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

openai
/
whisper-small

Automatic Speech Recognition
Transformers
PyTorch
google-tensorflow TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Model card Files Files and versions
xet
Community
51

Instructions to use openai/whisper-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use openai/whisper-small with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("automatic-speech-recognition", model="openai/whisper-small")
    # Load model directly
    from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
    
    processor = AutoProcessor.from_pretrained("openai/whisper-small")
    model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-small")
  • Notebooks
  • Google Colab
  • Kaggle
whisper-small
3.87 GB
Ctrl+K
Ctrl+K
  • 9 contributors
History: 65 commits
sanchit-gandhi's picture
sanchit-gandhi
add special tokens for fast
59deef8 almost 3 years ago
  • .gitattributes
    1.44 kB
    Adding `safetensors` variant of this model (#30) almost 3 years ago
  • README.md
    20.2 kB
    update cv13 zero shot results about 3 years ago
  • added_tokens.json
    34.6 kB
    add timestamp tokens (#31) almost 3 years ago
  • config.json
    1.97 kB
    Add Flax weights over 3 years ago
  • flax_model.msgpack
    967 MB
    xet
    Add Flax weights over 3 years ago
  • generation_config.json
    3.84 kB
    Update generation config with word-level alignment heads (#29) almost 3 years ago
  • merges.txt
    494 kB
    Upload processor almost 4 years ago
  • model.safetensors
    967 MB
    xet
    Adding `safetensors` variant of this model (#30) almost 3 years ago
  • normalizer.json
    52.7 kB
    Upload tokenizer almost 4 years ago
  • preprocessor_config.json
    185 kB
    Update `return_mask` param over 3 years ago
  • pytorch_model.bin
    967 MB
    xet
    Upload WhisperForConditionalGeneration almost 4 years ago
  • special_tokens_map.json
    2.08 kB
    Changes for fast tokenizer (#11) over 3 years ago
  • tf_model.h5
    967 MB
    xet
    Add TF weights (#1) almost 4 years ago
  • tokenizer.json
    2.48 MB
    add special tokens for fast almost 3 years ago
  • tokenizer_config.json
    805 Bytes
    add timestamp tokens (#31) almost 3 years ago
  • vocab.json
    836 kB
    add special tokens for fast almost 3 years ago