Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: How to boost Gemini transcription accuracy for company names?

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 32 posts

Re: Ask HN: How to boost Gemini transcription accuracy for company names?

#11

Post by samtts »

remus wrote: post #9
tifa2up wrote: post #6

Don't solve it on the STT level. Get the raw transcription from Gemini then pass the output to an LLM to fix company names and other modifications. Happy to share more details if helpful.

I've had some luck with this in other contexts. Get the initial transcript from STT (e.g. whisper), then feed that in to gemini with a prompt giving it as much extra context as possible. For example "This is a transcript from a youtube video. It's a conversation between x people, where they talk about y and z. Please clean up the transcript, paying particular attention to company names and acronyms."

[dead]

Re: Ask HN: How to boost Gemini transcription accuracy for company names?

#12

Post by gearhart »

We use openwhisper for transcription which accepts a list of "words to look out for" which we populate with a short list of the names of all the people and companies most likely to be mentioned in the text, and then we do a spell checking pass at the end using Gemini with a much longer list, telling it to look out for anything that might be a misspelling.

It's not perfect, but it's taken it from being an issue that made all our transcripts look terrible, to an issue I no longer think about.

I imagine just using the second spellchecking pass with Gemini would be almost as effective.

Re: Ask HN: How to boost Gemini transcription accuracy for company names?

#15

Post by flyinglizard »

remus wrote: post #9
tifa2up wrote: post #6

Don't solve it on the STT level. Get the raw transcription from Gemini then pass the output to an LLM to fix company names and other modifications. Happy to share more details if helpful.

I've had some luck with this in other contexts. Get the initial transcript from STT (e.g. whisper), then feed that in to gemini with a prompt giving it as much extra context as possible. For example "This is a transcript from a youtube video. It's a conversation between x people, where they talk about y and z. Please clean up the transcript, paying particular attention to company names and acronyms."

I've done the same, it works very well.

Re: Ask HN: How to boost Gemini transcription accuracy for company names?

#16

Post by idopmstuff »

tifa2up wrote: post #6

Don't solve it on the STT level. Get the raw transcription from Gemini then pass the output to an LLM to fix company names and other modifications. Happy to share more details if helpful.

Yeah, I've done it with industry-specific acronyms and this works well. Generate a list of company names and other terms it gets wrong, and give it definitions and any other useful context. For industry jargon, example sentences are good, but that's probably not relevant for company names.

Feed it that list and the transcript along with a simple prompt along the lines of "Attached is a transcript of a conversation created from an audio file. The model doing the transcription has trouble with company names/industry terms/acronyms/whatever else and will have made errors with those. I have also attached a list of company names/etc. that may have been spoken in the transcribed audio. Please review the transcription, and output a corrected version, along with a list of all corrections that you made. The list of corrections should include the original version of the word that you fixed, what you updated it to, and where it is in the document." If it's getting things wrong, you can also ask it to give an explanation of why it made each change that it did and use that to iterate on your prompt and the context you're giving it with your list of words.

Re: Ask HN: How to boost Gemini transcription accuracy for company names?

#19

Post by meerab »

I use a two-pass approach - first pass with ASR (OpenAI Whisper) and second pass with an LLM. I ask users to provide context upfront and use that as the "initial_prompt" parameter in Whisper: https://github.com/openai/whisper/discussions/963#discussion...

Gemini might have similar capabilities for custom vocabulary, though I'm not certain about their specific implementation. The two-pass ASR+LLM approach could work with Gemini's output as well.

Post reply on HN