Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
George Saon
gsaon
56
11
56
Follow
vivekrp's profile picture
Flyxion's profile picture
walter-528's profile picture
22 followers
·
24 following
https://research.ibm.com/people/george-saon
saon53915
gsaon
george-saon-37527b1b
AI & ML interests
ASR
Recent Activity
updated
a Space
12 days ago
ibm-granite/granite-speech-streaming-webgpu
new
activity
12 days ago
ibm-granite/granite-speech-streaming-webgpu:
Fix mic-start race causing orphaned dictation sessions on Safari
liked
a model
12 days ago
iky1e/granite-speech-5.0-470m-turboctc-mlx-q5
View all activity
Organizations
gsaon
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
New activity in
ibm-granite/granite-speech-streaming-webgpu
12 days ago
Fix mic-start race causing orphaned dictation sessions on Safari
🔥
1
#1 opened 12 days ago by
kristunlee
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc-nc
14 days ago
Model systematically turn 's into is
3
#8 opened 15 days ago by
nshmyrevgmail
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc-nc
18 days ago
Demo for this model on Spaces
🔥
1
1
#7 opened 19 days ago by
multimodalart
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc-nc
20 days ago
Update README with disclaimer
#6 opened 20 days ago by
kristunlee
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc
20 days ago
add pipeline_tag and library_name
#6 opened 20 days ago by
eustlb
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc-nc
20 days ago
convert to transformers format
👍
1
#4 opened 21 days ago by
eustlb
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc
21 days ago
bf16 as default dtype
#5 opened 21 days ago by
eustlb
convert to transformers format
1
#4 opened 21 days ago by
eustlb
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc-nc
24 days ago
Update README.md
1
#3 opened 24 days ago by
kristunlee
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc
28 days ago
Unify tokenizer to 16384 with blank at id 0 (no +1 offset)
#3 opened 28 days ago by
gsaon
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc-nc
28 days ago
Simplify decode: remove num_special_tokens/token_id_offset (blank at id 0, 1:1 ids)
#2 opened 28 days ago by
gsaon
Mirror model from gsaon/testCTC (masayuki 191a5h p25; bf16 weights)
#1 opened 28 days ago by
gsaon
New activity in
ibm-granite/granite-speech-5.0-470m-turboctc
about 1 month ago
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 1 month ago by
gsaon
New activity in
ibm-granite/granite-speech-4.1-2b
4 months ago
Is peak/loudness normalisation needed for quiet audio segments?
1
#9 opened 4 months ago by
GokseninYuksel
ONNX versions created:
🔥
2
1
#7 opened 4 months ago by
smcleod
What is the function of the weights in out_llm.safetensors?
1
#6 opened 4 months ago by
deathknight0
New activity in
ibm-granite/granite-speech-4.1-2b
5 months ago
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
Load more