mcshao

在modelscope下載funasr的標點預測模型，在進行預測時出現錯from funasr import AutoModel，顯示AttributeError: partially initialized module 'torchaudio' has no attribute 'lib' (most likely due to a circular import)

1

Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节） ## 🐛 Bug ### To Reproduce Steps to reproduce the behavior (**always include the command...

标点添加部分报错cuda不可用

3

## General Question

url can't be accessed now

1

The url of the StutteringIsCool and strongvoices section shows 404, can you please update the url or provide a workaround

运行官方示例出bug

6

按照conda create -n chattts conda activate chattts pip install -r requirements.txt pip install ChatTTS配置环境之后运行示例代码 ```py import ChatTTS import torch import torchaudio chat = ChatTTS.Chat() chat.load(compile=False) # Set to True for...

设置了start_bacth似乎是无效的

2

我的模型训练到batch_16000.pt时中断了 我想继续训练 我的脚本这样设置的 ./train.py \ --world-size 8 \ --num-epochs 30 \ --start-batch 16000 \ --max-duration 40 \ --num-buckets 100 \ --on-the-fly-feats true \ --exp-dir ./exp \ --bpe-model data/lang_bpe_2000/bpe.model \ 但是模型似乎还是从bacth0继续训练的...