George Saon
AI & ML interests
ASR
Recent Activity
updated a model 3 days ago
ibm-granite/granite-speech-5.0-470m-turboctc liked a Space 4 days ago
embedl/hfviewer liked a model 5 days ago
diarizeapp/granite-speech-5.0-470m-turboctc-onnxOrganizations
Fix mic-start race causing orphaned dictation sessions on Safari
🔥 1
#1 opened 20 days ago
by
kristunlee
Model systematically turn 's into is
3
#8 opened 22 days ago
by
nshmyrevgmail
Demo for this model on Spaces
🔥 1
1
#7 opened 27 days ago
by
multimodalart
Update README with disclaimer
#6 opened 27 days ago
by
kristunlee
add pipeline_tag and library_name
#6 opened 27 days ago
by
eustlb
convert to transformers format
👍 1
#4 opened 28 days ago
by
eustlb
bf16 as default dtype
#5 opened 28 days ago
by
eustlb
convert to transformers format
1
#4 opened 28 days ago
by
eustlb
Update README.md
1
#3 opened about 1 month ago
by
kristunlee
Unify tokenizer to 16384 with blank at id 0 (no +1 offset)
#3 opened about 1 month ago
by
gsaon
Simplify decode: remove num_special_tokens/token_id_offset (blank at id 0, 1:1 ids)
#2 opened about 1 month ago
by
gsaon
Mirror model from gsaon/testCTC (masayuki 191a5h p25; bf16 weights)
#1 opened about 1 month ago
by
gsaon
Update weights: robust T2623 p25_lr1e5_a0p4 (bf16, BN stats fp32)
#2 opened about 1 month ago
by
gsaon
Add packaged CTC Conformer export (C-T26.23, roman_bpe tokenizer, bf16 weights)
#1 opened about 2 months ago
by
gsaon
Is peak/loudness normalisation needed for quiet audio segments?
1
#9 opened 4 months ago
by
GokseninYuksel
ONNX versions created:
🔥 2
1
#7 opened 5 months ago
by
smcleod
What is the function of the weights in out_llm.safetensors?
1
#6 opened 5 months ago
by
deathknight0
Update README
#4 opened 5 months ago
by
kristunlee
Add punctuation and capitalization evaluation results
#2 opened 5 months ago
by
gsaon
Upload folder using huggingface_hub
#1 opened 5 months ago
by
gsaon