Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use openai/whisper-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-base") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Upload tokenizer (#28)
Verified signature- Upload tokenizer (2ca60a10925b961f7b3f37ed3646fd8991bac3f6) Co-authored-by: Arthur Zucker <ArthurZ@users.noreply.huggingface.co>e37978b
-
Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (#29)
Verified signature- Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (cb43b73359c24a3a61933d2a5907b53bbb82c6de)8c1db9b
-
Adding `safetensors` variant of this model (#22)
- Adding `safetensors` variant of this model (15ec5e35b3b840df9eb2a22a2cea891bfd3ef763) Co-authored-by: Nicolas Patry <Narsil@users.noreply.huggingface.co>55ccf2b
-
Update generation config with word-level alignment heads (#21)
- Upload config (a88bbdb978d3e958941976fba9daba137e014903)4ced08d
-
Update README.md
ba19fed
-
Update generation_config.json to suppress task tokens (#15)
- Update generation_config.json to suppress task tokens (06a16cfbc9b1ae72e7b367b481dae39b8b5f69f5) Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.huggingface.co>89144d6 -
Update config.json to suppress task tokens (#14)
- Update config.json to suppress task tokens (7fdab9d2f6a49b1e56bb6e549448e0148e1054f8) Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.huggingface.co>4147011
-
Update the pad token (#12)
- Update the pad token (964738b17617eb1060873e4f7b371186a48f8caa) Co-authored-by: Nicolas Patry <Narsil@users.noreply.huggingface.co>4e31d12
-
Upload tokenizer.json (#11)
- Upload tokenizer.json (a216e1ddde75fbe924e49e58f870d90476fe724b)74356c9 -
Add Flax weights
sanchit-gandhi4495b69
-
Update README.md
3386a58
-
Changes for fast tokenizer (#7)
- Update tokens (cbad20c57e9c29a3ac3eefa2ee23e88c69f96bbf) - Add tokenizer.json (7527b64ee55cf354da2bd36a871313974cd36684) Co-authored-by: Jonatan Kłosko <jonatanklosko@users.noreply.huggingface.co>5815f0e -
change hebrew code from iw (deprecated) to he (#8)
- Changed iw (deprecated) to he (fb1e2e3e79be1fb6afe7961929ae4311bc5506f5) Co-authored-by: Altryne <altryne@users.noreply.huggingface.co>0471144
-
Update README.md
572322d
-
Update generation_config.json
1fd8045 -
Upload config
a6e17ac
-
Allow single quotes "'" and hyphens "-" (#4)
- Allow single quotes "'" and hyphens "-" (0953d8ba6f790ff1534c090792df9949efb99e46) Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>b985d09
-
fix erroneous ls result
267437e -
Update README.md
01ae41c
-
Update `max_length` param
2bfc825 -
Update `return_mask` param
4c5961a
-
Add TF weights (#1)
- Add TF weights (ad24b4a9c34e511edf01bcee1a3e55ad295619ac)e926f15 -
Update README.md
aac9b65 -
Update README.md
627ab1f -
Create README.md
5bf8253
-
Upload tokenizer
3ce9635 -
Upload config
d355a9d -
Upload tokenizer
92a6b39 -
Upload config
63cf4db -
Upload tokenizer
19298ff -
Upload config
dba9350 -
Upload tokenizer
70584d9 -
Upload config
c7c6962 -
Upload tokenizer
8cd15f1 -
Upload config
1da8b5e
-
Upload processor
269dda8 -
Upload config
af37e19 -
Upload processor
3a63553 -
Upload config
6eda03c -
Upload processor
bba0d91 -
Upload processor
e0b99c0 -
Upload config
b5ba29d
-
Upload tokenizer
6a7ad65
-
Upload tokenizer
6ae1e4d -
Upload WhisperForConditionalGeneration
0736aa9 -
Upload tokenizer
963e846 -
Upload WhisperForConditionalGeneration
8ab3a84 -
Upload processor
9949175