This is another great application of AI, well done
LeMUR: LLMs for Audio and Speech
21–26 of 26 posts
Re: LeMUR: LLMs for Audio and Speech
#22Not downplaying this, but how is it any different than using any number of free audio transcription libraries (sphinx, google, etc.) and any LLM?
No, but no tech users will think it is magic.
Re: LeMUR: LLMs for Audio and Speech
#23Hey HN, Matt from AssemblyAI here. If you want to test out LeMUR one of the fastest ways is with our Google Colab: https://colab.research.google.com/drive/1xX-YeAgW5aFQfoquJPX... I'm happy to answer questions about the API as well
Do you use Whisper for the transcript (which version? base?) and GPT-3.5-turbo for the language model? Do you provide a self-hosted solution for the companies that don't want their meetings going "on the cloud"? I do not mean to be dismissive of all your work, I know too well the devil is in the details, but what are the key advantages of using your solution over having a Python dev (or GPT-4) write a similar tool us…
You can use deepgram who has their own model but also has an option to use whisper hosted by them
Re: LeMUR: LLMs for Audio and Speech
#24This looks decent but sadly you can get better results with OpenAI
Re: LeMUR: LLMs for Audio and Speech
#25Not downplaying this, but how is it any different than using any number of free audio transcription libraries (sphinx, google, etc.) and any LLM?
No, but no tech users will think it is magic.
Its the seamless integration that counts. With the playground for example you can have it read and summarize a near 3 hour video https://www.youtube.com/watch?v=Se91Pn3xxSs
with a few clicks and decide if you really want to watch
https://www.assemblyai.com/playground/v2/transcript/6lu93wlw...
Re: LeMUR: LLMs for Audio and Speech
#26Earlier quoted context omitted.
Their ASR model is Conformer trained on 1.1M hours, so the result should be better than Whisper. From their pricing page, with ~ length of a meeting, input size 15000 tokens (60 minutes audio file), output size 2000 tokens (1500 words), LeMUR default, the price estimate is $0.353, which is I think a fairly good price. This tool can save a lot of time for a secretary, even replace them. But I think sending your meetin…
Comparison by competitor but it’s believable IMO. Basically about the same performance as whisper: - https://deepgram.com/learn/nova-speech-to-text-whisper-api Not surprising though as at this level all these options are starting to be leveled by inconsistencies in manual groundtruth. Conformer alone also isn’t the most powerful architecture out there for speech. This is also slower than, say running a large k2 zipfo…
Deepgram will correlate the text in your transcription with the timestamp where that was uttered. This is really really impressive and useful.