Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
juanquivilla
/
sotto-cleanup-lfm25-350m
like
0
Text Generation
Safetensors
juanquivilla/sotto-transcript-cleanup
English
lfm2
speech-to-text
transcript-cleanup
text-correction
asr-post-processing
LFM
LiquidAI
grpo
full-fine-tune
inverse-text-normalization
conversational
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
sotto-cleanup-lfm25-350m
714 MB
Ctrl+K
Ctrl+K
1 contributor
History:
33 commits
juanquivilla
soup: corrected README with full prod metrics + soup explanation
6df6f01
verified
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
3 months ago
README.md
5.2 kB
soup: corrected README with full prod metrics + soup explanation
about 2 months ago
chat_template.jinja
Safe
1.3 kB
Upload folder using huggingface_hub
3 months ago
config.json
Safe
1.31 kB
v51: composite=88.68 β see model card for benchmark deltas vs v45
about 2 months ago
generation_config.json
Safe
141 Bytes
v45: SFT+chained GRPO with ITN β 95.9% number accuracy, 97.0% filler-free, deletion behavior matches v36
about 2 months ago
model.safetensors
709 MB
xet
soup_30: composite=89.45 β see model card for benchmark deltas vs v45
about 2 months ago
tokenizer.json
Safe
4.73 MB
Upload folder using huggingface_hub
3 months ago
tokenizer_config.json
Safe
548 Bytes
v36: full-FT GRPO with substantive-deletion-aware reward β filler-free 96.9%, sub-del-15-long 0.64%
about 2 months ago
training_args.bin
Safe
5.71 kB
xet
v15: ROUGE-L 0.960, 70% exact match β LR 2.5e-5 breakthrough
3 months ago