Kunal Dhawan

kunaldhawan's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 collections about 3 hours ago

Nemotron Labs Dory

Collection

Open looped language models with elastic depth, serving different compute budgets from a single checkpoint. • 4 items • Updated 10 days ago • 18

Nemotron 3.5 Transcribe

Collection

Open-weight offline ASR model supporting 40 languages, 1-hr audio, and 64k context. Hybrid MoE (~4.3B active). Available in BF16, FP8, and NVFP4. • 7 items • Updated about 3 hours ago • 8

upvoted an article 1 day ago

view article

Article

NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

• 

nvidia

•

1 day ago

• 76

upvoted an article 5 months ago

view article

Article

How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent

• 

nvidia

•

Jun 4

• 81

upvoted a collection 10 months ago

Nemotron Speech

Collection

Open, state-of-the-art, production‑ready enterprise speech models from the NVIDIA Speech research team for ASR, TTS, Speaker Diarization and S2S • 17 items • Updated about 3 hours ago • 75

upvoted an article 10 months ago

view article

Article

Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR

• 

nvidia

•

Jan 5

• 93

upvoted 2 papers over 1 year ago

Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer

Paper • 2306.08753 • Published Jun 14, 2023 • 2

Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations

Paper • 2407.03495 • Published Jul 3, 2024 • 1