Merge 35fac290ba937d032f9b635a14abf667037a1dcb into bfca0f6b2dd9f846c76366be807f01a8873140a0

GPT_SoVITS/AR/models/t2s_model.py

@@ -707,11 +707,12 @@ class Text2SemanticDecoder(nn.Module):
 
             if idx == 0:
                 attn_mask = F.pad(attn_mask[:, :, -1].unsqueeze(-2), (0, 1), value=False)
+                logits = logits[:, :-1]
             else:
                 attn_mask = F.pad(attn_mask, (0, 1), value=False)
 
             if idx < 11:  ###至少预测出10个token不然不给停止（0.4s）
-                logits = logits[:, :-1] 
+                logits = logits[:, :-1]
 
             samples = sample(
                 logits, y, top_k=top_k, top_p=top_p, repetition_penalty=repetition_penalty, temperature=temperature

README.md

@@ -347,7 +347,7 @@ Use v4 from v1/v2/v3 environment:
 
 2. Clone the latest codes from github.
 
-3. Download v4 pretrained models (gsv-v4-pretrained/s2v4.pth, and gsv-v4-pretrained/vocoder.pth) from [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main) and put them into `GPT_SoVITS/pretrained_models`.
+3. Download v4 pretrained models (gsv-v4-pretrained/s2v4.ckpt, and gsv-v4-pretrained/vocoder.pth) from [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main) and put them into `GPT_SoVITS/pretrained_models`.
 
 ## V2Pro Release Notes