Automatic Speech Recognition
Transformers
PyTorch
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results
Instructions to use openai/whisper-large-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large-v3") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large-v3", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit History
-
Update Vaani-Benchmark-V1.0 eval: rename task_id Hindi_wer -> Hindi_WER
Verified signature605f03e
-
Add Vaani-Benchmark-V1.0 Hindi WER eval results
Verified signature8bc8056
-
Update README.md
Verified signature06f233f
-
Update README.md (#144)
Verified signature- Update README.md (29aee6b8a7c9c86b46f63bf6fc2331151935026b)afda370
-
Update README.md (#126)
Verified signature- Update README.md (1eaca33abac3ee283e44e20ac60f50fc304a7f66) Co-authored-by: Vaibhav Srivastav <reach-vb@users.noreply.huggingface.co>3d06185
-
Update forced decoder ids (#79)
Verified signature- Update forced decoder ids (f6811141b63c306e32c86041979f6a691bb62892)1ecca60
-
Make sure language detection is trigger by default (#75)
Verified signature- Make sure language detection is trigger by default (849bf26601bac5d2369a39ca99ba1f82acd21474)30c6d73
-
Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (#69)
Verified signature- Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (b232b5823f9842b7c3ea34af5638a65f33d31fb0)6cdf07a -
Update generation_config.json
Verified signatureacdaf85
-
Add max length to config (#38)
- Upload config (c77eb7bc546b7d8b03868f996435cb26d1a0a94e) Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>bf128ed -
Add max length to config (#38)
- Upload config (c77eb7bc546b7d8b03868f996435cb26d1a0a94e) Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>7d7979e
-
Correct suppress token (#27)
- Correct suppress token (1b4b47310bbb39307260071081c05632ffb8da91)9ee8ba8 -
Update config.json (#25)
- Update config.json (1f785283573a2d3ebdf42a00516bd3ac89cc6ed5) Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>9ef08b9 -
Speculative Decoding doesn't work yet with Whisper-v3 (#23)
- Speculative Decoding doesn't work yet with Whisper-v3 (3264a14fc680cf148949b17860f045ce2cf81edb)77b8369 -
Upload tokenizer.json (#16)
- Upload tokenizer.json (b22d3c1ef0effee40be83e83527a6413b96d33d1) Co-authored-by: Jonatan Kłosko <jonatanklosko@users.noreply.huggingface.co>cf8f9cf -
Fix error in config.json (#9)
- Fix error in config.json (e83208648cb6842c4004598c42de0c4b7ed57899) Co-authored-by: Per <pere@users.noreply.huggingface.co>ca3e273
-
Add normalizer.json to enable English Normalizer to work in existing pipelines (#14)
- Add normalizer.json to enable English Normalizer to work in existing pipelines (6cb5c60308de96a48086c7d705071274e1479f0f)f364131
-
Add fp32, flax weights (#5)
- add fp32 and flax (6760c4ad746f98dd2bcabe46e41e957fc8c39498) Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>1940b90 -
Update README (#6)
- Update README with langauge/task/timestamp info (7121cfc0bf874953f9a47845177517abf1e0940d) Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>4a83ae2 -
Update README.md
4b1ba05
-
Upload processor (#2)
- Upload processor (b634ee66a93a2f270ba8bfab680050a66dd096e4) Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>d8411bd -
Create README.md (#1)
- Create README.md (a8f19813aa40a07cd781e0b364d0568e80a24a0c) Co-authored-by: Vaibhav Srivastav <reach-vb@users.noreply.huggingface.co>f0e19c5 -
Duplicate from sanchit-gandhi/whisper-large-v3
Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>8a2a8a3