apoorv

4.4K posts

apoorv banner
apoorv

apoorv

@apoorvcodes

research @smallest_ai

Katılım Ekim 2020
803 Takip Edilen1.3K Takipçiler
apoorv retweetledi
Pratyush Rai
Pratyush Rai@pratyush_r8·
@smallest_AI team is cooking 🫡🔥 TIL they just dropped an open-source Wispr Flow alternative. Makes total sense. Their voice models are already some of the best. OSS = way less stress about where your data goes. github.com/smallest-inc/M… @kamath_sutra & team ftw 🚀
English
5
11
94
5.6K
Maniꑭ
Maniꑭ@devxMani·
@apoorvcodes they r the best in the country rn I don't think so
English
1
0
0
45
apoorv retweetledi
Runtime
Runtime@RuntimeBRT·
🚨 Bengaluru and SF-based @smallest_AI has launched their SoTA TTS model, Lightning V3.
English
2
21
122
14.5K
apoorv retweetledi
Abhishek (key/value)
Abhishek (key/value)@StalwartCoder·
I cloned Peter Griffin's voice and made him do a code review. 10 seconds of audio. One API call. ~90ms latency. This is 100% AI-generated. Code attached.
English
7
12
78
8.7K
apoorv retweetledi
Nityanand Mathur
Nityanand Mathur@nityanandmathur·
We identified where pronunciation lives using acoustic causal tracing, then applied a closed-form, one-shot weight update which enforced null-space constraints ensuring zero interference with existing behavior. No retraining, no extra parameters, no degradation in prosody or speaker identity. Editing generative models like databases precise, local, and efficient.
English
0
2
7
495
apoorv retweetledi
Nityanand Mathur
Nityanand Mathur@nityanandmathur·
Where does pronunciation live in a large language model(LLM) based text-to-speech(TTS) system, and how can we surgically modify it for specific texts while preserving all other model behavior? To answer this very question, we introduced SonoEdit at @CPALconf yesterday. Our core hypothesis is that pronunciation errors aren’t global but they live in localized internal representations. If you find them precisely, you can fix them precisely.
Nityanand Mathur tweet mediaNityanand Mathur tweet media
English
6
13
59
5.3K
apoorv
apoorv@apoorvcodes·
@nityanandmathur aree aap sir, itne bade words ke liye shukriya
हिन्दी
0
0
0
40
Mrinal
Mrinal@Hi_Mrinal·
Some conversations which I think should be publicly available 1/n > I don't want to sound dumb but like, even just organizing code into folders counts as architecture right ?? >> That is what you call modularity, when you add folders you are just trying to separate concerns which is also a good habit. But there's the thing it's only a small piece of architecture. Modularity is more of a coding practice thing than a full architecture decision. What it does help with is debugging, testing, and keeping your code easy to maintain.
English
7
5
105
5K
apoorv retweetledi
aditya
aditya@adxtyahq·
realizing ChatGPT + Claude can build your whole app but your voice agent still sounds like a robot because TTS was optimized for reading not conversation. Smallest AI just changed that MOS 3.89 beats OpenAI, ElevenLabs, Cartesia and yeah… you can hear the difference instantly
Sudarshan Kamath@kamath_sutra

x.com/i/article/2036…

English
7
5
27
1.8K