OpenNMT / OpenNMT/CTranslate2

Error on using converted model

Open
#2,072 5 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

I converted this model https://huggingface.co/Oriserve/Whisper-Hindi2Hinglish-Prime
with ct2-transformers-converter --model "D:/Downloads/Whisper-Hindi2Hinglish-Prime/" --output_dir "D:/Downloads/Whisper-Hindi2Hinglish-Prime-ct2/" --copy_files tokenizer.json preprocessor_config.json --quantization float16
It converted but when I tried to use it I got this error

Standalone Faster-Whisper r192.3 running on: CUDA

Traceback (most recent call last):
  File "D:\whisper-fast\__main__.py", line 1600, in <module>
  File "D:\whisper-fast\__main__.py", line 1431, in cli
  File "faster_whisper\transcribe.py", line 151, in __init__
Exception: data did not match any variant of untagged enum ModelWrapper at line 264861 column 3
[6636] Failed to execute script '__main__' due to unhandled exception!

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

Reproduce the conversion with the Hugging Face Whisper-Hindi2Hinglish-Prime model and the shown ct2-transformers-converter command. Start at faster_whisper/transcribe.py line 151 and the reported main.py call, then determine why the converted output triggers the ModelWrapper error; done means the converted model can be loaded without that exception.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, huggingface
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.