Sagor Sarker comments

Results 11 comments of


                                            Sagor Sarker

Making Dataset for Bengali Language

Hi @PrithwirajRizu Your story should be like this. ```py article = open('article.txt', 'r').read() summary = open('summary.txt', 'r').read() story = article + '\n\n' + '@highlight'+'\n'+summary ``` Then follow [this](https://github.com/dondon2475848/make_datafiles_for_pgn) to generate...

ImportError

Hi @Baidya89 Can you share the snapshots of the code that raise this error? If possible please share. regards

Missing parentheses in call to 'print'. Did you mean print(...)?

Hi @sajeeb007 , Check the version and documentation accordingly. I am also guessing it will be a version problem. Also if possible please share the error message with the code...

Missing parentheses in call to 'print'. Did you mean print(...)?

I am assuming your problem was solved.

Error building "tokenizers" wheel when installing "bntransformer" via pip in Colab environment

Hi @basirul-billah , I am guessing the problem is transformers version. I will debug it and get back to you. It will take a longer time though. Thanks

Tiktoken educational BPE trainer takes long time to train with vocab size 30k

Hi @vladimirzenin , Thanks for your input. You right. A small subset will be enough for the tokens. But for our cases, Bengali is a diverse language. We have separated...

Getting so many `opentelemetry.attributes` warning in logs

Hi @tinalenguyen , Thanks for your response. I will try with latest version and share with you.

Getting so many `opentelemetry.attributes` warning in logs

Hi @tinalenguyen This issue resolved now with latest version. Thank you so much.

The `gemini-2.5-flash-native-audio-preview-12-2025` model cannot be used with modalities text for hybrid architecture with a separate TTS plugin

@tinalenguyen #4414

The `gemini-2.5-flash-native-audio-preview-12-2025` model cannot be used with modalities text for hybrid architecture with a separate TTS plugin

Hi @chenghao-mou , Thanks for the response. Looking forward to the Google fix.