Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use openai/whisper-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-tiny")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-tiny") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add missing merge to tokenizer (#40)
Verified signature- Add missing merge to tokenizer (decc97ac02d7286119b0c6447e042bbc894ad42f)169d4a4
-
Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (#39)
Verified signature- Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (d7840ba84c50969cd51c6cb79da312625c6e14d9)167c219
-
Update generation config with word-level alignment heads (#29)
- Upload config (ccda8cc8b137d58877e2235411384d4c6c90cfaf)1135fb8
-
Adding `safetensors` variant of this model (#14)
- Adding `safetensors` variant of this model (978a459c6c1fc7892bedc3bb481ac8fd61033b0e) Co-authored-by: Nicolas Patry <Narsil@users.noreply.huggingface.co>aaf41dd
-
Update README.md
ed50ab0 -
Update README.md
299b03b
-
Update generation_config.json to suppress task tokens (#11)
- Update generation_config.json to suppress task tokens (a02ea394f9cbca9b496cd8d351d0ed4c2f8edbb5) Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.huggingface.co>79aace4 -
Update config.json to suppress task tokens (#10)
- Update config.json to suppress task tokens (235da5827987d58d18cbddf5b9d39b93e9af19dc) Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.huggingface.co>3a57fe6
-
Update the pad token (#9)
- Update the pad token (c81434a0bf5416d998ca052af9a59d54987341c5) Co-authored-by: Nicolas Patry <Narsil@users.noreply.huggingface.co>a8d7651
-
Add Flax weights
sanchit-gandhi3025605
-
Update README.md
ada5a5d
-
change hebrew code from iw (deprecated) to he (#6)
- change hebrew code from iw (deprecated) to he (2f637251702bb9799886af508a2863d3584bbb1a) Co-authored-by: Altryne <altryne@users.noreply.huggingface.co>42189de
-
Update README.md (#7)
- Update README.md (3218f452197ec74016ec6011dad2f26e8e483e41) - up (e9ece4c60269bbf25d574ba764f21acaec095a47) - up (28aebf3e23b9cdb52b7ecc72d746ecb1509bb86c)38b4c8a
-
Changes for fast tokenizer (#5)
- Add tokenizer.json (dcca07232bfb1028e499333730f868b87fd3d043) - Update unknown token (8852c40b30c9b7b981faf4fa77167fd862fd5fdb) - Move <|endoftext|> from added_tokens.json to vocab.json (3e9581879a6134abfb58f5788096027dd1756a63) Co-authored-by: Jonatan Kłosko <jonatanklosko@users.noreply.huggingface.co>a179016
-
Update generation_config.json
bfeb067 -
Upload config
d2f590b
-
Allow single quotes "'" and hyphens "-" (#3)
- Allow single quotes "'" and hyphens "-" (a5796832d706e2ccafe86bdf823d50b75b4a6b2c) Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>5ab69db
-
Fix Syntax Error, close parenthesis. (#2)
- Fix Syntax Error, close parenthesis. (4204457610c9d68596a993f543b5ebd970ce44f1) Co-authored-by: steven tartakovsky <startakovsky@users.noreply.huggingface.co>f8fb469
-
add CV 11 hi results
4954caa
-
Update `max_length` param
8662dcd -
Update `return_mask` param
27a139f
-
Update README.md
ea73aed -
Add TF weights (#1)
- Add TF weights (ff14006adad7dfe98572f269c6f4eb6a6bd8b1bc)3910a69 -
Update README.md
1856a88 -
Update README.md
b28761d
-
Update README.md
6ee9f09 -
Create README.md
3e3f2e2
-
Upload tokenizer
0ce71a9 -
Upload config
cc0dc20 -
Upload tokenizer
e56482d -
Upload config
810c51a -
Upload tokenizer
faaff8f -
Upload config
8135e01 -
Upload tokenizer
de95790 -
Upload tokenizer
a85d084 -
Upload config
5df04e6 -
Upload tokenizer
a16fd86 -
Upload config
f4be1c1
-
Upload processor
f2536f1 -
Upload config
63ea017 -
Upload processor
3767537 -
Upload config
d327c9e -
Upload processor
45846a8 -
Upload processor
0996e56 -
Upload config
6dadadd
-
Upload tokenizer
c659245
-
Upload tokenizer
4c640cd -
Upload WhisperForConditionalGeneration
e314fcd