when i try to deploy wfaster-whisper-server in offline server, docker run problem came up

[james2v]

(base) [root@app2 ~]# docker run --gpus all -p 1080:8000 -v /app:/root/.cache/huggingface/ 784630b8bc0a

==========
== CUDA ==

CUDA Version 12.2.2

Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license

A copy of this license is made available in this container at /NGC-DL-CONTAINER-LICENSE for your convenience.

error: Failed to prepare distributions
Caused by: Failed to fetch wheel: faster-whisper-server @ file:///root/faster-whisper-server
Caused by: Failed to install requirements from build-system.requires (resolve)
Caused by: No solution found when resolving: hatchling
Caused by: Could not connect, are you offline?
Caused by: Request failed after 3 retries
Caused by: error sending request for url (https://pypi.org/simple/hatchling/)
Caused by: client error (Connect)
Caused by: dns error: failed to lookup address information: Try again
Caused by: failed to lookup address information: Try again

[fedirz]

I don't think you've included the full docker command in your description, as it doesn't have the image name. Are you using your own image or the one from Docker Hub?

[james2v]

I don't think you've included the full docker command in your description, as it doesn't have the image name. Are you using your own image or the one from Docker Hub?

784630b8bc0a is the image id of faster-whisper-server:latest-cuda, i am using the one form Doceker hub. i think the issus is that the when i run the docker image, it automatically execute
2024-10-21 09:22:43,704:INFO:httpx:_send_single_request:HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK" , but in my offline server it fails. any chance i can find a image without gradio

[mindspawn]

Seeing the same issue as well. I like making my docker stacks use an isolated network to be sure no accidental data leaks. Supporting offline mode would be very useful.

[mindspawn]

@fedirz .. I think the root cause is because there are package dependencies in pyproject.toml that are not in the Dockerfile hence an attempt is made to download them which fails in offline deployments. e.g. hatchling, piper-phonemize etc.