Able to Transcribe only some of the filler words

[getthegeet]

Dear Team and Community

We have been trying to get an accurate speech to text and have the filler word feature enabled.
Able to capture the filler word 'uh' however unable to capture 'um', mm or others that are suggested in the documentation.

Any support and help extended shall be appreciated.

[deepgram-community[bot]]

Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently.
_{Consider joining our Discord community for more opportunity to engage with your fellow Deepgram users. You can earn points which can be redeemed for cool stuff by being active in our communities!}

[deepgram-community[bot]]

Hey there! It looks like you haven't connected your GitHub account to your Deepgram account. You can do this at https://community.deepgram.com - being verified through this process will allow our team to help you in a much more streamlined fashion.

[deepgram-community[bot]]

It looks like we're missing some important information to help debug your issue. Would you mind providing us with the following details in a reply?

• The programming language you are working in (e.g. JavaScript, Python).
• A request ID that triggered your error or issue.

[getthegeet]

The is not error that is triggered. I just does not transcribe all the filler words unfortunately whilst using your tech in the playground mode as well

[jkroll-deepgram]

Hi @getthegeet, the only control over filler words transcription is by enabling that feature, as you mention you've already done.

It's possible that if you are using a small amount of test audio, some filler words are being missed or are not clear in the audio. Perhaps there is cross-talk or low confidence on behalf of the model.

I'd recommend testing some additional audio in order to see broader use of the filler words feature.

For reference for the broader community, here's the doc link, the parameter is filler_words=true, and it's supported for English-only, pre-recorded and streaming audio.

[mgreene]

Yeah I've seen this as well, I can't for the life of me get this to work. I've tried different microphones (originally using phone audio 8khz), nothing seems to work.

I tried Google's STT just to compare and it worked flawlessly. Unfortunately, Google's STT does not offer the other rich features DG offers like VAD events or confidence levels for words in interim results.