Error on using converted model

[WhoMI7]

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!

[jordimas]

Hello. This seems a problem with your tokenizer library. Which version are you using?
Can you try tokenizers>=0.20?

[WhoMI7]

Hello. This seems a problem with your tokenizer library. Which version are you using? Can you try tokenizers>=0.20?

Same error using Version: 0.22.2

[jordimas]

Can you provide a sample to reproduce the problem and exact version of your stack?
Thanks

[Purfview]

Standalone Faster-Whisper r192.3 running on: CUDA

That's some ancient version, I think it's using CTranslate2 v3.24.0. Do you use it because your GPU is some very old model?
Try the latest version.

[WhoMI7]

Standalone Faster-Whisper r192.3 running on: CUDA

That's some ancient version, I think it's using CTranslate2 v3.24.0. Do you use it because your GPU is some very old model? Try the latest version.

No I use https://github.com/dyphire/mpv-sub-fastwhisper with mpv so that's why r192.3. But yeah Gpu is kinda old (3070 ti).
Either way here's the result with your r245.4

Standalone Faster-Whisper-XXL r245.4 running on: CUDA

Traceback (most recent call last):
  File "D:\whisper-fast-XXL\__main__.py", line 2324, in <module>
  File "D:\whisper-fast-XXL\__main__.py", line 2031, in cli
  File "faster_whisper\transcribe.py", line 797, in __init__
Exception: data did not match any variant of untagged enum ModelWrapper at line 264861 column 3
[PYI-11596:ERROR] Failed to execute script '__main__' due to unhandled exception!

Can you provide a sample to reproduce the problem and exact version of your stack? Thanks

Converted with following command: ct2-transformers-converter --model "Oriserve/Whisper-Hindi2Hinglish-Prime" --output_dir "D:/whisper/_models/faster-whisper-Whisper-Hindi2Hinglish-Prime-ct2/" --copy_files tokenizer.json preprocessor_config.json --quantization float16

Then with faster-whisper.exe or faster-whisper-xxl.exe '.\IMG_6347.MOV' --model Whisper-Hindi2Hinglish-Prime-ct2 --device cuda -pp --standard --sentence --threads 4 --output_dir source

I hope this is what you mean by stack version:

Name: ctranslate2
Version: 4.6.0
Summary: Fast inference engine for Transformer models
Home-page: https://opennmt.net
Author: OpenNMT
Author-email:
License: MIT
Location: D:\Programs\Python311\Lib\site-packages
Requires: numpy, pyyaml, setuptools
Required-by: argos-translate-lt, faster-whisper, subplz
---
Name: transformers
Version: 5.12.1
Summary: Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Home-page: https://github.com/huggingface/transformers
Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors)
Author-email: transformers@huggingface.co
License: Apache 2.0 License
Location: D:\Programs\Python311\Lib\site-packages
Requires: huggingface-hub, numpy, packaging, pyyaml, regex, safetensors, tokenizers, tqdm, typer
Required-by: colbert-ai, manga-ocr, marker-pdf, mokuro, sentence-transformers, surya-ocr, texify
---
Name: tokenizers
Version: 0.22.2
Summary:
Home-page: https://github.com/huggingface/tokenizers
Author:
Author-email: Nicolas Patry <patry.nicolas@protonmail.com>, Anthony Moi <anthony@huggingface.co>
License:
Location: D:\Programs\Python311\Lib\site-packages
Requires: huggingface-hub
Required-by: chromadb, faster-whisper, transformers
---
Name: sentencepiece
Version: 0.2.0
Summary: SentencePiece python wrapper
Home-page: https://github.com/google/sentencepiece
Author: Taku Kudo
Author-email: taku@google.com
License: Apache
Location: D:\Programs\Python311\Lib\site-packages
Requires:
Required-by: argos-translate-lt
---
Name: torch
Version: 2.10.0
Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration
Home-page: https://pytorch.org
Author:
Author-email: PyTorch Team <packages@pytorch.org>
License: BSD-3-Clause
Location: D:\Programs\Python311\Lib\site-packages
Requires: filelock, fsspec, jinja2, networkx, sympy, typing-extensions
Required-by: accelerate, asteroid-filterbanks, bitsandbytes, dora_search, easyocr, julius, kornia, lightning, manga-ocr, marker-pdf, mokuro, open_clip_torch, openai-whisper, openunmix, pyannote-audio, pytorch-lightning, pytorch-metric-learning, sentence-transformers, stable-ts, stanza, surya-ocr, texify, timm, torch-audiomentations, torch_pitch_shift, torchmetrics, torchvision, ultralytics-thop