 = nn.Conv1d(
+            filter_channels, filter_channels, kernel_size, padding=kernel_size // 2
+        )
+        self.norm_2 = modules.LayerNorm(filter_channels)
+        self.proj = nn.Conv1d(filter_channels, 1, 1)
+
+        if gin_channels != 0:
+            self.cond = nn.Conv1d(gin_channels, in_channels, 1)
+
+    def forward(self, x, x_mask, g=None):
+        x = torch.detach(x)
+        if g is not None:
+            g = torch.detach(g)
+            x = x + self.cond(g)
+        x = self.conv_1(x * x_mask)
+        x = torch.relu(x)
+        x = self.norm_1(x)
+        x = self.drop(x)
+        x = self.conv_2(x * x_mask)
+        x = torch.relu(x)
+        x = self.norm_2(x)
+        x = self.drop(x)
+        x = self.proj(x * x_mask)
+        return x * x_mask
+
+
+class TextEncoder(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)
+        self.emb_bert = nn.Linear(256, hidden_channels)
+        nn.init.normal_(self.emb.weight, 0.0, hidden_channels**-0.5)
+
+        self.encoder = attentions.Encoder(
+            hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout
+        )
+        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
+
+    def forward(self, x, x_lengths, bert):
+        x = self.emb(x) * math.sqrt(self.hidden_channels)  # [b, t, h]
+        b = self.emb_bert(bert)
+        x = x + b
+        x = torch.transpose(x, 1, -1)  # [b, h, t]
+        x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(
+            x.dtype
+        )
+
+        x = self.encoder(x * x_mask, x_mask)
+        stats = self.proj(x) * x_mask
+
+        m, logs = torch.split(stats, self.out_channels, dim=1)
+        return x, m, logs, x_mask
+
+
+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(
+                modules.ResidualCouplingLayer(
+                    channels,
+                    hidden_channels,
+                    kernel_size,
+                    dilation_rate,
+                    n_layers,
+                    gin_channels=gin_channels,
+                    mean_only=True,
+                )
+            )
+            self.flows.append(modules.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
+
+    def remove_weight_norm(self):
+        for i in range(self.n_flows):
+            self.flows[i * 2].remove_weight_norm()
+
+
+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 = modules.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(commons.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
+
+    def remove_weight_norm(self):
+        self.enc.remove_weight_norm()
+
+
+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 = modules.ResBlock1 if resblock == "1" else modules.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, modules.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):
+        for l in self.ups:
+            remove_weight_norm(l)
+        for l in self.resblocks:
+            l.remove_weight_norm()
+        remove_weight_norm(self.conv_pre)
+        remove_weight_norm(self.conv_post)
+
+
+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, modules.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, modules.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,
+        use_sdp=False,
+        **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 = TextEncoder(
+            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, 1, 4, gin_channels=gin_channels
+        )
+        self.dp = DurationPredictor(
+            hidden_channels, 256, 3, 0.5, gin_channels=gin_channels
+        )
+        if n_speakers > 1:
+            self.emb_g = nn.Embedding(n_speakers, gin_channels)
+
+    def remove_weight_norm(self):
+        print("Removing weight norm...")
+        self.dec.remove_weight_norm()
+        self.flow.remove_weight_norm()
+        self.enc_q.remove_weight_norm()
+
+
+    def infer(self, x, x_lengths, bert, sid=None, noise_scale=1, length_scale=1, max_len=None):
+        x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, bert)
+        if self.n_speakers > 0:
+            g = self.emb_g(sid).unsqueeze(-1)  # [b, h, 1]
+        else:
+            g = None
+
+        logw = self.dp(x, x_mask, g=g)
+        w = torch.exp(logw) * x_mask * length_scale
+        w_ceil = torch.ceil(w)
+        y_lengths = torch.clamp_min(torch.sum(w_ceil, [1, 2]), 1).long()
+        y_mask = torch.unsqueeze(commons.sequence_mask(y_lengths, None), 1).to(
+            x_mask.dtype
+        )
+        attn_mask = torch.unsqueeze(x_mask, 2) * torch.unsqueeze(y_mask, -1)
+        attn = commons.generate_path(w_ceil, attn_mask)
+
+        m_p = torch.matmul(attn.squeeze(1), m_p.transpose(1, 2)).transpose(
+            1, 2
+        )  # [b, t', t], [b, t, d] -> [b, d, t']
+        logs_p = torch.matmul(attn.squeeze(1), logs_p.transpose(1, 2)).transpose(
+            1, 2
+        )  # [b, t', t], [b, t, d] -> [b, d, t']
+
+        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)

modules.py

@@ -0,0 +1,522 @@
+import copy
+import math
+import numpy as np
+import scipy
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
+from torch.nn.utils import weight_norm, remove_weight_norm
+
+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):
+    """
+    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 = 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)  # [b, cx?, t] -> [b, c, t, ?]
+
+        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

text/__init__.py

@@ -0,0 +1,447 @@
+from text.symbols import symbols
+
+
+# Mappings from symbol to numeric ID and vice versa:
+_symbol_to_id = {s: i for i, s in enumerate(symbols)}
+_id_to_symbol = {i: s for i, s in enumerate(symbols)}
+
+
+def cleaned_text_to_sequence(cleaned_text):
+    """Converts a string of text to a sequence of IDs corresponding to the symbols in the text.
+    Args:
+      text: string to convert to a sequence
+    Returns:
+      List of integers corresponding to the symbols in the text
+    """
+    sequence = [_symbol_to_id[symbol] for symbol in cleaned_text.split()]
+    return sequence
+
+
+def sequence_to_text(sequence):
+    """Converts a sequence of IDs back to a string"""
+    result = ""
+    for symbol_id in sequence:
+        s = _id_to_symbol[symbol_id]
+        result += s
+    return result
+
+
+pinyin_dict = {
+    "a": ("^", "a"),
+    "ai": ("^", "ai"),
+    "an": ("^", "an"),
+    "ang": ("^", "ang"),
+    "ao": ("^", "ao"),
+    "ba": ("b", "a"),
+    "bai": ("b", "ai"),
+    "ban": ("b", "an"),
+    "bang": ("b", "ang"),
+    "bao": ("b", "ao"),
+    "be": ("b", "e"),
+    "bei": ("b", "ei"),
+    "ben": ("b", "en"),
+    "beng": ("b", "eng"),
+    "bi": ("b", "i"),
+    "bian": ("b", "ian"),
+    "biao": ("b", "iao"),
+    "bie": ("b", "ie"),
+    "bin": ("b", "in"),
+    "bing": ("b", "ing"),
+    "bo": ("b", "o"),
+    "bu": ("b", "u"),
+    "ca": ("c", "a"),
+    "cai": ("c", "ai"),
+    "can": ("c", "an"),
+    "cang": ("c", "ang"),
+    "cao": ("c", "ao"),
+    "ce": ("c", "e"),
+    "cen": ("c", "en"),
+    "ceng": ("c", "eng"),
+    "cha": ("ch", "a"),
+    "chai": ("ch", "ai"),
+    "chan": ("ch", "an"),
+    "chang": ("ch", "ang"),
+    "chao": ("ch", "ao"),
+    "che": ("ch", "e"),
+    "chen": ("ch", "en"),
+    "cheng": ("ch", "eng"),
+    "chi": ("ch", "iii"),
+    "chong": ("ch", "ong"),
+    "chou": ("ch", "ou"),
+    "chu": ("ch", "u"),
+    "chua": ("ch", "ua"),
+    "chuai": ("ch", "uai"),
+    "chuan": ("ch", "uan"),
+    "chuang": ("ch", "uang"),
+    "chui": ("ch", "uei"),
+    "chun": ("ch", "uen"),
+    "chuo": ("ch", "uo"),
+    "ci": ("c", "ii"),
+    "cong": ("c", "ong"),
+    "cou": ("c", "ou"),
+    "cu": ("c", "u"),
+    "cuan": ("c", "uan"),
+    "cui": ("c", "uei"),
+    "cun": ("c", "uen"),
+    "cuo": ("c", "uo"),
+    "da": ("d", "a"),
+    "dai": ("d", "ai"),
+    "dan": ("d", "an"),
+    "dang": ("d", "ang"),
+    "dao": ("d", "ao"),
+    "de": ("d", "e"),
+    "dei": ("d", "ei"),
+    "den": ("d", "en"),
+    "deng": ("d", "eng"),
+    "di": ("d", "i"),
+    "dia": ("d", "ia"),
+    "dian": ("d", "ian"),
+    "diao": ("d", "iao"),
+    "die": ("d", "ie"),
+    "ding": ("d", "ing"),
+    "diu": ("d", "iou"),
+    "dong": ("d", "ong"),
+    "dou": ("d", "ou"),
+    "du": ("d", "u"),
+    "duan": ("d", "uan"),
+    "dui": ("d", "uei"),
+    "dun": ("d", "uen"),
+    "duo": ("d", "uo"),
+    "e": ("^", "e"),
+    "ei": ("^", "ei"),
+    "en": ("^", "en"),
+    "ng": ("^", "en"),
+    "eng": ("^", "eng"),
+    "er": ("^", "er"),
+    "fa": ("f", "a"),
+    "fan": ("f", "an"),
+    "fang": ("f", "ang"),
+    "fei": ("f", "ei"),
+    "fen": ("f", "en"),
+    "feng": ("f", "eng"),
+    "fo": ("f", "o"),
+    "fou": ("f", "ou"),
+    "fu": ("f", "u"),
+    "ga": ("g", "a"),
+    "gai": ("g", "ai"),
+    "gan": ("g", "an"),
+    "gang": ("g", "ang"),
+    "gao": ("g", "ao"),
+    "ge": ("g", "e"),
+    "gei": ("g", "ei"),
+    "gen": ("g", "en"),
+    "geng": ("g", "eng"),
+    "gong": ("g", "ong"),
+    "gou": ("g", "ou"),
+    "gu": ("g", "u"),
+    "gua": ("g", "ua"),
+    "guai": ("g", "uai"),
+    "guan": ("g", "uan"),
+    "guang": ("g", "uang"),
+    "gui": ("g", "uei"),
+    "gun": ("g", "uen"),
+    "guo": ("g", "uo"),
+    "ha": ("h", "a"),
+    "hai": ("h", "ai"),
+    "han": ("h", "an"),
+    "hang": ("h", "ang"),
+    "hao": ("h", "ao"),
+    "he": ("h", "e"),
+    "hei": ("h", "ei"),
+    "hen": ("h", "en"),
+    "heng": ("h", "eng"),
+    "hong": ("h", "ong"),
+    "hou": ("h", "ou"),
+    "hu": ("h", "u"),
+    "hua": ("h", "ua"),
+    "huai": ("h", "uai"),
+    "huan": ("h", "uan"),
+    "huang": ("h", "uang"),
+    "hui": ("h", "uei"),
+    "hun": ("h", "uen"),
+    "huo": ("h", "uo"),
+    "ji": ("j", "i"),
+    "jia": ("j", "ia"),
+    "jian": ("j", "ian"),
+    "jiang": ("j", "iang"),
+    "jiao": ("j", "iao"),
+    "jie": ("j", "ie"),
+    "jin": ("j", "in"),
+    "jing": ("j", "ing"),
+    "jiong": ("j", "iong"),
+    "jiu": ("j", "iou"),
+    "ju": ("j", "v"),
+    "juan": ("j", "van"),
+    "jue": ("j", "ve"),
+    "jun": ("j", "vn"),
+    "ka": ("k", "a"),
+    "kai": ("k", "ai"),
+    "kan": ("k", "an"),
+    "kang": ("k", "ang"),
+    "kao": ("k", "ao"),
+    "ke": ("k", "e"),
+    "kei": ("k", "ei"),
+    "ken": ("k", "en"),
+    "keng": ("k", "eng"),
+    "kong": ("k", "ong"),
+    "kou": ("k", "ou"),
+    "ku": ("k", "u"),
+    "kua": ("k", "ua"),
+    "kuai": ("k", "uai"),
+    "kuan": ("k", "uan"),
+    "kuang": ("k", "uang"),
+    "kui": ("k", "uei"),
+    "kun": ("k", "uen"),
+    "kuo": ("k", "uo"),
+    "la": ("l", "a"),
+    "lai": ("l", "ai"),
+    "lan": ("l", "an"),
+    "lang": ("l", "ang"),
+    "lao": ("l", "ao"),
+    "le": ("l", "e"),
+    "lei": ("l", "ei"),
+    "leng": ("l", "eng"),
+    "li": ("l", "i"),
+    "lia": ("l", "ia"),
+    "lian": ("l", "ian"),
+    "liang": ("l", "iang"),
+    "liao": ("l", "iao"),
+    "lie": ("l", "ie"),
+    "lin": ("l", "in"),
+    "ling": ("l", "ing"),
+    "liu": ("l", "iou"),
+    "lo": ("l", "o"),
+    "long": ("l", "ong"),
+    "lou": ("l", "ou"),
+    "lu": ("l", "u"),
+    "lv": ("l", "v"),
+    "luan": ("l", "uan"),
+    "lve": ("l", "ve"),
+    "lue": ("l", "ve"),
+    "lun": ("l", "uen"),
+    "luo": ("l", "uo"),
+    "ma": ("m", "a"),
+    "mai": ("m", "ai"),
+    "man": ("m", "an"),
+    "mang": ("m", "ang"),
+    "mao": ("m", "ao"),
+    "me": ("m", "e"),
+    "mei": ("m", "ei"),
+    "men": ("m", "en"),
+    "meng": ("m", "eng"),
+    "mi": ("m", "i"),
+    "mian": ("m", "ian"),
+    "miao": ("m", "iao"),
+    "mie": ("m", "ie"),
+    "min": ("m", "in"),
+    "ming": ("m", "ing"),
+    "miu": ("m", "iou"),
+    "mo": ("m", "o"),
+    "mou": ("m", "ou"),
+    "mu": ("m", "u"),
+    "na": ("n", "a"),
+    "nai": ("n", "ai"),
+    "nan": ("n", "an"),
+    "nang": ("n", "ang"),
+    "nao": ("n", "ao"),
+    "ne": ("n", "e"),
+    "nei": ("n", "ei"),
+    "nen": ("n", "en"),
+    "neng": ("n", "eng"),
+    "ni": ("n", "i"),
+    "nia": ("n", "ia"),
+    "nian": ("n", "ian"),
+    "niang": ("n", "iang"),
+    "niao": ("n", "iao"),
+    "nie": ("n", "ie"),
+    "nin": ("n", "in"),
+    "ning": ("n", "ing"),
+    "niu": ("n", "iou"),
+    "nong": ("n", "ong"),
+    "nou": ("n", "ou"),
+    "nu": ("n", "u"),
+    "nv": ("n", "v"),
+    "nuan": ("n", "uan"),
+    "nve": ("n", "ve"),
+    "nue": ("n", "ve"),
+    "nuo": ("n", "uo"),
+    "o": ("^", "o"),
+    "ou": ("^", "ou"),
+    "pa": ("p", "a"),
+    "pai": ("p", "ai"),
+    "pan": ("p", "an"),
+    "pang": ("p", "ang"),
+    "pao": ("p", "ao"),
+    "pe": ("p", "e"),
+    "pei": ("p", "ei"),
+    "pen": ("p", "en"),
+    "peng": ("p", "eng"),
+    "pi": ("p", "i"),
+    "pian": ("p", "ian"),
+    "piao": ("p", "iao"),
+    "pie": ("p", "ie"),
+    "pin": ("p", "in"),
+    "ping": ("p", "ing"),
+    "po": ("p", "o"),
+    "pou": ("p", "ou"),
+    "pu": ("p", "u"),
+    "qi": ("q", "i"),
+    "qia": ("q", "ia"),
+    "qian": ("q", "ian"),
+    "qiang": ("q", "iang"),
+    "qiao": ("q", "iao"),
+    "qie": ("q", "ie"),
+    "qin": ("q", "in"),
+    "qing": ("q", "ing"),
+    "qiong": ("q", "iong"),
+    "qiu": ("q", "iou"),
+    "qu": ("q", "v"),
+    "quan": ("q", "van"),
+    "que": ("q", "ve"),
+    "qun": ("q", "vn"),
+    "ran": ("r", "an"),
+    "rang": ("r", "ang"),
+    "rao": ("r", "ao"),
+    "re": ("r", "e"),
+    "ren": ("r", "en"),
+    "reng": ("r", "eng"),
+    "ri": ("r", "iii"),
+    "rong": ("r", "ong"),
+    "rou": ("r", "ou"),
+    "ru": ("r", "u"),
+    "rua": ("r", "ua"),
+    "ruan": ("r", "uan"),
+    "rui": ("r", "uei"),
+    "run": ("r", "uen"),
+    "ruo": ("r", "uo"),
+    "sa": ("s", "a"),
+    "sai": ("s", "ai"),
+    "san": ("s", "an"),
+    "sang": ("s", "ang"),
+    "sao": ("s", "ao"),
+    "se": ("s", "e"),
+    "sen": ("s", "en"),
+    "seng": ("s", "eng"),
+    "sha": ("sh", "a"),
+    "shai": ("sh", "ai"),
+    "shan": ("sh", "an"),
+    "shang": ("sh", "ang"),
+    "shao": ("sh", "ao"),
+    "she": ("sh", "e"),
+    "shei": ("sh", "ei"),
+    "shen": ("sh", "en"),
+    "sheng": ("sh", "eng"),
+    "shi": ("sh", "iii"),
+    "shou": ("sh", "ou"),
+    "shu": ("sh", "u"),
+    "shua": ("sh", "ua"),
+    "shuai": ("sh", "uai"),
+    "shuan": ("sh", "uan"),
+    "shuang": ("sh", "uang"),
+    "shui": ("sh", "uei"),
+    "shun": ("sh", "uen"),
+    "shuo": ("sh", "uo"),
+    "si": ("s", "ii"),
+    "song": ("s", "ong"),
+    "sou": ("s", "ou"),
+    "su": ("s", "u"),
+    "suan": ("s", "uan"),
+    "sui": ("s", "uei"),
+    "sun": ("s", "uen"),
+    "suo": ("s", "uo"),
+    "ta": ("t", "a"),
+    "tai": ("t", "ai"),
+    "tan": ("t", "an"),
+    "tang": ("t", "ang"),
+    "tao": ("t", "ao"),
+    "te": ("t", "e"),
+    "tei": ("t", "ei"),
+    "teng": ("t", "eng"),
+    "ti": ("t", "i"),
+    "tian": ("t", "ian"),
+    "tiao": ("t", "iao"),
+    "tie": ("t", "ie"),
+    "ting": ("t", "ing"),
+    "tong": ("t", "ong"),
+    "tou": ("t", "ou"),
+    "tu": ("t", "u"),
+    "tuan": ("t", "uan"),
+    "tui": ("t", "uei"),
+    "tun": ("t", "uen"),
+    "tuo": ("t", "uo"),
+    "wa": ("^", "ua"),
+    "wai": ("^", "uai"),
+    "wan": ("^", "uan"),
+    "wang": ("^", "uang"),
+    "wei": ("^", "uei"),
+    "wen": ("^", "uen"),
+    "weng": ("^", "ueng"),
+    "wo": ("^", "uo"),
+    "wu": ("^", "u"),
+    "xi": ("x", "i"),
+    "xia": ("x", "ia"),
+    "xian": ("x", "ian"),
+    "xiang": ("x", "iang"),
+    "xiao": ("x", "iao"),
+    "xie": ("x", "ie"),
+    "xin": ("x", "in"),
+    "xing": ("x", "ing"),
+    "xiong": ("x", "iong"),
+    "xiu": ("x", "iou"),
+    "xu": ("x", "v"),
+    "xuan": ("x", "van"),
+    "xue": ("x", "ve"),
+    "xun": ("x", "vn"),
+    "ya": ("^", "ia"),
+    "yan": ("^", "ian"),
+    "yang": ("^", "iang"),
+    "yao": ("^", "iao"),
+    "ye": ("^", "ie"),
+    "yi": ("^", "i"),
+    "yin": ("^", "in"),
+    "ying": ("^", "ing"),
+    "yo": ("^", "iou"),
+    "yong": ("^", "iong"),
+    "you": ("^", "iou"),
+    "yu": ("^", "v"),
+    "yuan": ("^", "van"),
+    "yue": ("^", "ve"),
+    "yun": ("^", "vn"),
+    "za": ("z", "a"),
+    "zai": ("z", "ai"),
+    "zan": ("z", "an"),
+    "zang": ("z", "ang"),
+    "zao": ("z", "ao"),
+    "ze": ("z", "e"),
+    "zei": ("z", "ei"),
+    "zen": ("z", "en"),
+    "zeng": ("z", "eng"),
+    "zha": ("zh", "a"),
+    "zhai": ("zh", "ai"),
+    "zhan": ("zh", "an"),
+    "zhang": ("zh", "ang"),
+    "zhao": ("zh", "ao"),
+    "zhe": ("zh", "e"),
+    "zhei": ("zh", "ei"),
+    "zhen": ("zh", "en"),
+    "zheng": ("zh", "eng"),
+    "zhi": ("zh", "iii"),
+    "zhong": ("zh", "ong"),
+    "zhou": ("zh", "ou"),
+    "zhu": ("zh", "u"),
+    "zhua": ("zh", "ua"),
+    "zhuai": ("zh", "uai"),
+    "zhuan": ("zh", "uan"),
+    "zhuang": ("zh", "uang"),
+    "zhui": ("zh", "uei"),
+    "zhun": ("zh", "uen"),
+    "zhuo": ("zh", "uo"),
+    "zi": ("z", "ii"),
+    "zong": ("z", "ong"),
+    "zou": ("z", "ou"),
+    "zu": ("z", "u"),
+    "zuan": ("z", "uan"),
+    "zui": ("z", "uei"),
+    "zun": ("z", "uen"),
+    "zuo": ("z", "uo"),
+}

text/symbols.py

@@ -0,0 +1,71 @@
+_pause = ["sil", "eos", "sp", "#0", "#1", "#2", "#3"]
+
+_initials = [
+    "^",
+    "b",
+    "c",
+    "ch",
+    "d",
+    "f",
+    "g",
+    "h",
+    "j",
+    "k",
+    "l",
+    "m",
+    "n",
+    "p",
+    "q",
+    "r",
+    "s",
+    "sh",
+    "t",
+    "x",
+    "z",
+    "zh",
+]
+
+_tones = ["1", "2", "3", "4", "5"]
+
+_finals = [
+    "a",
+    "ai",
+    "an",
+    "ang",
+    "ao",
+    "e",
+    "ei",
+    "en",
+    "eng",
+    "er",
+    "i",
+    "ia",
+    "ian",
+    "iang",
+    "iao",
+    "ie",
+    "ii",
+    "iii",
+    "in",
+    "ing",
+    "iong",
+    "iou",
+    "o",
+    "ong",
+    "ou",
+    "u",
+    "ua",
+    "uai",
+    "uan",
+    "uang",
+    "uei",
+    "uen",
+    "ueng",
+    "uo",
+    "v",
+    "van",
+    "ve",
+    "vn",
+]
+
+symbols = _pause + _initials + [i + j for i in _finals for j in _tones]

transforms.py

@@ -0,0 +1,210 @@
+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

utils.py

@@ -0,0 +1,319 @@
+import os
+import glob
+import sys
+import argparse
+import logging
+import json
+import subprocess
+import numpy as np
+from scipy.io.wavfile import read
+import torch
+
+MATPLOTLIB_FLAG = False
+
+logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+logger = logging
+
+
+def load_checkpoint(checkpoint_path, model, optimizer=None):
+    assert os.path.isfile(checkpoint_path)
+    checkpoint_dict = torch.load(checkpoint_path, map_location="cpu")
+    iteration = checkpoint_dict["iteration"]
+    learning_rate = checkpoint_dict["learning_rate"]
+    if optimizer is not None:
+        optimizer.load_state_dict(checkpoint_dict["optimizer"])
+    saved_state_dict = checkpoint_dict["model"]
+    if hasattr(model, "module"):
+        state_dict = model.module.state_dict()
+    else:
+        state_dict = model.state_dict()
+    new_state_dict = {}
+    for k, v in state_dict.items():
+        try:
+            new_state_dict[k] = saved_state_dict[k]
+        except:
+            logger.info("%s is not in the checkpoint" % k)
+            new_state_dict[k] = v
+    if hasattr(model, "module"):
+        model.module.load_state_dict(new_state_dict)
+    else:
+        model.load_state_dict(new_state_dict)
+    logger.info(
+        "Loaded checkpoint '{}' (iteration {})".format(checkpoint_path, iteration)
+    )
+    return model, optimizer, learning_rate, iteration
+
+
+def save_checkpoint(model, optimizer, learning_rate, iteration, checkpoint_path):
+    logger.info(
+        "Saving model and optimizer state at iteration {} to {}".format(
+            iteration, checkpoint_path
+        )
+    )
+    if hasattr(model, "module"):
+        state_dict = model.module.state_dict()
+    else:
+        state_dict = model.state_dict()
+    torch.save(
+        {
+            "model": state_dict,
+            "iteration": iteration,
+            "optimizer": optimizer.state_dict(),
+            "learning_rate": learning_rate,
+        },
+        checkpoint_path,
+    )
+
+
+def load_model(checkpoint_path, model):
+    assert os.path.isfile(checkpoint_path)
+    checkpoint_dict = torch.load(checkpoint_path, map_location="cpu")
+    saved_state_dict = checkpoint_dict["model"]
+    if hasattr(model, "module"):
+        state_dict = model.module.state_dict()
+    else:
+        state_dict = model.state_dict()
+    new_state_dict = {}
+    for k, v in state_dict.items():
+        try:
+            new_state_dict[k] = saved_state_dict[k]
+        except:
+            logger.info("%s is not in the checkpoint" % k)
+            new_state_dict[k] = v
+    if hasattr(model, "module"):
+        model.module.load_state_dict(new_state_dict)
+    else:
+        model.load_state_dict(new_state_dict)
+    return model
+
+
+def save_model(model, checkpoint_path):
+    if hasattr(model, 'module'):
+        state_dict = model.module.state_dict()
+    else:
+        state_dict = model.state_dict()
+    torch.save({'model': state_dict}, checkpoint_path)
+
+
+def summarize(
+    writer,
+    global_step,
+    scalars={},
+    histograms={},
+    images={},
+    audios={},
+    audio_sampling_rate=22050,
+):
+    for k, v in scalars.items():
+        writer.add_scalar(k, v, global_step)
+    for k, v in histograms.items():
+        writer.add_histogram(k, v, global_step)
+    for k, v in images.items():
+        writer.add_image(k, v, global_step, dataformats="HWC")
+    for k, v in audios.items():
+        writer.add_audio(k, v, global_step, audio_sampling_rate)
+
+
+def latest_checkpoint_path(dir_path, regex="G_*.pth"):
+    f_list = glob.glob(os.path.join(dir_path, regex))
+    f_list.sort(key=lambda f: int("".join(filter(str.isdigit, f))))
+    x = f_list[-1]
+    print(x)
+    return x
+
+
+def plot_spectrogram_to_numpy(spectrogram):
+    global MATPLOTLIB_FLAG
+    if not MATPLOTLIB_FLAG:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        MATPLOTLIB_FLAG = True
+        mpl_logger = logging.getLogger("matplotlib")
+        mpl_logger.setLevel(logging.WARNING)
+    import matplotlib.pylab as plt
+    import numpy as np
+
+    fig, ax = plt.subplots(figsize=(10, 2))
+    im = ax.imshow(spectrogram, aspect="auto", origin="lower", interpolation="none")
+    plt.colorbar(im, ax=ax)
+    plt.xlabel("Frames")
+    plt.ylabel("Channels")
+    plt.tight_layout()
+
+    fig.canvas.draw()
+    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
+    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
+    plt.close()
+    return data
+
+
+def plot_alignment_to_numpy(alignment, info=None):
+    global MATPLOTLIB_FLAG
+    if not MATPLOTLIB_FLAG:
+        import matplotlib
+
+        matplotlib.use("Agg")
+        MATPLOTLIB_FLAG = True
+        mpl_logger = logging.getLogger("matplotlib")
+        mpl_logger.setLevel(logging.WARNING)
+    import matplotlib.pylab as plt
+    import numpy as np
+
+    fig, ax = plt.subplots(figsize=(6, 4))
+    im = ax.imshow(
+        alignment.transpose(), aspect="auto", origin="lower", interpolation="none"
+    )
+    fig.colorbar(im, ax=ax)
+    xlabel = "Decoder timestep"
+    if info is not None:
+        xlabel += "\n\n" + info
+    plt.xlabel(xlabel)
+    plt.ylabel("Encoder timestep")
+    plt.tight_layout()
+
+    fig.canvas.draw()
+    data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
+    data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
+    plt.close()
+    return data
+
+
+def load_wav_to_torch(full_path):
+    sampling_rate, data = read(full_path)
+    return torch.FloatTensor(data.astype(np.float32)), sampling_rate
+
+
+def load_filepaths_and_text(filename, split="|"):
+    with open(filename, encoding="utf-8") as f:
+        filepaths_and_text = []
+        for line in f:
+            path_text = line.strip().split(split)
+            filepaths_and_text.append(path_text)
+    return filepaths_and_text
+
+
+def get_hparams(init=True):
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-c",
+        "--config",
+        type=str,
+        default="./configs/bert_vits.json",
+        help="JSON file for configuration",
+    )
+    parser.add_argument("-m", "--model", type=str, required=True, help="Model name")
+
+    args = parser.parse_args()
+    model_dir = os.path.join("./logs", args.model)
+
+    if not os.path.exists(model_dir):
+        os.makedirs(model_dir)
+
+    config_path = args.config
+    config_save_path = os.path.join(model_dir, "config.json")
+    if init:
+        with open(config_path, "r") as f:
+            data = f.read()
+        with open(config_save_path, "w") as f:
+            f.write(data)
+    else:
+        with open(config_save_path, "r") as f:
+            data = f.read()
+    config = json.loads(data)
+
+    hparams = HParams(**config)
+    hparams.model_dir = model_dir
+    return hparams
+
+
+def get_hparams_from_dir(model_dir):
+    config_save_path = os.path.join(model_dir, "config.json")
+    with open(config_save_path, "r") as f:
+        data = f.read()
+    config = json.loads(data)
+
+    hparams = HParams(**config)
+    hparams.model_dir = model_dir
+    return hparams
+
+
+def get_hparams_from_file(config_path):
+    with open(config_path, "r") as f:
+        data = f.read()
+    config = json.loads(data)
+
+    hparams = HParams(**config)
+    return hparams
+
+
+def check_git_hash(model_dir):
+    source_dir = os.path.dirname(os.path.realpath(__file__))
+    if not os.path.exists(os.path.join(source_dir, ".git")):
+        logger.warn(
+            "{} is not a git repository, therefore hash value comparison will be ignored.".format(
+                source_dir
+            )
+        )
+        return
+
+    cur_hash = subprocess.getoutput("git rev-parse HEAD")
+
+    path = os.path.join(model_dir, "githash")
+    if os.path.exists(path):
+        saved_hash = open(path).read()
+        if saved_hash != cur_hash:
+            logger.warn(
+                "git hash values are different. {}(saved) != {}(current)".format(
+                    saved_hash[:8], cur_hash[:8]
+                )
+            )
+    else:
+        open(path, "w").write(cur_hash)
+
+
+def get_logger(model_dir, filename="train.log"):
+    global logger
+    logger = logging.getLogger(os.path.basename(model_dir))
+    logger.setLevel(logging.DEBUG)
+
+    formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
+    if not os.path.exists(model_dir):
+        os.makedirs(model_dir)
+    h = logging.FileHandler(os.path.join(model_dir, filename))
+    h.setLevel(logging.DEBUG)
+    h.setFormatter(formatter)
+    logger.addHandler(h)
+    return logger
+
+
+class HParams:
+    def __init__(self, **kwargs):
+        for k, v in kwargs.items():
+            if type(v) == dict:
+                v = HParams(**v)
+            self[k] = v
+
+    def keys(self):
+        return self.__dict__.keys()
+
+    def items(self):
+        return self.__dict__.items()
+
+    def values(self):
+        return self.__dict__.values()
+
+    def __len__(self):
+        return len(self.__dict__)
+
+    def __getitem__(self, key):
+        return getattr(self, key)
+
+    def __setitem__(self, key, value):
+        return setattr(self, key, value)
+
+    def __contains__(self, key):
+        return key in self.__dict__
+
+    def __repr__(self):
+        return self.__dict__.__repr__()

vits_pinyin.py

@@ -0,0 +1,88 @@
+import re
+
+from pypinyin import Style
+from pypinyin.contrib.neutral_tone import NeutralToneWith5Mixin
+from pypinyin.converter import DefaultConverter
+from pypinyin.core import Pinyin
+
+from text import pinyin_dict
+from bert import TTSProsody
+
+
+class MyConverter(NeutralToneWith5Mixin, DefaultConverter):
+    pass
+
+
+def is_chinese(uchar):
+    if uchar >= u'\u4e00' and uchar <= u'\u9fa5':
+        return True
+    else:
+        return False
+
+
+def clean_chinese(text: str):
+    text = text.strip()
+    text_clean = []
+    for char in text:
+        if (is_chinese(char)):
+            text_clean.append(char)
+        else:
+            if len(text_clean) > 1 and is_chinese(text_clean[-1]):
+                text_clean.append(',')
+    text_clean = ''.join(text_clean).strip(',')
+    return text_clean
+
+
+class VITS_PinYin:
+    def __init__(self, bert_path, device):
+        self.pinyin_parser = Pinyin(MyConverter())
+        self.prosody = TTSProsody(bert_path, device)
+
+    def get_phoneme4pinyin(self, pinyins):
+        result = []
+        count_phone = []
+        for pinyin in pinyins:
+            if pinyin[:-1] in pinyin_dict:
+                tone = pinyin[-1]
+                a = pinyin[:-1]
+                a1, a2 = pinyin_dict[a]
+                result += [a1, a2 + tone]
+                count_phone.append(2)
+        return result, count_phone
+
+    def chinese_to_phonemes(self, text):
+        text = clean_chinese(text)
+        phonemes = ["sil"]
+        chars = ['[PAD]']
+        count_phone = []
+        count_phone.append(1)
+        for subtext in text.split(","):
+            if (len(subtext) == 0):
+                continue
+            pinyins = self.correct_pinyin_tone3(subtext)
+            sub_p, sub_c = self.get_phoneme4pinyin(pinyins)
+            phonemes.extend(sub_p)
+            phonemes.append("sp")
+            count_phone.extend(sub_c)
+            count_phone.append(1)
+            chars.append(subtext)
+            chars.append(',')
+        phonemes.append("sil")
+        count_phone.append(1)
+        chars.append('[PAD]')
+        chars = "".join(chars)
+        char_embeds = self.prosody.get_char_embeds(chars)
+        char_embeds = self.prosody.expand_for_phone(char_embeds, count_phone)
+        return " ".join(phonemes), char_embeds
+
+    def correct_pinyin_tone3(self, text):
+        pinyin_list = [p[0] for p in self.pinyin_parser.pinyin(
+            text, style=Style.TONE3, strict=False, neutral_tone_with_five=True)]
+        if len(pinyin_list) >= 2:
+            for i in range(1, len(pinyin_list)):
+                try:
+                    if re.findall(r'\d', pinyin_list[i-1])[0] == '3' and re.findall(r'\d', pinyin_list[i])[0] == '3':
+                        pinyin_list[i-1] = pinyin_list[i-1].replace('3', '2')
+                except IndexError:
+                    pass
+        return pinyin_list