Today 23-07, the tokenizer is still not available in the transformers library, but the branch you used in this video has vanished, pip can't install from it anymore. Is there an alternative way to install the tokenizer? I actually kinda hacked into the bash script you mentioned in your previous video about NLLB and made a method to load it directly and keep it on memory to process batches of text ( i want to make a local translation server for another service). It works well, but it is a lengthy and piece of code and it has a cold start. I prefer if I can run it on the transformers library. Looking forward for a solution. Thank you very much, your video is a saviour! :)
PS: I also tried to load the tokenizer provided in hugging face's nllb-200-distilled-600M but AutoTokenizer class won't load it, I downloaded the files and tried to load from the system, But I got the same error as when I tried to load from the repo directly: "ValueError: Tokenizer class NllbTokenizer does not exist or is not currently imported."
Could you please drop your email for me so that I can reach out to you. I so much enjoyed you vidoes and it has really helpful. Also is there a way it can translate a language to multiple languages at once ?
![สั่งทอง.. จาก temu ของจริงป่ะ? ( part : 1/2 ) [โกงไหมครับ ep.94 ] | DOM](http://i.ytimg.com/vi/2tYS1qTMB78/mqdefault.jpg)
hi bro exiting to see a tamil guy making awesome AI/ML videos. Looking forward to connect with you
Thanks bro
Hello, what should I put in "model=model" and "tokenizer=tokenizer" ?
🚀🚀🚀 Now I have to try it for sure!
Let me know the quality of it
Today 23-07, the tokenizer is still not available in the transformers library, but the branch you used in this video has vanished, pip can't install from it anymore. Is there an alternative way to install the tokenizer?
I actually kinda hacked into the bash script you mentioned in your previous video about NLLB and made a method to load it directly and keep it on memory to process batches of text ( i want to make a local translation server for another service). It works well, but it is a lengthy and piece of code and it has a cold start. I prefer if I can run it on the transformers library. Looking forward for a solution.
Thank you very much, your video is a saviour! :)
PS: I also tried to load the tokenizer provided in hugging face's nllb-200-distilled-600M but AutoTokenizer class won't load it, I downloaded the files and tried to load from the system, But I got the same error as when I tried to load from the repo directly: "ValueError: Tokenizer class NllbTokenizer does not exist or is not currently imported."
i simply installed it as plugin in subtitle edit software and without running code translate
plz make video on how to implement this model in Rasa chat bot
Hey great video
Can you please help with the language-detection aspect of this model? Thanks
Please elaborate
How to fine tune this model?
i can find hokkien,it is not an unwritten language.but i have seen speechtospeech demo on huggingface.
How to finetune this model?
It needs Tpu or not?
Any tutor how to mirroring site bro
Could you please elaborate thanks
Noise in background
Sorry I think it's the wind outside
Could you please drop your email for me so that I can reach out to you. I so much enjoyed you vidoes and it has really helpful. Also is there a way it can translate a language to multiple languages at once ?
Thanks 1littlecoder at gmail dot com