Hosein Mohebbi comments

Repositories
Issues
Comments

Results 1 comments of


                                            Hosein Mohebbi

Is there a way to extract embeddings for prosody, content and acoustic details?

I tried this (authors may correct me(?)): ``` with torch.no_grad(): enc_out = fa_encoder(test_wav) vq_post_emb, vq_id, _, quantized, spk_embs = fa_decoder(enc_out, eval_vq=False, vq=True) prosody_code = vq_id[:1] content_code = vq_id[1:3] residual_code =...