gmaysMar 31

Cohere Transcribe: Speech Recognition

https://cohere.com/blog/transcribe

Cohere Transcribe: state-of-the-art speech recognition

Unmatched accuracy and speed. Transcribe converts your business’ audio data into precise text for search, analytics, and automation.

Cohere
Show threaddinakernelMar 31

My worry is that ASR will end up like OCR. If the multi modal large AI system is good enough (latency wise), the advantage of domain understanding eats the other technlogies alive.

In OCR, even when the characters are poorly scanned, the deep domain understanding these large multi modal AIs have allows it to understand what the document actually meant - this is going to be order id because in the million invoices I have seen before order id is normally below order date - etc. The same issue is going to be there in ASR also is my worry.

Show threadcorlinp

This is exactly the case today. Multimodal LLMs like gpt-4o-transcribe are way better than traditional ASR, not only because of deeper understanding but because of the ability to actually prompt it with your company's specific terminology, org chart, etc.

For example, if the prompt includes that Caitlin is an accountant and Kaitlyn is an engineer, if you transcribe "Tell Kaitlyn to review my PR" it will know who you're referring to. That's something WER doesn't really capture.

BTW, I built an open-source Mac tool for using gpt-4o-transcribe with an OpenAI API key and custom prompts: https://github.com/corlinp/voibe

GitHub - corlinp/voibe: Mac Menu bar app for accurate speech-to-text with multimodal LLMs

Mac Menu bar app for accurate speech-to-text with multimodal LLMs - corlinp/voibe

GitHub
Mar 31 at 6:49pmWeb
Show threadBolwinMar 31
Many ASR models already support prompts/adding your own terminology. This one doesn't, but full LLMs especially such expensive ones aren't needed for that.