Hi,
I’m using the openAI API, I’m trying to get short segments (~4 words) with timings & punctuations.
What I went through:
API doesn’t allow to set the number of words per segment
Thought I could build it from words level transcribe → there is no punctuation there, also characters like - and ' weirdly managed
Thought I could merge text or segments with words (I can get punctuation from text and timing from words)
Until I noticed a few things between text/segments and words:
Text might differ. Literally having word in words that totally not exist in text/segments
Timestamps is a big mismatch between words and segments
No punctuation in words
Words containing ' or - like « it’s » in some language would be consider as one word, in other language as two word.
This makes merging segments and words difficult since there is not the same amount of words in both side and rules on specific characters differ depending on the language
Did anyone succeed getting a word based transcribe with punctuation and level timestamp with the API or short segments ?