deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 09:59:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
zhoubofan.zbf
2024-08-30 00:47:40 +08:00
parent 5f21aef786
commit 53a3c1b17f
4 changed files with 58 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
cosyvoice/flow/flow.py
View File

@@ -107,7 +107,7 @@ class MaskedDiffWithXvec(torch.nn.Module):
# 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)).float().unsqueeze(-1).to(embedding)
mask = (~make_pad_mask(token_len)).to(embedding.dtype).unsqueeze(-1).to(embedding)
token = self.input_embedding(torch.clamp(token, min=0)) * mask
# text encode