Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Max retries exceeded with url: /hubertsiuzdak/snac_24khz/resolve/main/config.json #84

Open
sankexin opened this issue Sep 19, 2024 · 4 comments

Comments

@sankexin
Copy link

sankexin commented Sep 19, 2024

download by yourself and modify:

snacmodel = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").eval().to(device)
=>
snacmodel = SNAC.from_pretrained(repo_id="hubertsiuzdak/snac_24khz", local_dir=f"/root/mini-omni/snac_24khz", local_files_only=True).eval().to(device)

@mini-omni
Copy link
Contributor

It seems you can not access huggingface properly, please check your proxy.

@loredunk
Copy link

I also encountered the same problem, but changing it like you suggested still didn't work.

@vra
Copy link

vra commented Oct 18, 2024

@loredunk 试试这个https://hf-mirror.com/

@xns0318
Copy link

xns0318 commented Oct 31, 2024

@loredunk If you downloaded the weights and configuration files, you can also inference.py file by typing the following code
def SNAC_from_pretrained(cls,ckpt_dir):
config_path = os.path.join(ckpt_dir,'config.json')
model_path = os.path.join(ckpt_dir,'pytorch_model.bin')
model = cls.from_config(config_path)
state_dict = torch.load(model_path, map_location="cpu")
model.load_state_dict(state_dict)
model.eval()
return model
SNAC.from_pretrained = classmethod(SNAC_from_pretrained)
snacmodel = SNAC.from_pretrained(ckpt_dir = r".\pth\snac_24khz")

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants