Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use openai/whisper-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large") - Notebooks
- Google Colab
- Kaggle
Input error
#3
by mrJezy - opened
Running the example I came across to the following error, when trying to retrieve the logits using the model:
logits = model(input_features).logits
"ValueError: You have to specify either decoder_input_ids or decoder_inputs_embeds"
Hey, this is normal, the readme will be update soon!
Thanks! Appreciate your quick response!
Same issue for me,Then how do I execute it?
Same issue here. Any update?