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
oddadmix
/
Kokoro-7M-Distill
Like
16
Text-to-Speech
English
tts
english
kokoro
styletts2
distillation
on-device
knowledge-distillation
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Copy to bucket
new
main
Kokoro-7M-Distill
Ctrl+K
Ctrl+K
1 contributor
History:
10 commits
oddadmix
Upload folder using huggingface_hub
9357717
verified
about 7 hours ago
kokoro_patched
Upload folder using huggingface_hub
8 days ago
training
Upload folder using huggingface_hub
about 7 hours ago
.gitattributes
Safe
1.52 kB
initial commit
8 days ago
README.md
Safe
3.71 kB
Rewrite the card for public release: drop scores and the experiment history
4 days ago
TRAINING.md
5.85 kB
Upload TRAINING.md with huggingface_hub
about 7 hours ago
af_heart.pt
Safe
524 kB
xet
Upload folder using huggingface_hub
8 days ago
af_msa.pt
Safe
pickle
Detected Pickle imports (3)
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
What is a pickle import?
524 kB
xet
Default to af_msa.pt: the style pack the student was distilled on (UTMOS 4.138 vs 3.570, WER 0.0525 vs 0.0701)
8 days ago
config.json
Safe
2.16 kB
Upload folder using huggingface_hub
8 days ago
kokoro_en_7m.pth
Safe
30.1 MB
xet
Upload folder using huggingface_hub
8 days ago
load_model.py
Safe
1.66 kB
Rename to Kokoro-7M-Distill; card leads with the 4.1x CPU speedup at level quality
7 days ago
