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-mlx

Automatic Speech Recognition
MLX
ONNX
Safetensors
asr
speech-recognition
robust-asr
quantized
int4
4bit
mixed-precision
dwq
on-device
apple-silicon
qwen3
qwen3-asr
mega-asr
Model card Files Files and versions
xet
Community

Instructions to use Reza2kn/mega-asr-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use Reza2kn/mega-asr-mlx with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir mega-asr-mlx Reza2kn/mega-asr-mlx
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps
  • LM Studio
mega-asr-mlx / mlx /llm-mixed8_4
1.6 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 6 commits
Reza2kn's picture
Reza2kn
Add mixed 8-bit attn + 4-bit MLP variant (92.2%)
b0f4547 verified about 13 hours ago
  • config.json
    44.1 kB
    Add mixed 8-bit attn + 4-bit MLP variant (92.2%) about 13 hours ago
  • generation_config.json
    128 Bytes
    Add mixed 8-bit attn + 4-bit MLP variant (92.2%) about 13 hours ago
  • model.safetensors
    1.59 GB
    xet
    Add mixed 8-bit attn + 4-bit MLP variant (92.2%) about 13 hours ago
  • model.safetensors.index.json
    49.7 kB
    Add mixed 8-bit attn + 4-bit MLP variant (92.2%) about 13 hours ago
  • tokenizer.json
    11.4 MB
    xet
    Add mixed 8-bit attn + 4-bit MLP variant (92.2%) about 13 hours ago
  • tokenizer_config.json
    1.37 kB
    Add mixed 8-bit attn + 4-bit MLP variant (92.2%) about 13 hours ago