Article
Yang-Mills, OpenAI proof, and the mass gap problem
dlouapre
• • 7
Eustache Le Bihan
eustlb
AI & ML interests
Audio - ASR
Recent Activity
upvoted an article about 2 hours ago
Yang-Mills, OpenAI proof, and the mass gap problem new activity 3 days ago
nvidia/Nemotron-3-Diarization:PostProcessing Config via Transformers new activity 3 days ago
eustlb/LFM3-Audio-2B:Native transformers configs (huggingface/transformers#50393)Organizations
upvoted an article about 2 hours ago
PostProcessing Config via Transformers
3
#8 opened 23 days ago
by 
erklem
Native transformers configs (huggingface/transformers#50393)
#1 opened 3 days ago
by eustlb
updated a
model 3 days ago
published a
model 3 days ago
updated a
model 3 days ago
published a
model 3 days ago
Point users to the official bosonai/higgs-audio-v2-tokenizer?
2
#1 opened 7 days ago
by 
bytebecky
Update audio_tokenizer model card to point to official bosonai repo
#40 opened 4 days ago
by eustlb
updated a
model 4 days ago
upvoted an article 8 days ago
Article
A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.
- +2
olesiagradium, lmz, bezzam, eustlb
• • 40 published an article 9 days ago
Article
A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.
- +2
olesiagradium, lmz, bezzam, eustlb
• • 40 Add Hugging Face Transformers support
#5 opened 16 days ago
by eustlb
updated a
bucket 16 days ago
Add Hugging Face Transformers support
👍 1
1
#2 opened 16 days ago
by eustlb
published a
bucket 16 days ago
updated 4
Spaces 19 days ago
The State of Open Source Audio
🎧
2
55K open audio models across seven tasks, and who ships them
Who ships TTS models
🏗
Labs shipping TTS models, ranked by engagement earned
Number of audio-text-to-text models on the Hub
💬
Monthly audio-text-to-text models on the Hub, with landmark
Number of VAD models on the Hub
📈
2
Monthly voice activity detection models on the Hub, with lan