Marc-Antoine Allard's picture

Marc-Antoine Allard

Mallard74

·

AI & ML interests

Passionate about machine learning, NLP, ASR etc.

Recent Activity

authored a paper 14 days ago

Experiential Reflective Learning for Self-Improving LLM Agents

upvoted an article 7 months ago

Gaia2 and ARE: Empowering the community to study agents

upvoted an article 7 months ago

Open-source DeepResearch – Freeing our search agents

View all activity

Organizations

liked a Space 9 months ago

Open ASR Leaderboard

Explore speech recognition model benchmarks and request new ones

liked 2 models 9 months ago

nvidia/canary-qwen-2.5b

Automatic Speech Recognition • 3B • Updated Dec 15, 2025 • 152k • 408

microsoft/MediPhi-PubMed

Text Generation • 4B • Updated Dec 15, 2025 • 148 • 10

liked a Space 9 months ago

ICML2025

Streamlit template space

liked a model 9 months ago

kyutai/mimi

Feature Extraction • 96.2M • Updated Jul 2, 2025 • 1.32M • • 295

liked 3 models 10 months ago

kyutai/stt-1b-en_fr

Automatic Speech Recognition • Updated Nov 18, 2025 • 123

kyutai/stt-2.6b-en

Automatic Speech Recognition • Updated Jun 26, 2025 • 120

mistralai/Magistral-Small-2506

24B • Updated Jul 28, 2025 • 42.9k • 609

liked a Space 10 months ago

AI Text Detector

Detect AI-generated texts with precision

liked a dataset 11 months ago

linagora/SUMM-RE

Viewer • Updated Oct 15, 2024 • 832 • 1.38k • 4

liked a model 12 months ago

nvidia/Llama-3_1-Nemotron-Ultra-253B-v1

Text Generation • Updated Oct 15, 2025 • 6.12k • • 343

liked 8 models about 1 year ago

meta-llama/Llama-4-Scout-17B-16E-Instruct

Image-Text-to-Text • Updated May 22, 2025 • 320k • • 1.26k

bofenghuang/whisper-large-v3-distil-multi4-v0.2

Automatic Speech Recognition • 0.8B • Updated Mar 28, 2025 • 47 • 1

distil-whisper/distil-large-v3.5

Automatic Speech Recognition • 0.8B • Updated Mar 25, 2025 • 42.4k • 87

nvidia/stt_fr_fastconformer_hybrid_large_pc

Automatic Speech Recognition • Updated Feb 27, 2025 • 447 • 6

mistralai/Mistral-Small-3.1-24B-Instruct-2503

Updated Dec 22, 2025 • 525k • 1.36k

microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • 6B • Updated Dec 10, 2025 • 351k • 1.58k

Qwen/QwQ-32B

Text Generation • 33B • Updated Mar 11, 2025 • 68.8k • • 2.89k

sesame/csm-1b

Text-to-Speech • Updated Dec 1, 2025 • 153k • 2.36k

liked a Space about 1 year ago

Sesame CSM

Conversational speech generation