Qwen3-VL
Collection
9 items
•
Updated
•
179
fireblade2534
fireblade2534
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
16 days ago
Qwen3-VL
liked
a model
18 days ago
Qwen/Qwen-Image-Edit-2509
upvoted
a
collection
18 days ago
Qwen3-Omni
Organizations
None yet
upvoted
a
collection
16 days ago
liked
a
model
18 days ago
upvoted
a
collection
18 days ago
liked
a
model
21 days ago
liked
a
dataset
30 days ago
liked
2
models
about 1 month ago
liked
a
model
about 2 months ago
liked
a
model
3 months ago
liked
4
models
4 months ago
OpenBuddy/OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview2-QAT
Text Generation
•
33B
•
Updated
•
5
•
12
moonshotai/Kimi-Dev-72B
Text Generation
•
73B
•
Updated
•
6.34k
•
•
370
tencent/SongGeneration
Text-to-Audio
•
Updated
•
1.13k
•
233
nanonets/Nanonets-OCR-s
Image-Text-to-Text
•
4B
•
Updated
•
129k
•
1.53k
liked
a
Space
4 months ago
liked
a
model
5 months ago
liked
a
Space
5 months ago
liked
a
model
5 months ago
liked
2
Spaces
5 months ago
reacted to
fdaudens's
post with 🔥
5 months ago
Post
3211
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: nvidia/parakeet-tdt-0.6b-v2
Demo: nvidia/parakeet-tdt-0.6b-v2
ASR Leaderboard: hf-audio/open_asr_leaderboard
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: nvidia/parakeet-tdt-0.6b-v2
Demo: nvidia/parakeet-tdt-0.6b-v2
ASR Leaderboard: hf-audio/open_asr_leaderboard
- 1 reply