-
Notifications
You must be signed in to change notification settings - Fork 390
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Incorrect transcription #685
Comments
Hi @hamsipower , thanks for the report! Did you try with the original PyTorch model from Transformers? If the output is different it's indeed a bug, we'll have a loop asap. |
@fxmarty , tried installing directly from github but no evail. :( Edit; Ah, also I found out that if I don't include "language='tr'" field to the model.config in the PyTorch version, the outputs of ONNX and PyTorch are not exactly the same but somewhat similar. Not sure if it's related but I hope it helps. |
Thank you! Could you share the collab or the code copy/pastable so that I have a look? |
Here you go; Colab. Edit; The pipeline seems to transcribe English audio fine, but it tries tro translate to English when non-English audio is given. Also, unlike |
@fxmarty , since you added Edit; The onnx inference time is slower than the original PyTorch model. For 30 second clip PyTorch; 41 secs, optimum 61 secs. Edit2; Okay, got it working with the following line;
but the inference time still takes a hit. |
@hamsipower Is there anything working with the vanilla pytorch pipeline that is not using an ORTModel? I'm not super familiar with ASR, but to me if you don't pass I feel like the ASR pipeline doc/implementation https://huggingface.co/docs/transformers/v4.25.1/en/main_classes/pipelines#transformers.AutomaticSpeechRecognitionPipeline is lacking to specify the language and task maybe For the slowdown, I guess it could be an issue similar to microsoft/onnxruntime#13808 & #524 . Could you open a new issue with a reproducible code & detail about your CPU ( I'd recommend you to try on GPU as well, if available, to see if you can see any speedup with ORT. @mht-sharma I recall you had similar issues with Whisper on CPU? It would be great to open an issue to track. |
@fxmarty , yes you're correct. That was a mistake on my part, just thought it will detect language in the pipeline similar to I will open a new issue if the performance issue persists, thank you! Edit; Tried GPU for ORT pipeline. It's also weird that
|
@hamsipower Yes, to run ONNX Runtime on GPU you need to install I'll close, feel free to open a new issue! |
System Info
Who can help?
@JingyaHuang, @echarlaix
Information
Tasks
examples
folder (such as GLUE/SQuAD, ...)Reproduction
Expected behavior
The text should be longer, it's a 30 second clip with a lot of talking and the language should be Turkish. Tried running with #420 .
The text was updated successfully, but these errors were encountered: