TGTGInsighttelegram intelligenceLIVE / telegram public index
← GitHub Trends

TGINSIGHT SIMILAR POSTS

Find similar content

Source channel @githubtrending · Post #14974 · Jul 19

#cplusplus ik_llama.cpp is an improved version of llama.cpp that runs faster on CPUs and hybrid GPU/CPU setups. It supports many new advanced quantization methods, which help models use less memory and run more efficiently. It also offers better performance for special models like DeepSeek and MoE, with faster prompt processing and token generation. You can run it on various hardware, including Android, and it has features to control where model data is stored (CPU or GPU). This means you get quicker AI responses and can handle bigger or more complex models smoothly on your computer or device[2][1][4]. https://github.com/ikawrakow/ik_llama.cpp

Hashtags

Results

45 similar posts found

Search: #stt

当前筛选 #stt清除筛选
Ali Ahmad

@AlisherAhmatovich · Post #1189 · 01/09/2025, 04:15 PM

O'zbekcha STT (Speech-to-Text) uchun benchmarking v1 tayyor! O'zbek tilida nutqni matnga aylantirish bo'yicha dastlabki etalon tizimni yaratdik! Ushbu jarayonda: ✅ Adabiy O'zbek tili ✅ Turli hududiy shevalar ✅ Musiqalar va suhbatlar ✅ Shovqinli audiolar bilan o’zimizni va bozordagi mavjud modellarni sinab ko'rdik. Tez orada natijalarni va benchmarkni e’lon qilamiz, hamda benchmarkni doimiy yangilab borish niyatimiz bor. Benchmark mezonlari: - WER (Word Error Rate) - So’zlar xatolik darajasi. - CER (Character Error Rate) – Harflar xatolik darajasi. Bu nafaqat texnologik rivojlanish, balki O'zbek tilining raqamli muhitda mustahkam o'rin egallashi yo'lida muhim qadamdir. Maqsadimiz – O'zbekcha STT modellarining aniq va sifatli ishlashini ta'minlashdir. Kelajak rejalari: - Test natijalarini batafsil tahlil qilib, modellarni yanada takomillashtirish. O'zbek tili texnologiyalari rivoji uchun birgalikda ishlashda davom etamiz! STT modelimizni @aishaovozbot’da yoki aisha.group’da sinab ko’rishingiz mumkin. #aisha#stt @elzodxon

Hashtags

PreviousPage 1 of 4Next