如何确定每个单词的说话时间

[huwenkai26]

想知道每个字的朗读时间戳该如何做呢

[MaxMax2016]

 def infer(self, x, x_lengths, bert=None, 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)

 def infer(self, x, x_lengths, bert=None, 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, w_ceil

w_ceil即为每个发音单元持续的帧数，"hop_length": 256，即1帧 16 ms

[huwenkai26]

这块的代码小白有点懵，打印w_ceil看起来是个数组的样子