bk111

after updated as your code. It looks like it needs more gpu memory. I have a 10G N gpu. What is the smallest amount for audio to text demo on...

> No, it's a browser extension. You install it on your browser and then you can use it on any website. 2023年6月30日(金) 12:05 bk111 ***@***.***>: > […](#) > What's it...

I tried to use windows11(settings/installed apps, NVIDIA driver 546.33, NVIDIA cuda11.8)(nvidia-smi, CUDA 12.3)-wsl2-Ubuntu-docker container-nvidia/cuda image, (https://hub.docker.com/r/nvidia/cuda/tags?page=2&name=11.8), no luck. Do I need "jax[cuda12_pip]==0.4.19" or "jax[cuda11_pip]==0.4.19"? and how about container version?

> You might need to check your jax version. > > I am use jax 0.4.19, it works. > > !pip install jax==0.4.19 !pip install -U "jax[cuda12_pip]==0.4.19" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html now,...

> [@bk111](https://github.com/bk111) Hi, bro. This is a different things. You can pip install `jieba` and `pypinyin` and get it. Thanks for your hint. Cause pypinyin and pypinyin-dict cannot handle some...

> [@bk111](https://github.com/bk111) > > 1. The principle is similar, but the purpose of the project is different. I just want to make a library that integrates free translation services, and...

> if putting in "apple?" doesn't do it then likely no. You could try using custom phenomes or stress/intonation as described at the bottom of this: https://huggingface.co/spaces/hexgrad/Kokoro-TTS sorry, could you...

> I was kind of wondering the same but I cannot really get it to work any differently when I include the punctuation. Is there any part in the documentation...

> huggingface on huggingface, https://huggingface.co/spaces/hexgrad/Kokoro-TTS, the input is 'Is it an apple?' , but the audio has no rising intonation. Do you find another TTS solution with normal intonation?