Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

HY-2012
/
M5-TTS.AXERA

Text-to-Speech
axera
ax650
npu
voice-cloning
zero-shot
m5-tts
python
cpp
Model card Files Files and versions
xet
Community
M5-TTS.AXERA / samples /listen
1.68 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
HY-2012's picture
HY-2012
remove fp32-era assets (kept on v1-fp32)
e0fb3c4 verified 1 day ago
  • stream
    all-NPU: int8/fp16 host tables, in-graph codec RVQ (443 MB) 1 day ago
  • cpp_en.wav
    173 kB
    xet
    all-NPU: int8/fp16 host tables, in-graph codec RVQ (443 MB) 1 day ago
  • cpp_greedy.wav
    157 kB
    xet
    all-NPU: int8/fp16 host tables, in-graph codec RVQ (443 MB) 1 day ago
  • cpp_long.wav
    419 kB
    xet
    all-NPU: int8/fp16 host tables, in-graph codec RVQ (443 MB) 1 day ago
  • cpp_zh.wav
    169 kB
    xet
    all-NPU: int8/fp16 host tables, in-graph codec RVQ (443 MB) 1 day ago