Yoach Lacombe

ylacombe's activity

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

updated 4 models 2 months ago

ylacombe/omniASR_W2V_300M_SSL

0.3B • Updated Nov 18, 2025 • 130

ylacombe/omniASR_W2V_1B_SSL

1.0B • Updated Nov 18, 2025 • 33

ylacombe/omniASR_W2V_3B_SSL

3B • Updated Nov 18, 2025 • 1.45k

ylacombe/omniASR_W2V_7B_SSL

6B • Updated Nov 18, 2025 • 7

liked a Space 2 months ago

Running on CPU Upgrade

Featured

2.92k

The Smol Training Playbook

📚

2.92k

The secrets to building world-class LLMs

published 4 models 2 months ago

ylacombe/omniASR_W2V_7B_SSL

6B • Updated Nov 18, 2025 • 7

ylacombe/omniASR_W2V_3B_SSL

3B • Updated Nov 18, 2025 • 1.45k

ylacombe/omniASR_W2V_1B_SSL

1.0B • Updated Nov 18, 2025 • 33

ylacombe/omniASR_W2V_300M_SSL

0.3B • Updated Nov 18, 2025 • 130

liked a Space 3 months ago

Running

77

Unlocking On-Policy Distillation for Any Model Family

📝

77

Improve model performance by transferring knowledge between different model families

upvoted an article 6 months ago

view article

Article

Parquet Content-Defined Chunking

• 

Jul 25, 2025

•

74

upvoted an article 7 months ago

view article

Article

Efficient MultiModal Data Pipeline

• 
• 
• +3

Jul 8, 2025

•

70

liked 2 models 8 months ago

Qwen/Qwen3-Embedding-0.6B

Feature Extraction • 0.6B • Updated Jun 20, 2025 • 2.01M • • 841

fishaudio/openaudio-s1-mini

Text-to-Speech • Updated Jun 2, 2025 • 4.6k • 557

liked a dataset 10 months ago

MrDragonFox/Elise

Viewer • Updated Mar 27, 2025 • 1.2k • 1.33k • 120

liked a model 11 months ago

speechbrain/asr-conformer-loquacious

Automatic Speech Recognition • Updated Jun 4, 2025 • 7 • 14

updated a model 12 months ago

ylacombe/accent-classifier

Audio Classification • 1.0B • Updated Feb 13, 2025 • 14 • 6

upvoted an article 12 months ago

view article

Article

1 Billion Classifications

• 

Feb 13, 2025

•

45

upvoted 2 collections 12 months ago

Speakers

Collection

A set of models dedicated to voice descriptions, with special focus on speaker traits (timbral and non-timbral characteristics, etc) • 3 items • Updated Jun 11, 2025 • 5

Hibiki fr-en

Collection

Hibiki is a model for streaming speech translation , which can run on device! See https://github.com/kyutai-labs/hibiki. • 7 items • Updated Dec 24, 2025 • 55