Blog, Articles, and discussions

Gemma 3n fully available in the open-source ecosystem!

By June 26, 2025 • 115

Community Articles

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

and 5 others •

Code a simple RAG from scratch

Uncensor any LLM with abliteration

Supercharge Edge AI With High‑Accuracy Reasoning Using NVIDIA Nemotron Nano 2 9B

and 9 others •

AV1 for robotics AI streaming, training and storage.

Luth: Efficient French Specialization for Small Language Models

and 1 other •

European Vision-Language Model Optimization for Nuclear Regulatory Data

Introducing Marvis TTS: Real-Time Streaming Speech Synthesis

KV Caching Explained: Optimizing Transformer Inference Efficiency

Making any LLM model "reasoning"

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

NVIDIA Releases 6 Million Multi-Lingual Reasoning Dataset

and 4 others •

Psychology: Identity Constructs and Constraint-Based Emotion

Building a Hugging Face AI Agent with Bright Data’s Web MCP Integration

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

and 5 others •

Introducing ColQwen-Omni: Retrieve in every modality

and 4 others •

How French People Use AI in Everyday Life

🕳️ Attention Sinks in LLMs for endless fluency

The Large Language Model Course

Blazingly fast whisper transcriptions with Inference Endpoints

By May 13, 2025 • 74

Hugging Face and Cloudflare Partner to Make Real-Time Speech and Video Seamless with FastRTC

By April 9, 2025 • 28

HuggingFace, IISc partner to supercharge model building on India's diverse languages

By February 27, 2025 • 22

FastRTC: The Real-Time Communication Library for Python

By February 25, 2025 • 172

Deploying Speech-to-Speech on Hugging Face

By October 22, 2024 • 41

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

By May 1, 2024 • 80

Fine-Tune W2V2-Bert for low-resource ASR with 🤗 Transformers

By January 19, 2024 • 39

Speculative Decoding for 2x Faster Whisper Inference

By December 20, 2023 • 30

AudioLDM 2, but faster ⚡️

By August 30, 2023 • 14

Deploy MusicGen in no time with Inference Endpoints

By August 4, 2023 • 4

Fine-tuning MMS Adapter Models for Multi-Lingual ASR

By June 19, 2023 • 20

Speech Synthesis, Recognition, and More With SpeechT5

By February 8, 2023 • 12

A Complete Guide to Audio Datasets

By December 15, 2022 • 39

Fine-Tune Whisper with 🤗 Transformers

By November 3, 2022 • 285

Community Articles

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

and 5 others •

Code a simple RAG from scratch

Uncensor any LLM with abliteration

Supercharge Edge AI With High‑Accuracy Reasoning Using NVIDIA Nemotron Nano 2 9B

and 9 others •

AV1 for robotics AI streaming, training and storage.

Luth: Efficient French Specialization for Small Language Models

and 1 other •

European Vision-Language Model Optimization for Nuclear Regulatory Data

Introducing Marvis TTS: Real-Time Streaming Speech Synthesis

KV Caching Explained: Optimizing Transformer Inference Efficiency

Making any LLM model "reasoning"

ChatML vs Harmony: Understanding the new Format from OpenAI 🔍

NVIDIA Releases 6 Million Multi-Lingual Reasoning Dataset

and 4 others •

Psychology: Identity Constructs and Constraint-Based Emotion

Building a Hugging Face AI Agent with Bright Data’s Web MCP Integration

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

and 5 others •

Introducing ColQwen-Omni: Retrieve in every modality

and 4 others •

How French People Use AI in Everyday Life

🕳️ Attention Sinks in LLMs for endless fluency

The Large Language Model Course

View all