HeisenbergWithoutHat

I seriously hope this project can live on. If yudai is no more active in this project. Maybe the best idea is to fork this project and let it live...

> > hello man: > > May I ask you that when i use "gotty -w kubectl", i succeed entry into the pod, then i close the browser.In pod the...

应该是recipeAsCode吧？ 比如pipelineAsCode=gitops；recipeAsCode就是cookOps

> Cooklang 功能太弱了，只有食材提取的能力。 更关键的烹饪技法没有规范化。 其实我觉得Cooklang只能够作为定义中的食材提取的部分；而这个烹饪技法--如同大家所说--可以用github action或者gitlab-ci等方式来完成。 而烹饪技法的流水线，又可以进一步提高人类协作的效率，可能这是目前的唯一价值；不然厨师们为啥要用一个不熟悉的语言来定义菜谱呢？ 当然最终目标还是输入菜谱之后，锅里面就能够标准化的生产出对应的菜，不过那个时候估计人工智能已经很发达了，还要喂养人类干嘛，当电池吗:)

训练GPT的时候，遇到了一样的问题，但是我的semantic_data_len并不是0。而且这个跟数据集好像有关系，有的数据集会触发，有的不会 ``` "/opt/anaconda3/envs/GPTSoVITS/bin/python" GPT_SoVITS/s1_train.py --config_file "TEMP/tmp_s1.yaml" Seed set to 1234 Using 16bit Automatic Mixed Precision (AMP) GPU available: True (cuda), used: True TPU available: False, using: 0 TPU cores IPU...

> Can you assign me this issue i would love to work on it Actually, I am waiting for reply of the moderator to see if it is a common...

I've written the code for it as mentioned in PR #21 . Please help close this issue if the PR is accepted.

Same question for one NVIDIA RTX 4090, as this might be the configuration for most casual user and some universities.

> #audio_output = gr.Audio(label="Audio Output", autoplay=True, streaming=True) # wav audio_output = gr.Audio(label="Audio Output") This method can only apply to single sentencer. As for multiple sentences, voice snippets generated later will...

I solved it in this PR https://github.com/FunAudioLLM/CosyVoice/pull/772. It's just one file(inference.py) so you guys can try it out yourself if you are in a hurry. 刚通过自己拼接的方式解决了这个问题，详见这个PR https://github.com/FunAudioLLM/CosyVoice/pull/772. 只需要改 inference.py 这一个文件，所以如果比较急的话，可以直接把PR里面的文件拷贝过去试试。