Yoach Lacombe

ylacombe's activity

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

updated 4 models 28 days ago

ylacombe/omniASR_W2V_300M_SSL

0.3B • Updated 28 days ago • 59

ylacombe/omniASR_W2V_1B_SSL

1.0B • Updated 28 days ago • 22

ylacombe/omniASR_W2V_3B_SSL

3B • Updated 28 days ago • 98

ylacombe/omniASR_W2V_7B_SSL

6B • Updated 28 days ago • 23

liked a Space about 1 month ago

Running on CPU Upgrade

Featured

2.6k

The Smol Training Playbook

📚

2.6k

The secrets to building world-class LLMs

published 4 models about 1 month ago

ylacombe/omniASR_W2V_7B_SSL

6B • Updated 28 days ago • 23

ylacombe/omniASR_W2V_3B_SSL

3B • Updated 28 days ago • 98

ylacombe/omniASR_W2V_1B_SSL

1.0B • Updated 28 days ago • 22

ylacombe/omniASR_W2V_300M_SSL

0.3B • Updated 28 days ago • 59

liked a Space about 2 months ago

Running

71

Unlocking On-Policy Distillation for Any Model Family

📝

71

Apply on-policy distillation to any model family

upvoted 2 articles 5 months ago

view article

Article

Parquet Content-Defined Chunking

• 

Jul 25

•

71

view article

Article

Efficient MultiModal Data Pipeline

• 
• 
• +3

Jul 8

•

59

liked 2 models 6 months ago

Qwen/Qwen3-Embedding-0.6B

Feature Extraction • 0.6B • Updated Jun 20 • 3.79M • • 782

fishaudio/openaudio-s1-mini

Text-to-Speech • Updated Jun 2 • 3.6k • 531

liked a dataset 9 months ago

MrDragonFox/Elise

Viewer • Updated Mar 27 • 1.2k • 2.14k • 113

liked a model 10 months ago

speechbrain/asr-conformer-loquacious

Automatic Speech Recognition • Updated Jun 4 • 44 • 14

updated a model 10 months ago

ylacombe/accent-classifier

Audio Classification • 1.0B • Updated Feb 13 • 28 • 6

upvoted an article 10 months ago

view article

Article

1 Billion Classifications

• 

Feb 13

•

45

upvoted 2 collections 10 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 • 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. • 5 items • Updated 6 days ago • 54