Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
English
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use openai/whisper-base.en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-base.en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-base.en") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-base.en", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (#17)
Verified signature- Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. (5f20981fe10ee9ca74131ec6ce4c7af029383b0f)911407f
-
Adding `safetensors` variant of this model (#13)
- Adding `safetensors` variant of this model (aba9b9f0008cfab6a230a1f18b7f5102c4d67614) Co-authored-by: Nicolas Patry <Narsil@users.noreply.huggingface.co>564c17e
-
Update generation config with word-level alignment heads (#12)
- Upload config (4e475376cc7623a0e9baf84df9ff091dbf934414)efd3751
-
Update README.md
1773a19
-
Update generation_config.json to suppress task tokens (#8)
- Update generation_config.json to suppress task tokens (dcc71d844d5f3bd7a2aedefe9b497945c5251ff3) Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.huggingface.co>98672e2 -
Update config.json to suppress task tokens (#7)
- Update config.json to suppress task tokens (6f34264878561a61feb7f97685595d60c4a50830) Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.huggingface.co>c1a81ce
-
Add Flax weights
sanchit-gandhi2ae9a06
-
Update README.md
6d5c61a
-
Update README.md (#6)
- Update README.md (f9729e6e3530494ca4c5a52b62261926a2e827b6)4b7b2ac
-
Changes for fast tokenizer (#5)
- Add tokenizer.json (188aef90df69b620ce6cfd6e40b9584aeeb26562) Co-authored-by: Jonatan Kłosko <jonatanklosko@users.noreply.huggingface.co>b1397f9
-
Update generation_config.json
c5e8f38 -
Update generation_config.json
0308e2c -
Upload config
e07573b
-
Revert: Add "<|startoftranscript|>" to forced decoder ids (#4)
- Revert: Add "<|startoftranscript|>" to forced decoder ids (8e01a999cd6cb3790d1c89a85bf8de6b2ccb7ba8)95a3107 -
Add "<|startoftranscript|>" to forced decoder ids (#3)
- Add "<|startoftranscript|>" to forced decoder ids (969fcd0a260f0ba98f049b3a396d85e36beb3052)c2efd02
-
Allow single quotes "'" and hyphens "-" (#2)
- Allow single quotes "'" and hyphens "-" (e2c101c33bb8cb33915ea296d953c8d004f9bf37) Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>6866d59
-
Update `max_length` param
c60f6aa -
Update `return_mask` param
e21fc35
-
Add TF weights (#1)
- Add TF weights (cfa0355f9e77b58f4328bbffeadfafaeb8107945)e634357 -
Update README.md
37e9ff5 -
Create README.md
4b2681e
-
Upload config
3fd0f54 -
Upload tokenizer
b562e46 -
Upload config
e41d381 -
Upload tokenizer
8ec47de -
Upload tokenizer
e20f2df -
Upload tokenizer
a386759 -
Upload tokenizer
b7db4da
-
Upload processor
2597ebe -
Upload config
e83c45a -
Upload processor
0f387fb -
Upload config
5718b15 -
Upload processor
9bf007f -
Upload processor
a208949 -
Upload config
8d87270
-
Upload tokenizer
ad2acfa -
Upload WhisperForConditionalGeneration
58f78f1 -
Upload processor
db6b9b8 -
Upload config
e82f11f
-
Upload processor
39e4785 -
Upload model
c2f3a65 -
initial commit
13aff91