Compare commits

..

4 Commits

Author SHA1 Message Date
Spr_Aachen
784d7d1cbb
Merge 35fac290ba937d032f9b635a14abf667037a1dcb into c767f0b83b998e996a4d230d86da575a03f54a3f 2026-01-05 09:48:03 +08:00
ChasonJiang
c767f0b83b
修复bug (#2704)
* 修复bug

* fallbak and bug fix
2025-12-30 16:00:21 +08:00
ChasonJiang
9080a967d5
修复采样错误 (#2703) 2025-12-30 15:21:03 +08:00
sushistack
51df9f7384
Fix model file name in README instructions (#2700) 2025-12-25 16:44:21 +08:00
2 changed files with 2 additions and 3 deletions

View File

@ -707,12 +707,11 @@ 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

View File

@ -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.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`.
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`.
## V2Pro Release Notes