Execute CosyVoice on the local deployment following the step-by-step instructions in ReadMe.md. Cosyvoice fails to start.

zhanbei1 commented 3 months ago

Describe the bug Follow the instructions in README.md step by step, deploy on a personal server, execute python3 webui.py --port 50000 --model_dir speech_tts/CosyVoice-300M Unable to start, error reported.

After executing the startup command, all the logs are as follows (this is all the logs) : ` 2024-07-10 15:46:16, 963-modelscope-INFO-PyTorch version 2.0.1+cu118 Found. The 15:46:16 2024-07-10, 964 - modelscope - INFO - Loading ast index from/root/cache/modelscope/ast_indexer

2024-07-10 15:46:17, 372-modelscope-INFO-Loading done! Current index file version is 1.15.0, with md5 9f4fb120384b6702f0cca427af528ecb and a total number of 980 components indexed / root/miniconda3 / envs/cosyvoice/lib/python3.8 / site - packages/torch / _jit_internal. Py: 726: FutureWarning: ignore(True) has been deprecated. TorchScript will now drop the function call on compilation. Use torch.jit.unused now. {} warnings.warn( Killed `

Expected behavior I want to deploy CosyVoice on my personal server and run it successfully.

Screenshots

Desktop (please complete the following information):

OS: centos7, 2-core 2G, new Alibaba cloud environment, no other services are deployed
Version：Cosy Voice commit number is ：9aea393d18b633e06c2eb8df34a0e817dd11c403

Additional context The first time it starts, an error is reported saying that a Tensorflow is missing. I installed it. After many times to start, will report the error, has been unable to start. I don't have enough resources? Or is there something else that doesn't operate? If resources are not enough, how do I add resources