1 回答
- 最新
- 投票最多
- 评论最多
1
I know this doesn't answer your question directly but I'm wondering whether you have seen this https://aws.amazon.com/blogs/machine-learning/improving-speech-to-text-transcripts-from-amazon-transcribe-using-custom-vocabularies-and-amazon-augmented-ai/ Might give you something to start from.
已回答 2 年前
Thank you for the link, @Kishan! It is still useful even it doesn't solve my question.
Building up your custom vocabulary from low-confidence prediction is definitely a possible alternative.