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
cstr
/
nemotron-3.5-asr-streaming-GGUF
Like
6
Automatic Speech Recognition
GGUF
35 languages
asr
speech-recognition
streaming
fastconformer
rnnt
multilingual
crispasr
License:
openmdw-1.1
Model card
Files
Files and versions
xet
Community
1
Copy to bucket
new
main
nemotron-3.5-asr-streaming-GGUF
1.69 GB
Ctrl+K
Ctrl+K
1 contributor
History:
12 commits
cstr
Requantize nemotron-3.5-asr-streaming-0.6b-q4_k.gguf: conv pw1/pw2 F16→Q8_0 (#81 CPU perf fix; all other tensors byte-identical)
61e58fb
verified
3 months ago
.gitattributes
Safe
1.75 kB
Add Q4_K quantized model
4 months ago
README.md
Safe
7.22 kB
Update README with streaming docs, env vars, quality reference
4 months ago
nemotron-3.5-asr-streaming-0.6b-f16.gguf
Safe
1.29 GB
xet
Replace F16 with fixed converter (F32 pre-encode, correct tensor names)
4 months ago
nemotron-3.5-asr-streaming-0.6b-q4_k.gguf
Safe
409 MB
xet
Requantize nemotron-3.5-asr-streaming-0.6b-q4_k.gguf: conv pw1/pw2 F16→Q8_0 (#81 CPU perf fix; all other tensors byte-identical)
3 months ago