Merge branch 'main' into inference_streaming

2026-02-05 01:49:25 +08:00 · 2024-08-29 23:48:02 +08:00
parent 1ab3186799 dcc943db43
commit 662012999a
13 changed files with 750 additions and 1 deletions
--- a/cosyvoice/transformer/encoder.py
+++ b/cosyvoice/transformer/encoder.py
@@ -299,7 +299,7 @@ class BaseEncoder(torch.nn.Module):
               rate.
            3. Currently, nn.Sequential is used to stack all the convolution
               layers in subsampling, we need to rewrite it to make it work
-               with cache, which is not prefered.
+               with cache, which is not preferred.
        Args:
            xs (torch.Tensor): (1, max_len, dim)
            chunk_size (int): decoding chunk size