Eric Bezzam PRO
AI & ML interests
speech, audio, imaging
Recent Activity
liked a model about 1 hour ago
k2-fsa/OmniVoice upvoted an article about 3 hours ago
Introducing Cohere-transcribe: state-of-the-art speech recognition updated a model about 7 hours ago
bezzam/Qwen3-ForcedAligner-0.6BOrganizations
Omnilingual ASR (1,600+ Languages)
https://ai.meta.com/blog/omnilingual-asr-advancing-automatic-speech-recognition/
- Paused240
Omnilingual ASR Media Transcription
🌍240Transcribe audio/video files into text instantly
-
facebook/omnilingual-asr-corpus
Viewer • Updated • 548k • 4.82k • 201 -
facebook/omniASR-CTC-300M
Automatic Speech Recognition • Updated • 13 -
facebook/omniASR-CTC-1B
Automatic Speech Recognition • Updated • 6
Speech recognition datasets
DigiCam (CelebA)
Models for DigiCam trained on the CelebA 26K dataset.
VibeVoice
Neural codecs
Omnilingual ASR (1,600+ Languages)
https://ai.meta.com/blog/omnilingual-asr-advancing-automatic-speech-recognition/
- Paused240
Omnilingual ASR Media Transcription
🌍240Transcribe audio/video files into text instantly
-
facebook/omnilingual-asr-corpus
Viewer • Updated • 548k • 4.82k • 201 -
facebook/omniASR-CTC-300M
Automatic Speech Recognition • Updated • 13 -
facebook/omniASR-CTC-1B
Automatic Speech Recognition • Updated • 6
Multimodel audio
Speech recognition datasets
Text-to-speech datasets
DigiCam (CelebA)
Models for DigiCam trained on the CelebA 26K dataset.
DiffuserCam Mirflickr
Models for the paper "A modular and robust physics-based approach for lensless image reconstruction"