Fine tuning Model

#4
by Macs98 - opened

Hello!

I'm attempting to perform fine-tuning on this English-to-Spanish translation model. I have sentence pairs stored in xlsx files for both English and Spanish. However, the process is not as straightforward as with the OPUS-mt-en-es model, where I could load the model using the following code:

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model_name = "Helsinki-NLP/opus-mt-en-es"
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

Does anyone have a tutorial, preferably in Google Colab, on how to perform fine-tuning on the Seamless-M4T model?

Did you resolve fine-tuning?

If you find any answer to that, please share it with us here.

Sign up or log in to comment