Fine-tunining Whisper models for shorter audio segments
#5
by
Malishevsky
- opened
Hi all. My project needs to recognize many short audio parts. Can I use fine to change the multilingual model for short audios like 10 seconds ? If not, can I train the model from scratch for these purposes? I would be grateful for any help and hints.
Hi, this is a general question about Whisper and it seems you already asked it in openai/whisper which is a better place to ask this type of questions: https://github.com/openai/whisper/discussions/1342
So I'm closing the discussion here.
guillaumekln
changed discussion status to
closed