Hugging Face's logo

openai
/
whisper-small

Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Model card Files
xet
 Community
54
whisper-small

Commit History

  1. Add missing merge to tokenizer (#38)⁠

    sanchit-gandhi
    Verified signature
    973afd2

  1. Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (#37)⁠

    patrickvonplaten
    Verified signature
    998cb1a

  1. add special tokens for fast (#33)⁠

    sanchit-gandhi
    e34e8ae

  2. add timestamp tokens (#31)⁠

    sanchit-gandhi
    b93f5c7

  1. Adding `safetensors` variant of this model (#28)⁠

    sanchit-gandhi +1: Narsil
    4b5b137

  1. Adding `safetensors` variant of this model (#30)⁠

    sanchit-gandhi +1: Narsil
    1450e63

  1. Update generation config with word-level alignment heads (#29)⁠

    sanchit-gandhi
    15291b7

  1. update cv13 zero shot results

    sanchit-gandhi
    dc81969

  1. Update README with zero-shot cv13 results

    sanchit-gandhi
    3d64a9b

  1. Update README.md

    sanchit-gandhi
    f674449

  1. Update generation_config.json to suppress task tokens (#23)⁠

    sanchit-gandhi +1: guillaumekln
    e0bba93

  1. Update the pad token (#19)⁠

    sanchit-gandhi +1: Narsil
    358bfe9

  1. Upload tokenizer.json (#17)⁠

    ArthurZ HF Staff
    d767983

  2. Add Flax weights

    sanchit-gandhi
    2d276f0

  1. Update README.md

    sanchit-gandhi
    6fcee57

  1. Changes for fast tokenizer (#11)⁠

    ArthurZ +1: jonatanklosko HF Staff
    faaf572

  2. change hebrew code from iw (deprecated) to he (#13)⁠

    ArthurZ +1: altryne HF Staff
    2855749

  1. fix ls eval result

    sanchit-gandhi
    dd003eb

  2. Update README.md (#14)⁠

    sanchit-gandhi
    4de1c19

  1. Update generation_config.json

    ArthurZ HF Staff
    6353835

  2. Update generation_config.json

    ArthurZ HF Staff
    8b8afdb

  3. Update generation_config.json

    ArthurZ HF Staff
    d494e79

  4. Update generation_config.json

    ArthurZ HF Staff
    2a22f16

  5. Update generation_config.json

    ArthurZ HF Staff
    e6c46e3

  6. Update generation_config.json

    ArthurZ HF Staff
    c6413eb

  7. Update generation_config.json

    ArthurZ HF Staff
    496a60a

  8. Update generation_config.json

    ArthurZ HF Staff
    84ead71

  1. Update generation_config.json

    ArthurZ HF Staff
    dfa8dc1

  2. Update generation_config.json

    ArthurZ HF Staff
    1183ca3

  3. Upload config (#10)⁠

    ArthurZ HF Staff
    a5fe5bc

  1. Revert forced decoder ids (#6)⁠

    sanchit-gandhi
    ecd5620

  2. Add "<|startoftranscript|>" to forced decoder ids (#5)⁠

    sanchit-gandhi
    942e13b

  1. Allow single quotes "'" and hyphens "-" (#4)⁠

    ArthurZ +1: sanchit-gandhi HF Staff
    62e030d

  1. add CV 11 hi results

    sanchit-gandhi
    0cfcd5b

  1. Update `max_length` param

    ArthurZ HF Staff
    3514146

  2. Update `return_mask` param

    ArthurZ HF Staff
    b24b76a

  1. Add TF weights (#1)⁠

    amyeroberts
    d652565

  2. Update README.md

    ArthurZ HF Staff
    27ec1f6

  3. Update README.md

    ArthurZ HF Staff
    a30bd98

  4. Create README.md

    ArthurZ HF Staff
    57fb052

  1. Upload tokenizer

    ArthurZ HF Staff
    f609efc

  2. Upload config

    ArthurZ HF Staff
    ef307ff

  3. Upload tokenizer

    ArthurZ HF Staff
    4397c79

  4. Upload config

    ArthurZ HF Staff
    83f04f3

  5. Upload tokenizer

    ArthurZ HF Staff
    9d008e3

  6. Upload config

    ArthurZ HF Staff
    1cff2f3

  7. Upload tokenizer

    ArthurZ HF Staff
    d8437df

  8. Upload config

    ArthurZ HF Staff
    e776ca7

  9. Upload tokenizer

    ArthurZ HF Staff
    f20a372

  10. Upload config

    ArthurZ HF Staff
    1f90997