-
bezzam/omniasr-llm-7b-v2
Automatic Speech Recognition • 8B • Updated • 165 • 1 -
bezzam/omniasr-ctc-7b-v2
Automatic Speech Recognition • 7B • Updated • 92 -
bezzam/omniasr-llm-3b-v2
Automatic Speech Recognition • 4B • Updated • 112 -
bezzam/omniasr-ctc-3b-v2
Automatic Speech Recognition • 3B • Updated • 115
Eric Bezzam PRO
bezzam
AI & ML interests
speech, audio, imaging
Recent Activity
updated a Space about 23 hours ago
hf-audio/open_tts_leaderboard updated a bucket about 23 hours ago
hf-audio/tts_leaderboard_h200 updated a collection about 24 hours ago
TTS evalOrganizations
https://ai.meta.com/blog/omnilingual-asr-advancing-automatic-speech-recognition/
Models for DigiCam trained on the CelebA 26K dataset.
-
bezzam/omniasr-llm-7b-v2
Automatic Speech Recognition • 8B • Updated • 165 • 1 -
bezzam/omniasr-ctc-7b-v2
Automatic Speech Recognition • 7B • Updated • 92 -
bezzam/omniasr-llm-3b-v2
Automatic Speech Recognition • 4B • Updated • 112 -
bezzam/omniasr-ctc-3b-v2
Automatic Speech Recognition • 3B • Updated • 115
https://ai.meta.com/blog/omnilingual-asr-advancing-automatic-speech-recognition/
Models for DigiCam trained on the CelebA 26K dataset.
Models for the paper "A modular and robust physics-based approach for lensless image reconstruction"