Kyle PRO

iky1e's activity

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

upvoted a collection about 9 hours ago

Bonsai

Collection

1-bit Bonsai models • 6 items • Updated 2 days ago • 119

upvoted an article about 19 hours ago

view article

Article

Speculative Decoding for 2x Faster Whisper Inference

• 

Dec 20, 2023

•

32

upvoted a paper 4 days ago

Voxtral TTS

Paper • 2603.25551 • Published 7 days ago • 56

upvoted a collection 6 days ago

UnifoLM_WBT_Dataset

Collection

8 items • Updated 6 days ago • 71

upvoted an article 6 days ago

view article

Article

Introducing Cohere-transcribe: state-of-the-art speech recognition

• 

7 days ago

•

34

upvoted a paper 16 days ago

Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and AST

Paper • 2509.14128 • Published Sep 17, 2025 • 2

upvoted 2 collections 17 days ago

Demucs MLX — Music Source Separation

Collection

Demucs music stem separation for Apple Silicon. Float32 and float16 variants. • 2 items • Updated 17 days ago • 1

Granite Speech Models

Collection

Multilingual ASR and speech-to-text (STT) models for enterprise transcription and translation. • 6 items • Updated about 23 hours ago • 24

upvoted a collection 19 days ago

DeepFilterNet-MLX

Collection

MLX ports of the DeepFilterNet speech enhancement models for Apple Silicon • 7 items • Updated 19 days ago • 1

upvoted 3 papers 19 days ago

DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filtering

Paper • 2110.05588 • Published Oct 11, 2021 • 1

DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audio

Paper • 2205.05474 • Published May 11, 2022 • 1

DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement

Paper • 2305.08227 • Published May 14, 2023 • 2

upvoted a paper 20 days ago

Sasha: Creative Goal-Oriented Reasoning in Smart Homes with Large Language Models

Paper • 2305.09802 • Published May 16, 2023 • 1

upvoted a collection 20 days ago

Flavors of Moonshine

Collection

A suite of tiny automatic speech recognition (ASR) models specialized for a range of underrepresented languages. • 6 items • Updated Sep 11, 2025 • 2

upvoted a paper 20 days ago

Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices

Paper • 2509.02523 • Published Sep 2, 2025 • 21

upvoted a collection 20 days ago

Speech

Collection

2 items • Updated May 2, 2025 • 1

upvoted a paper 20 days ago

Moonshine: Speech Recognition for Live Transcription and Voice Commands

Paper • 2410.15608 • Published Oct 21, 2024 • 12

upvoted a collection 20 days ago

Transformers.js V4 demos

Collection

A collection of demos built with Transformers.js V4 • 22 items • Updated 2 days ago • 39

upvoted a paper 20 days ago

Sharp Monocular View Synthesis in Less Than a Second

Paper • 2512.10685 • Published Dec 11, 2025 • 29

upvoted a collection 22 days ago

SEA-LION v4

Collection

15 items • Updated 17 days ago • 12