Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Duplicated from
k2-fsa/OmniVoice
pravinuxd
/
OmniVoice
like
0
Text-to-Speech
Safetensors
ELM
JAX
646 languages
omnivoice
zero-shot
multilingual
voice-cloning
voice-design
arxiv:
2604.00688
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
OmniVoice
3.27 GB
Ctrl+K
Ctrl+K
2 contributors
History:
12 commits
pravinuxd
perf: int8/fp16 quantisations + configurable num_step (dub.py)
a73c911
verified
18 days ago
audio_tokenizer
Duplicate from k2-fsa/OmniVoice
20 days ago
omnivoice
Upload OmniVoice weights and tokenizer snapshot
19 days ago
.gitattributes
Safe
1.57 kB
Duplicate from k2-fsa/OmniVoice
20 days ago
.gitignore
Safe
35 Bytes
Upload OmniVoice weights and tokenizer snapshot
19 days ago
README.md
Safe
8.77 kB
Duplicate from k2-fsa/OmniVoice
20 days ago
chat_template.jinja
Safe
4.17 kB
Duplicate from k2-fsa/OmniVoice
20 days ago
config.json
Safe
2.24 kB
Duplicate from k2-fsa/OmniVoice
20 days ago
dub.py
Safe
70.2 kB
perf: int8/fp16 quantisations + configurable num_step (dub.py)
18 days ago
model.safetensors
Safe
2.45 GB
xet
Duplicate from k2-fsa/OmniVoice
20 days ago
publish-to-pravinuxd-hub.sh
Safe
1.33 kB
Upload OmniVoice weights and tokenizer snapshot
19 days ago
server.py
Safe
27.5 kB
add server.py for self-bootstrap
18 days ago
tokenizer.json
Safe
11.4 MB
xet
Duplicate from k2-fsa/OmniVoice
20 days ago
tokenizer_config.json
Safe
533 Bytes
Duplicate from k2-fsa/OmniVoice
20 days ago
