OpenNMT / OpenNMT/CTranslate2

run fasterwhisper with ctranslate2 on aarch64

Open
#1,908 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
4.7k
Forks
536
Avg merge
12h 12m
Merged PRs (30d)
4

Description

Traceback (most recent call last):
  File "/app/transcriber_app.py", line 151, in <module>
    api = create_app(cli_args)
  File "/app/transcriber_app.py", line 70, in create_app
    model = WhisperModel(
  File "/usr/local/lib/python3.10/dist-packages/faster_whisper/transcribe.py", line 647, in __init__
    self.model = ctranslate2.models.Whisper(
ValueError: This CTranslate2 package was not compiled with CUDA support

I have been following the official installation guide but still get this error all the time.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with /app/transcriber_app.py and the faster_whisper/transcribe.py call to ctranslate2.models.Whisper shown in the traceback. Check how the official installation guide builds or installs CTranslate2 on aarch64 and whether CUDA support is expected. Done means the reported configuration can initialize WhisperModel without the CUDA-support error.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, python
Domain
ai, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.