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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Reza2kn
/
mega-asr-nvfp4

Automatic Speech Recognition
ONNX
Safetensors
modelopt
nvidia
nvfp4
blackwell
rtx-50
tensorrt-llm
asr
speech-recognition
robust-asr
quantized
4bit
awq
e2m1
qwen3
qwen3-asr
mega-asr
Model card Files Files and versions
xet
Community
mega-asr-nvfp4 / examples
2.64 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 8 commits
Reza2kn's picture
Reza2kn
NVFP4 AWQ-Lite Qwen3-ASR-1.7B (91.4% on VITW)
31e4b1c verified about 22 hours ago
  • distortion.wav
    353 kB
    xet
    NVFP4 AWQ-Lite Qwen3-ASR-1.7B (91.4% on VITW) about 22 hours ago
  • dropout.wav
    321 kB
    xet
    NVFP4 AWQ-Lite Qwen3-ASR-1.7B (91.4% on VITW) about 22 hours ago
  • echo.wav
    359 kB
    xet
    NVFP4 AWQ-Lite Qwen3-ASR-1.7B (91.4% on VITW) about 22 hours ago
  • far_field.wav
    284 kB
    xet
    NVFP4 AWQ-Lite Qwen3-ASR-1.7B (91.4% on VITW) about 22 hours ago
  • mixed.wav
    244 kB
    xet
    NVFP4 AWQ-Lite Qwen3-ASR-1.7B (91.4% on VITW) about 22 hours ago
  • noise.wav
    417 kB
    xet
    NVFP4 AWQ-Lite Qwen3-ASR-1.7B (91.4% on VITW) about 22 hours ago
  • obstructed.wav
    422 kB
    xet
    NVFP4 AWQ-Lite Qwen3-ASR-1.7B (91.4% on VITW) about 22 hours ago
  • recording.wav
    240 kB
    xet
    NVFP4 AWQ-Lite Qwen3-ASR-1.7B (91.4% on VITW) about 22 hours ago