Hugging Face's logo 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
/
x-asr-zh-en-streaming-zipformer2-gguf

Automatic Speech Recognition
GGUF
Chinese
English
rapidspeech
streaming
zipformer2
transducer
ggml
code-switching
Model card Files Files and versions
xet
Community
x-asr-zh-en-streaming-zipformer2-gguf / 160ms
631 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
Luigi's picture
Luigi
Add q3_k (imatrix, near-lossless, 69MB) + imatrix .dat calibration files
725856f verified about 2 months ago
  • imatrix-160ms.dat

    Pickle imports

    • No problematic imports detected

    What is a pickle import?

    123 kB
    xet
    Add q3_k (imatrix, near-lossless, 69MB) + imatrix .dat calibration files about 2 months ago
  • tokens.txt
    58.8 kB
    Add all 4 streaming chunk variants (f16 + Q4_K) + model card about 2 months ago
  • x-asr-zh-en-160ms-f16.gguf
    306 MB
    xet
    Add all 4 streaming chunk variants (f16 + Q4_K) + model card about 2 months ago
  • x-asr-zh-en-160ms-q3_k.gguf
    71.7 MB
    xet
    Add q3_k (imatrix, near-lossless, 69MB) + imatrix .dat calibration files about 2 months ago
  • x-asr-zh-en-160ms-q4_k.gguf
    89 MB
    xet
    Add all 4 streaming chunk variants (f16 + Q4_K) + model card about 2 months ago
  • x-asr-zh-en-160ms-q8_0.gguf
    164 MB
    xet
    Add Q8_0 variants (lossless: token-exact with f16, ~half size, ~1.2x faster on CPU) about 2 months ago