Video wird geladen...
Video konnte nicht geladen werden
Introducing Saaras V4 Multi-speaker Our best-in-class speech recognition model that accurately captures overlapping conversations and multi-speaker interactions, while delivering state-of-the-art performance in English across accents.
31,374 Aufrufe • vor 2 Monaten •via X (Twitter)
28 Kommentare

sarvam ai admin carefully finding the perfect indian news debate clip to demonstrate saaras .

Thank you ye bahaut jaroori tha. Now I hope TV channels live individual mute ka option le aaye 😂

thank you @SarvamAI the day is not far, when I am able to watch all my favourite Japanese anime in Hindi, with incredible accent with emotion and thrill'😍

finally an ASR model trained for the hardest benchmark: 5 founders talking over each other at a tpot dinner

Is this feature is available in Indus app

- Please add an Edit Message feature. - Copy and Select All options are not working properly for prompts. - Please make the Enter key create a new line instead of sending the message, or add an option to choose this behavior. Thanks for continuing improve in Savram Ai model

insane example to choose bruv

@SarvamAI has taken it upon themselves to take india on the high pedestal of AI leaders and seem to be on the right path too. On the sidenote- they should have chosen a voice clipping of the Arnab Goswami show to really test this voice model

When asking #SarvamAI questions via voice, if I pause the response and try to listen to it again, it restarts from the beginning; this needs to be fixed. @SarvamAI @SarvamForDevs @pratykumar

Keep building India

incredible product surely will help in making things more easy!

Overlapping speakers are where speech recognition becomes genuinely difficult. Accuracy by accent, speaker count and overlap duration would make this especially valuable for meetings, support calls and public service applications.

Accurately parsing overlapping conversations and multiple speakers is one of the hardest roadblocks in audio processing.🤩

saaras v4 sounds impressive but can it handle non-english languages and dialects as well or it's still a work in progress?

Applied for a job at @SarvamAI but never got any response. I am willing to relocate to India and contribute to building our own AI. I bring in lots of infrastructure and software engineering experience. Its just not clear how you are hiring at the moment.

Is this available in South Africa?🇿🇦

😅

cant wait to use this

one use case might be to understand the tv debates.

Your auth is broken!

😂😂

whats the practical use case of it?

Amazing

I was mind-blown by the products that were showcased at Epoch yesterday ! Especially Bulbul V4 and Kivi ! Great work @SarvamAI !!

when can we use it?

now this is nice

Sir ,give me download link of sarvam ai in gguf format ,only 5 gb in size for running on mobile.

Wow!
