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
bumpyclock
/
nemotron-speech-streaming-en-0.6b-int8
like
1
Automatic Speech Recognition
ONNX
English
parakeet-rs
nemotron
fastconformer
rnnt
int8
speech-recognition
streaming-asr
asr
License:
nvidia-open-model-license
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
nemotron-speech-streaming-en-0.6b-int8
918 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
bumpyclock
Add int8 (encoder MatMul-only) quantization of Nemotron Streaming 0.6B
bdf5c6c
verified
19 days ago
.gitattributes
Safe
1.57 kB
Add int8 (encoder MatMul-only) quantization of Nemotron Streaming 0.6B
19 days ago
NOTICE.txt
779 Bytes
Add int8 (encoder MatMul-only) quantization of Nemotron Streaming 0.6B
19 days ago
README.md
2.19 kB
Add int8 (encoder MatMul-only) quantization of Nemotron Streaming 0.6B
19 days ago
decoder_joint.onnx
Safe
35.8 MB
xet
Add int8 (encoder MatMul-only) quantization of Nemotron Streaming 0.6B
19 days ago
encoder.onnx
44.7 MB
xet
Add int8 (encoder MatMul-only) quantization of Nemotron Streaming 0.6B
19 days ago
encoder.onnx.data
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
838 MB
xet
Add int8 (encoder MatMul-only) quantization of Nemotron Streaming 0.6B
19 days ago
tokenizer.model
Safe
251 kB
xet
Add int8 (encoder MatMul-only) quantization of Nemotron Streaming 0.6B
19 days ago
