myshell-ai/AIlice

Speech.PrepareModel not downloading voice model

robonxt-ai opened this issue · 3 comments

robonxt-ai commented

When starting AIlice (both main and web) with the --speechOn flag, I'm getting this error:

Command used:

$ ailice_main --modelID=lm-server:llava --prompt="main" --contextWindowRatio=0.5 --speechOn

Result (truncated):

...
The speech module is preparing speech recognition and TTS models, which may include the work of downloading weight data, so it may take a long time.
Encountered an exception, AIlice is exiting: An error happened while trying to locate the files on the Hub and we cannot find the appropriate snapshot folder for the specified revision on the local disk. Please check your internet connection and try again.
  File "/home/user/ailice/AIliceMain.py", line 104, in main
    mainLoop(**kwargs)
  File "/home/user/ailice/AIliceMain.py", line 56, in mainLoop
    speech.PrepareModel()
  File "/home/user/ailice/common/lightRPC.py", line 102, in methodTemplate
    return self.RemoteCall(methodName,args,kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/ailice/common/lightRPC.py", line 129, in RemoteCall
    raise ret["exception"]```

I am running using LM Studio to run my model (trinity v1.2 7B for testing), and it works fine without speech.

stevenlu137 commented

I can also reproduce this error here.
It looks like huggingface has some network problems. Let's wait a few hours and see.

stevenlu137 commented

Now that the maintenance of huggingface has ended, the problem in my environment has disappeared.

robonxt-ai commented