Загрузка видео...

Не удалось загрузить видео

На главную

parakeet.cpp: native C++/ggml (ggml) inference for NVIDIA AI Developer's Parakeet, one of the best speech-to-text models out there, from the LocalAI team. Every Parakeet model (TDT/CTC/RNNT/hybrid + cache-aware streaming), byte-for-byte identical output to NeMo, now running anywhere with no Python and even a bit faster, on CPU and GPU....

mudler_it's profile picture

Ettore Di Giacinto

3,582 subscribers

55,955 просмотров • 5 месяцев назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Depth Anything 3 now runs as pure C++/ggml (ggml) . No Python, no PyTorch, no CUDA toolkit at inference, just one self-contained GGUF. It's faster than PyTorch on CPU! and ties speed on GPU. The CPU win came from the last place..I'd have looked. Quantized GGUF on Hugging Face🤗 Shout out to Georgi Gerganov for ggml (we are building a ggml-world!❤️) and to ByteDance Open Source and Depth Anything 3 authors Bingyi Kang Jun Hao Liew Donny Y. Chen !
0:11

Depth Anything 3 now runs as pure C++/ggml (ggml) . No Python, no PyTorch, no CUDA toolkit at inference, just one self-contained GGUF. It's faster than PyTorch on CPU! and ties speed on GPU. The CPU win came from the last place..I'd have looked. Quantized GGUF on Hugging Face🤗 Shout out to Georgi Gerganov for ggml (we are building a ggml-world!❤️) and to ByteDance Open Source and Depth Anything 3 authors Bingyi Kang Jun Hao Liew Donny Y. Chen !

Ettore Di Giacinto

34,915 просмотров • 4 месяцев назад

I switched from a quantized Whisper Large v3 Turbo to Parakeet V3 in VoiceInk and the latency is much better.
0:11

I switched from a quantized Whisper Large v3 Turbo to Parakeet V3 in VoiceInk and the latency is much better.

Armin Ronacher ⇌

18,497 просмотров • 8 месяцев назад

We are open-sourcing TTSKit! Run state-of-the-art text-to-speech models on your Mac and iPhone. The launch version supports Qwen Qwen3-TTS and generates audio faster than real-time playback with sub-200 ms time-to-first-byte. Voice cloning and advanced speed optimizations will be in the next version. Link to the GitHub repo and models on Hugging Face in comments.
0:16

We are open-sourcing TTSKit! Run state-of-the-art text-to-speech models on your Mac and iPhone. The launch version supports Qwen Qwen3-TTS and generates audio faster than real-time playback with sub-200 ms time-to-first-byte. Voice cloning and advanced speed optimizations will be in the next version. Link to the GitHub repo and models on Hugging Face in comments.

argmax

61,998 просмотров • 8 месяцев назад

I finally got NVIDIA AI Developer's 3D Gaussian Unscented Transforms up and running natively on Windows via gsplat. Just in time for me to make a tutorial so people can enter NVIDIA's 3DGUT sweepstakes!!! Huge thanks to Ruilong Li for responding to my Github issues and solving my roadblocks this evening. #3D #Computervision
0:19

I finally got NVIDIA AI Developer's 3D Gaussian Unscented Transforms up and running natively on Windows via gsplat. Just in time for me to make a tutorial so people can enter NVIDIA's 3DGUT sweepstakes!!! Huge thanks to Ruilong Li for responding to my Github issues and solving my roadblocks this evening. #3D #Computervision

Jonathan Stephens

16,901 просмотров • 1 год назад

AI Tip: Turn on the NVIDIA Broadcast app when live streaming for AI greenscreen + to filter out noise 📺 Tell us your fave tips & tricks for taking advantage of AI apps on your GPU below + comment #AIonRTX to win a AORUS GIGABYTE GeForce RTX 4080 16GB GAMING OC GPU!
0:10

AI Tip: Turn on the NVIDIA Broadcast app when live streaming for AI greenscreen + to filter out noise 📺 Tell us your fave tips & tricks for taking advantage of AI apps on your GPU below + comment #AIonRTX to win a AORUS GIGABYTE GeForce RTX 4080 16GB GAMING OC GPU!

NVIDIA GeForce

410,444 просмотров • 3 лет назад

As a supporter of the open weights ecosystem, we're proud to be a post-training partner for NVIDIA Nemotron. We post-train Nemotron models for customer use cases, de-risk mainline RL runs on our AC2 platform and training stack, and contribute aggregate workload statistics for inference benchmarking. This is how open models get better, and we're excited to keep working closely with NVIDIA AI.
0:11

As a supporter of the open weights ecosystem, we're proud to be a post-training partner for NVIDIA Nemotron. We post-train Nemotron models for customer use cases, de-risk mainline RL runs on our AC2 platform and training stack, and contribute aggregate workload statistics for inference benchmarking. This is how open models get better, and we're excited to keep working closely with NVIDIA AI.

Applied Compute

25,683 просмотров • 3 месяцев назад

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.
0:12

We’re releasing model weights for our 8B- parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. Learn more about how Dynamic Byte Latent Transformer is paving the way for groundbreaking developments in the field of language modeling. Read the research paper, and download the model and code.

AI at Meta

195,705 просмотров • 1 год назад

We are continuing to advance open-source AI. Just announced -- new tools for speech, safety, and autonomous driving. Learn about the open models, datasets, and research we’re releasing at #NeurIPS2025:
0:10

We are continuing to advance open-source AI. Just announced -- new tools for speech, safety, and autonomous driving. Learn about the open models, datasets, and research we’re releasing at #NeurIPS2025:

NVIDIA

69,061 просмотров • 11 месяцев назад

How to run AI models locally? -> Go to 🤗 Hugging Face -> Grab the GGUF model link -> Drop it into 👋 Jan Hub That's all there is to it.
0:12

How to run AI models locally? -> Go to 🤗 Hugging Face -> Grab the GGUF model link -> Drop it into 👋 Jan Hub That's all there is to it.

👋 Jan

44,726 просмотров • 1 год назад

90% of "AI developers" just download pre packaged GGUF files from Hugging Face, hit run, and call it a day. The top 10% know how to pull the raw safetensors, run the math, and quantize massive models into Q4_K_M themselves. If you think llama.cpp can only execute models, you’re missing the best part of the open source ecosystem. It’s a high performance optimization suite. Manually stripping 69% of the VRAM footprint off a brand new model architecture is where real infrastructure value is made. If you want to actually master local inference and deploy models like Google’s massive Gemma 4 12B it on consumer NVIDIA hardware using llama.cpp, you need to learn this pipeline. Let's build it. I just took the raw 22.7 GB Gemma 4 baseline and manually compressed it down to a 7.02 GB Q4_K_M GGUF artifact using llama.cpp. That is a 69% reduction in footprint. No quality loss. No VRAM bottlenecks. Just native, hardware accelerated C++ inference running a full 2,50,000 token context window on a dual NVIDIA Tesla T4 setup. Stop melting your VRAM on unoptimized weights and stop relying on other people's pipelines. Own your stack. I mapped this entire architecture from dynamic binary fetching to raw quantization and real time GPU streaming into a single, bulletproof notebook. Notebook link is in the comments below. Bookmark this blueprint for your next deployment and tell me which quantization works best for your workflow and model.
0:19

90% of "AI developers" just download pre packaged GGUF files from Hugging Face, hit run, and call it a day. The top 10% know how to pull the raw safetensors, run the math, and quantize massive models into Q4_K_M themselves. If you think llama.cpp can only execute models, you’re missing the best part of the open source ecosystem. It’s a high performance optimization suite. Manually stripping 69% of the VRAM footprint off a brand new model architecture is where real infrastructure value is made. If you want to actually master local inference and deploy models like Google’s massive Gemma 4 12B it on consumer NVIDIA hardware using llama.cpp, you need to learn this pipeline. Let's build it. I just took the raw 22.7 GB Gemma 4 baseline and manually compressed it down to a 7.02 GB Q4_K_M GGUF artifact using llama.cpp. That is a 69% reduction in footprint. No quality loss. No VRAM bottlenecks. Just native, hardware accelerated C++ inference running a full 2,50,000 token context window on a dual NVIDIA Tesla T4 setup. Stop melting your VRAM on unoptimized weights and stop relying on other people's pipelines. Own your stack. I mapped this entire architecture from dynamic binary fetching to raw quantization and real time GPU streaming into a single, bulletproof notebook. Notebook link is in the comments below. Bookmark this blueprint for your next deployment and tell me which quantization works best for your workflow and model.

Alok

62,631 просмотров • 3 месяцев назад

Qwen3.5-35B-A3B is now in Jan 🔥 It surpasses previous Qwen3 models more than 6× its size. Get the latest Jan at Thanks to Qwen for the base model and Georgi Gerganov for llama.cpp 💛
0:13

Qwen3.5-35B-A3B is now in Jan 🔥 It surpasses previous Qwen3 models more than 6× its size. Get the latest Jan at Thanks to Qwen for the base model and Georgi Gerganov for llama.cpp 💛

👋 Jan

34,433 просмотров • 8 месяцев назад

Announcing our latest open medical AI models for developers: MedGemma 1.5, which is small enough to run offline & improves performance on 3D imaging (CT & MRI), & MedASR, a speech-to-text model for medical dictation. Both available on Hugging Face + Vertex AI. #MedGemma #HealthAI #GenerativeAI
0:18

Announcing our latest open medical AI models for developers: MedGemma 1.5, which is small enough to run offline & improves performance on 3D imaging (CT & MRI), & MedASR, a speech-to-text model for medical dictation. Both available on Hugging Face + Vertex AI. #MedGemma #HealthAI #GenerativeAI

Google Research

395,893 просмотров • 9 месяцев назад

Frontier world models now run on edge GPUs. ⚡ Now openly available, NVIDIA Cosmos 3 Edge brings advanced world-model capabilities to local devices. The 4-billion-parameter omnimodel can understand and generate text, image, video, ambient sound and action for physical AI across robotics, autonomous vehicles and smart infrastructure. 🔗 #SIGGRAPH2026
0:15

Frontier world models now run on edge GPUs. ⚡ Now openly available, NVIDIA Cosmos 3 Edge brings advanced world-model capabilities to local devices. The 4-billion-parameter omnimodel can understand and generate text, image, video, ambient sound and action for physical AI across robotics, autonomous vehicles and smart infrastructure. 🔗 #SIGGRAPH2026

NVIDIA

33,144 просмотров • 3 месяцев назад

A Sun Parakeet shakes its head to the beat
0:16

A Sun Parakeet shakes its head to the beat

Science girl

41,293 просмотров • 1 год назад

Hey @NVIDIA, how do you make the perfect byte? From working with us to tech CEO, do breakfast like Jensen Huang with new NVIDIA Breakfast Bytes—only available for order online at now through May 13 NVIDIA GTC #GTC2025
0:14

Hey @NVIDIA, how do you make the perfect byte? From working with us to tech CEO, do breakfast like Jensen Huang with new NVIDIA Breakfast Bytes—only available for order online at now through May 13 NVIDIA GTC #GTC2025

Denny’s

59,988 просмотров • 1 год назад

It’s live. AxonDAO’s GPU fleet is installed and will soon be rentable on the open market via vast.ai. Premium GPU capacity - 8x NVIDIA B200 and 8x RTX Pro 6000 - built for large-scale AI training, inference, rendering, and research workloads. 🧵
0:14

It’s live. AxonDAO’s GPU fleet is installed and will soon be rentable on the open market via vast.ai. Premium GPU capacity - 8x NVIDIA B200 and 8x RTX Pro 6000 - built for large-scale AI training, inference, rendering, and research workloads. 🧵

AxonDAO

17,725 просмотров • 8 месяцев назад

WE DELIVER 24/7, DAY BY DAY! 03.06.2025! On Tuesday, ByteWallet will be launched and available to all ByteBlockchain miners. That is the day every $BYTE miner has been waiting for. Are you ready to transfer your $BYTE to ByteWallet? How much $BYTE are you holding now? Start mining $BYTE now:
0:18

WE DELIVER 24/7, DAY BY DAY! 03.06.2025! On Tuesday, ByteWallet will be launched and available to all ByteBlockchain miners. That is the day every $BYTE miner has been waiting for. Are you ready to transfer your $BYTE to ByteWallet? How much $BYTE are you holding now? Start mining $BYTE now:

ByteBlockchain.org

33,083 просмотров • 1 год назад

Want to bring open-source vision language models to the edge? 💻 Check out our Hugging Face article on deploying NVIDIA Cosmos Reasoning 2B across the NVIDIA Jetson family with vLLM and a Live VLM WebUI. 📖
0:17

Want to bring open-source vision language models to the edge? 💻 Check out our Hugging Face article on deploying NVIDIA Cosmos Reasoning 2B across the NVIDIA Jetson family with vLLM and a Live VLM WebUI. 📖

NVIDIA Robotics

54,057 просмотров • 8 месяцев назад

We’re proud to share that $vMINT is now a member of the NVIDIA Developer Program 🌟 This will provide us with the following things (among others): Access to over 150 SDKs for advanced software development Comprehensive training resources through the Deep Learning Institute and NVIDIA On-Demand for skill enhancement Early access programs Stay tuned for more exciting updates 👀 #Volumint $vMINT #nvidia $nvda #nvda #AI #Marketmaking
0:11

We’re proud to share that $vMINT is now a member of the NVIDIA Developer Program 🌟 This will provide us with the following things (among others): Access to over 150 SDKs for advanced software development Comprehensive training resources through the Deep Learning Institute and NVIDIA On-Demand for skill enhancement Early access programs Stay tuned for more exciting updates 👀 #Volumint $vMINT #nvidia $nvda #nvda #AI #Marketmaking

VoluMint Labs.

146,072 просмотров • 2 лет назад