deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 18:09:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix lint

Browse Source
This commit is contained in:
lyuxiang.lx
2024-12-16 09:54:24 +08:00
parent 6b5931dc70
commit ac70560364
8 changed files with 33 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
cosyvoice/flow/flow.py
View File

@@ -202,7 +202,6 @@ class CausalMaskedDiffWithXvec(torch.nn.Module):
embedding = self.spk_embed_affine_layer(embedding)
# concat text and prompt_text
token_len1, token_len2 = prompt_token.shape[1], token.shape[1]
token, token_len = torch.concat([prompt_token, token], dim=1), prompt_token_len + token_len
mask = (~make_pad_mask(token_len)).unsqueeze(-1).to(embedding)
token = self.input_embedding(torch.clamp(token, min=0)) * mask
@@ -211,7 +210,7 @@ class CausalMaskedDiffWithXvec(torch.nn.Module):
h, h_lengths = self.encoder(token, token_len)
if finalize is False:
h = h[:, :-self.pre_lookahead_len * self.token_mel_ratio]
mel_len1, mel_len2 = prompt_feat.shape[1], h.shape[1] - prompt_feat.shape[1]
mel_len1, mel_len2 = prompt_feat.shape[1], h.shape[1] - prompt_feat.shape[1]
h = self.encoder_proj(h)
# get conditions
@@ -229,4 +228,4 @@ class CausalMaskedDiffWithXvec(torch.nn.Module):
)
feat = feat[:, :, mel_len1:]
assert feat.shape[2] == mel_len2
return feat, None
return feat, None