RunPod•5d ago

Help with deploying WhisperX ($35 bounty)

I've been trying to get WhisperX to run on runpod serverless. Here is what I have so far: https://github.com/YashGupta5961/whisperx-worker . The worker deploys but its running into some problems processing the request. I cant seem to debug whats going wrong. I am willing to offer $35 USD to anyone who can get it working with diarization. I know its not much but I hope it can be motivating to bang their head against the wall for me 😄

GitHub

GitHub - YashGupta5961/whisperx-worker: RunPod Serverless worker fo...

RunPod Serverless worker for WhisperX. Contribute to YashGupta5961/whisperx-worker development by creating an account on GitHub.

6 Replies

KalpakOP•5d ago

==========
== CUDA ==
==========
CUDA Version 11.6.2
Container image Copyright (c) 2016-2022, 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.
quirks.py           :115  2025-02-22 22:55:07,714 Applied quirks (see `speechbrain.utils.quirks`): [disable_jit_profiling, allow_tf32]
quirks.py           :120  2025-02-22 22:55:07,714 Excluded quirks specified by the `SB_DISABLE_QUIRKS` environment (comma-separated list): []
/usr/local/lib/python3.10/dist-packages/pyannote/audio/pipelines/speaker_verification.py:45: UserWarning: Module 'speechbrain.pretrained' was deprecated, redirecting to 'speechbrain.inference'. Please update your script. This is a change from SpeechBrain 1.0. See: https://github.com/speechbrain/speechbrain/releases/tag/v1.0.0
  from speechbrain.pretrained import (
--- Starting Serverless Worker |  Version 1.7.7 ---
{"requestId": null, "message": "Jobs in queue: 1", "level": "INFO"}
{"requestId": null, "message": "Jobs in progress: 1", "level": "INFO"}
{"requestId": "7e0e8478-41d1-47b4-8f7b-98098cd53cbf-u1", "message": "Started.", "level": "INFO"}
{"requestId": "7e0e8478-41d1-47b4-8f7b-98098cd53cbf-u1", "message": "Failed to return job results. | 400, message='Bad Request', url='https://api.runpod.ai/v2/h03p8vmv03m3u7/job-done/gdowmh2i4enic6/7e0e8478-41d1-47b4-8f7b-98098cd53cbf-u1?gpu=NVIDIA+RTX+A5000&isStream=false'", "level": "ERROR"}
{"requestId": "7e0e8478-41d1-47b4-8f7b-98098cd53cbf-u1", "message": "Finished.", "level": "INFO"}

==========
== CUDA ==
==========
CUDA Version 11.6.2
Container image Copyright (c) 2016-2022, 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.
quirks.py           :115  2025-02-22 22:55:07,714 Applied quirks (see `speechbrain.utils.quirks`): [disable_jit_profiling, allow_tf32]
quirks.py           :120  2025-02-22 22:55:07,714 Excluded quirks specified by the `SB_DISABLE_QUIRKS` environment (comma-separated list): []
/usr/local/lib/python3.10/dist-packages/pyannote/audio/pipelines/speaker_verification.py:45: UserWarning: Module 'speechbrain.pretrained' was deprecated, redirecting to 'speechbrain.inference'. Please update your script. This is a change from SpeechBrain 1.0. See: https://github.com/speechbrain/speechbrain/releases/tag/v1.0.0
  from speechbrain.pretrained import (
--- Starting Serverless Worker |  Version 1.7.7 ---
{"requestId": null, "message": "Jobs in queue: 1", "level": "INFO"}
{"requestId": null, "message": "Jobs in progress: 1", "level": "INFO"}
{"requestId": "7e0e8478-41d1-47b4-8f7b-98098cd53cbf-u1", "message": "Started.", "level": "INFO"}
{"requestId": "7e0e8478-41d1-47b4-8f7b-98098cd53cbf-u1", "message": "Failed to return job results. | 400, message='Bad Request', url='https://api.runpod.ai/v2/h03p8vmv03m3u7/job-done/gdowmh2i4enic6/7e0e8478-41d1-47b4-8f7b-98098cd53cbf-u1?gpu=NVIDIA+RTX+A5000&isStream=false'", "level": "ERROR"}
{"requestId": "7e0e8478-41d1-47b4-8f7b-98098cd53cbf-u1", "message": "Finished.", "level": "INFO"}

these are the worker logs I tried using this docker image (https://hub.docker.com/layers/madiator2011/whisperx-worker/test4) but diarization doesn't seem to work:

{
  "delayTime": 704,
  "error": "An error happened while trying to locate the file on the Hub and we cannot find the requested files in the local cache. Please check your connection and try again or make sure your Internet connection is on.",
  "executionTime": 7228,
  "id": "7623d46e-ae16-4394-9aa0-e11d0bd32a63-u1",
  "status": "FAILED",
  "workerId": "9wk6lupo31k4ob"
}

{
  "delayTime": 704,
  "error": "An error happened while trying to locate the file on the Hub and we cannot find the requested files in the local cache. Please check your connection and try again or make sure your Internet connection is on.",
  "executionTime": 7228,
  "id": "7623d46e-ae16-4394-9aa0-e11d0bd32a63-u1",
  "status": "FAILED",
  "workerId": "9wk6lupo31k4ob"
}

nerdylive•4d ago

Maybe you need to download the model into your network storage Or you need to supply a hf token so it gets downloaded

KalpakOP•4d ago

@nerdylive would I pass the hf token in as a env variable? The image doesnt link the source code so im unsure how it accepts it

nerdylive•4d ago

Search it in madiator's github I think you can find it

riverfog7•4d ago

It says huggingface_access_token on the Readme

KalpakOP•4d ago

passing in the token gives the result above: https://discord.com/channels/912829806415085598/1342990814204395662/1342994966879670352

Gaming

Programming

Help with deploying WhisperX ($35 bounty)

Did you find this page helpful?