fireblade2534's picture

fireblade2534

fireblade2534

·

AI & ML interests

None yet

Recent Activity

liked a Space 1 day ago

ACE-Step/ACE-Step

liked a Space 3 days ago

RiverZ/ICEdit

reacted to fdaudens's post with 🔥 6 days ago

Forget everything you know about transcription models - NVIDIA's parakeet-tdt-0.6b-v2 changed the game for me! Just tested it with Steve Jobs' Stanford speech and was speechless (pun intended). The video isn’t sped up. 3 things that floored me: - Transcription took just 10 seconds for a 15-min file - Got a CSV with perfect timestamps, punctuation & capitalization - Stunning accuracy (correctly captured "Reed College" and other specifics) NVIDIA also released a demo where you can click any transcribed segment to play it instantly. The improvement is significant: number 1 on the ASR Leaderboard, 6% error rate (best in class) with complete commercial freedom (cc-by-4.0 license). Time to update those Whisper pipelines! H/t @Steveeeeeeen for the finding! Model: https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2 Demo: https://huggingface.co/spaces/nvidia/parakeet-tdt-0.6b-v2 ASR Leaderboard: https://huggingface.co/spaces/hf-audio/open_asr_leaderboard

View all activity

Organizations

None yet

fireblade2534's activity

upvoted a collection 9 days ago

Qwen3

27 items • Updated about 12 hours ago • 545

upvoted a collection 10 days ago

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 65 items • Updated about 4 hours ago • 137

upvoted a collection 13 days ago

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & outperforms all leading quantization methods. • 29 items • Updated 7 days ago • 84

upvoted a collection 2 months ago

Phi-4

Phi-4 family of small language, multi-modal and reasoning models. • 13 items • Updated 7 days ago • 141

upvoted 6 articles 3 months ago

Article

Build awesome datasets for video generation

Feb 12

• 30

Article

From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub

Feb 12

• 64

Article

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

Jan 23

• 174

Article

Finally, a Replacement for BERT: Introducing ModernBERT

Dec 19, 2024

• 624

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.24k

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 852

upvoted a collection 5 months ago

Hermes 3

The Hermes 3 Series of Models • 12 items • Updated Feb 13 • 120