Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use openai/whisper-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-medium")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-medium") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-medium") - Notebooks
- Google Colab
- Kaggle
Update citation
#4
by sanchit-gandhi - opened
README.md
CHANGED
|
@@ -346,12 +346,14 @@ There are also potential dual use concerns that come with releasing Whisper. Whi
|
|
| 346 |
|
| 347 |
|
| 348 |
### BibTeX entry and citation info
|
| 349 |
-
*Since no official citation was provided, we use the following in the mean time*
|
| 350 |
```bibtex
|
| 351 |
-
@
|
| 352 |
-
|
| 353 |
-
|
| 354 |
-
|
| 355 |
-
|
|
|
|
|
|
|
|
|
|
| 356 |
}
|
| 357 |
```
|
|
|
|
| 346 |
|
| 347 |
|
| 348 |
### BibTeX entry and citation info
|
|
|
|
| 349 |
```bibtex
|
| 350 |
+
@techreport{radford22_whipser,
|
| 351 |
+
title="{Robust Speech Recognition via Large-Scale Weak Supervision}",
|
| 352 |
+
author={Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
|
| 353 |
+
journal={Technical Report, OpenAI},
|
| 354 |
+
url={https://cdn.openai.com/papers/whisper.pdf},
|
| 355 |
+
year={2022},
|
| 356 |
+
type={Technical report},
|
| 357 |
+
institution={OpenAI}
|
| 358 |
}
|
| 359 |
```
|