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
Luigi
/
MOSS-TTS-Nano-100M-GGUF
like
0
ONNX
GGUF
Chinese
English
tts
moss
jetson
ggml
edge
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
MOSS-TTS-Nano-100M-GGUF
1.46 GB
Ctrl+K
Ctrl+K
1 contributor
History:
14 commits
Luigi
int8 AR ONNX (dynamic QInt8, ~1.5x faster CPU, weights-only)
f97fffb
verified
29 days ago
MOSS-Audio-Tokenizer-Nano-ONNX
demo: codec ONNX (encode+decode for voice clone + streaming)
29 days ago
MOSS-TTS-Nano-100M-ONNX-int8
int8 AR ONNX (dynamic QInt8, ~1.5x faster CPU, weights-only)
29 days ago
MOSS-TTS-Nano-100M-ONNX
AR ONNX (prefill/decode/local + manifest) for the ORT demo backend
29 days ago
tokenizer
demo: tokenizer config.json
29 days ago
.gitattributes
Safe
2.06 kB
AR ONNX (prefill/decode/local + manifest) for the ORT demo backend
29 days ago
README.md
Safe
1.28 kB
card
29 days ago
browser_poc_manifest.json
Safe
503 kB
demo: prompt-config manifest (token ids + templates)
29 days ago
moss_codec.gguf
13.3 MB
xet
split moss_codec.gguf
29 days ago
moss_nano.gguf
125 MB
xet
split moss_nano.gguf
29 days ago
moss_nano_full.gguf
138 MB
xet
MOSS-TTS-Nano Q8_0 merged AR+codec (verified, RTF 0.35 w/ custom kernel)
29 days ago
