Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
chg0901 created a comment on an issue on FunAudioLLM/CosyVoice
如何保存利用价值ptompt音乐学习到的音色为独立的模型？ Jandown ***@***.***> 于 2024年12月20日周五 10:28写道： > 使用2-0.5B模型的自然语言控制，就提示 您正在使用自然语言控制模式, > pretrained_models/CosyVoice2-0.5B模型不支持此模式, 请使用iic/CosyVoice-300M-Instruct...
chg0901 opened an issue on FunAudioLLM/CosyVoice
看起来大家对流式语音的生成以及长文字tts的速度不满, 大家有优化后的版本么
### 参考的issue #### 速度不满 - #755 - #739 - #742 - #723 #### 如何优化批量流式输入输出? - #713 - #700 -
chg0901 created a comment on an issue on FunAudioLLM/CosyVoice
https://github.com/FunAudioLLM/CosyVoice/issues/729#issuecomment-2545399338 - #729 It appears that you're encountering an issue with the absence of the spk2info.pt file in the pretrained_mod...
chg0901 created a comment on an issue on FunAudioLLM/CosyVoice
> 实测下来流式首响基本都要800ms以上，不知道150ms怎么做的 还有其他更快的么, 这个生成效果感觉最后也有概率会破音, 如何避免啊
chg0901 created a comment on an issue on FunAudioLLM/CosyVoice
怎么改呀, 能提个PR么, 如何拼接多段流式语音呢, 更重要的是让使用者无感的来听长语音
chg0901 pushed 2 commits to main chg0901/NaViT
chg0901 closed a pull request on chg0901/NaViT
Solve TypeError: meshgrid() got an unexpected keyword argument 'indexing'
```python pos = torch.stack(torch.meshgrid(( arange(ph), arange(pw) # TypeError: meshgrid() got an unexpected keyword...
chg0901 pushed 2 commits to main chg0901/NaViT
chg0901 closed a pull request on chg0901/NaViT
Update README.md add depth parameters
add depth parameters ```python n = NaViT( image_size = 256, patch_size = 32, num_classes = 1000, dim = 1024, depth=3, # add depth parameters heads = 16, ...
chg0901 opened a pull request on chg0901/NaViT
Update README.md add depth parameters
add depth parameters ```python n = NaViT( image_size = 256, patch_size = 32, num_classes = 1000, dim = 1024, depth=3, # add depth parameters heads = 16, ...
chg0901 created a branch on chg0901/NaViT
chg0901-patch-2 - Implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"
chg0901 opened a pull request on chg0901/NaViT
Solve TypeError: meshgrid() got an unexpected keyword argument 'indexing'
```python pos = torch.stack(torch.meshgrid(( arange(ph), arange(pw) # TypeError: meshgrid() got an unexpected keyword...
chg0901 created a branch on chg0901/NaViT
chg0901-patch-1 - Implementation of "Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution"
chg0901 created a comment on an issue on kyegomez/NaViT
please check this two parameters and make sure your input image could be devided by patch_size ```python image_size = 256, patch_size = 32, ```