Additional training #32
-
|
Have you released any code making it possible to do additional pretraining/finetuning? This is of course especially relevant for the languages that have high WER today but where it is possible to obtain additional training data. |
Beta Was this translation helpful? Give feedback.
Replies: 2 comments
-
|
We currently don't have plans to release training/fine-tuning code, but there might be an implementation from the community soon. |
Beta Was this translation helpful? Give feedback.
-
|
And here it is! Check-out this blog for fine-tuning Whisper for multilingual ASR with Hugging Face Transformers: https://huggingface.co/blog/fine-tune-whisper It provides a step-by-step guide to fine-tuning, right from data preparation to evaluation 🤗 There'a Google Colab so you can also run it as a notebook 😉 |
Beta Was this translation helpful? Give feedback.
And here it is! Check-out this blog for fine-tuning Whisper for multilingual ASR with Hugging Face Transformers: https://huggingface.co/blog/fine-tune-whisper
It provides a step-by-step guide to fine-tuning, right from data preparation to evaluation 🤗 There'a Google Colab so you can also run it as a notebook 😉