I play with the IBM Watson Speech To Text Service API . For those who do not know that this service is used for transcription of sound. You upload the audio file to the service and return the text. The service is still good, but the problem is that the returned text does not contain punctuation marks. I tried to solve this problem with nltk , but there were no results.
Some nltk code I tried.
Is there any way to solve my problem? What would you do if you were in my case?
source share