George Saon's picture

22 2 6

George Saon

gsaon

·

https://research.ibm.com/people/george-saon

gsaon

AI & ML interests

ASR

Recent Activity

upvoted a collection 3 days ago

replied to randomblock1's post 3 days ago

Try IBM's Granite Speech 3.3 8B in a Space! Currently ranks #2 on the Open ASR Leaderboard (https://huggingface.co/spaces/hf-audio/open_asr_leaderboard) by Word Error Rate. My go-to transcription model is probably still https://huggingface.co/nvidia/parakeet-tdt-0.6b-v2, as Granite does not perform punctuation or capitalization. Still interesting nonetheless! https://huggingface.co/spaces/randomblock1/granite-speech-3.3 (sorry it's slow, it runs on base CPU)

liked a Space 3 days ago

randomblock1/granite-speech-3.3

View all activity

Organizations

upvoted a collection 3 days ago

Granite Speech

3 items • Updated May 2 • 13

replied to randomblock1's post 3 days ago

Hey, thanks for trying out our model! I really wish you could run it on a GPU otherwise it's super slow. Something you may want to experiment with is code-switching: you can upload an audio file with multiple languages in the same sentence (from English, French, German, Spanish and Portuguese).

liked a Space 3 days ago

Granite Speech 3.3 Speech-To-Text

granite-speech-3.3-8b in a huggingface space

New activity in ibm-granite/granite-speech-3.3-8b 4 days ago

Earnings22

#16 opened 6 days ago by

updated 2 models 5 days ago

ibm-granite/granite-speech-3.3-2b

Automatic Speech Recognition • 3B • Updated 5 days ago • 56.1k • 28

ibm-granite/granite-speech-3.3-8b

Automatic Speech Recognition • 9B • Updated 5 days ago • 7.09k • 109

New activity in ibm-granite/granite-speech-3.3-8b 15 days ago

Vllm LORA Modules

#15 opened 15 days ago by

New activity in Ganbatte/STT-parakeet-tdt-0.6b-v2 18 days ago

🚩 Report: Spam

#1 opened 18 days ago by

liked a model 28 days ago

ibm-granite/granite-speech-3.3-2b

Automatic Speech Recognition • 3B • Updated 5 days ago • 56.1k • 28

New activity in ibm-granite/granite-speech-3.3-8b about 1 month ago

Scripts fpr finetuning this model on custom data

#9 opened 2 months ago by

New activity in ibm-granite/granite-speech-3.3-2b about 2 months ago

Update README.md

#8 opened about 2 months ago by

New activity in ibm-granite/granite-speech-3.3-8b about 2 months ago

Update README.md

#14 opened about 2 months ago by

Dear author, I would like to know what is the minimum version of VLLM required to run this model?

#13 opened about 2 months ago by

New activity in ibm-granite/granite-speech-3.3-2b about 2 months ago

Is there any plan for publishing the training code?

#7 opened about 2 months ago by

liked a model about 2 months ago

ibm-granite/granite-speech-3.3-8b

Automatic Speech Recognition • 9B • Updated 5 days ago • 7.09k • 109

New activity in ibm-granite/granite-speech-3.3-8b 2 months ago

Long Form Audio

#10 opened 2 months ago by

What Transformers version is required?

#8 opened 2 months ago by

Update config.json

#11 opened 2 months ago by

Upload folder using huggingface_hub

#12 opened 2 months ago by

New activity in ibm-granite/granite-speech-3.3-2b 2 months ago

Upload folder using huggingface_hub

#6 opened 2 months ago by