Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

prosody和phone量化后的维度不同 #3

Open
wcr369 opened this issue Apr 16, 2024 · 2 comments
Open

prosody和phone量化后的维度不同 #3

wcr369 opened this issue Apr 16, 2024 · 2 comments

Comments

@wcr369
Copy link

wcr369 commented Apr 16, 2024

在运行vq_post_emb_a, vq_id_a, _, quantized, spk_embs_a = fa_decoder_v2(enc_out_a, prosody_a, eval_vq=False, vq=True)时,由于phone量化后的维度比prosody大一位导致在outs += out的时候报错,请问这是bug吗

@isMoJo
Copy link

isMoJo commented Apr 24, 2024

我也遇到了相同的问题,求答案~~

@synthere
Copy link

synthere commented Aug 15, 2024

发现部分文件会有这要的问题,试着在forward里加了个补齐没问题了

+            pads = torch.zeros([prosody_feature.shape[0], prosody_feature.shape[1], x.shape[-1] - prosody_feature.shape[-1]])
+            prosody_feature = torch.cat([prosody_feature, pads], dim=2)

            x_timbre = x

            outs, qs, commit_loss, quantized_buf = self.quantize(
                x, prosody_feature, n_quantizers=n_quantizers
            )

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants